|
创作新主题 |
社区所有版块导航
DATA
| docker Elasticsearch |
WEB开发
| linux MongoDB Redis DATABASE NGINX 其他Web框架 web工具 zookeeper tornado NoSql Bootstrap js peewee Git bottle IE MQ Jquery |
机器学习
| 机器学习算法 |
产品
| 短视频 |
印度
| 印度 |
一周十大热门主题
点击阅读原文访问arxivdaily.com，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏等功能！
cs.LG 方向，今日共计253篇
大模型相关(38篇)
【1】Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction
标题：通过动态系统预测对LLM幻觉进行低成本黑匣子检测
链接：https://arxiv.org/abs/2605.05134
摘要：Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or external knowledge retrieval, we propose a new method that treats the LLM as a black-box dynamical system. By projecting LLM responses into a high-dimensional manifold via an embedding model, we characterize the resulting vector sequences as observable realizations of the model's latent state-space dynamics. Leveraging Koopman operator theory, we fit the transition operators for both factual and hallucinated regimes and define a differential residual score based on their respective prediction errors. To accommodate varying user requirements and domain-specific sensitivities, we introduce a preference-aware calibration mechanism that optimizes the classification threshold based on a small set of demonstrations. This approach enables low-cost hallucination detection in a single-sample pass, avoiding the need for secondary sampling or external grounding. Extensive testing across three data benchmarks demonstrates that our method achieves state-of-the-art performance with reduced resource overhead.
【2】Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation
标题：根据不完整医疗保健数据估计关节治疗效果：利用LLM驱动的进化MNAR插补进行时间原因规范化流程
链接：https://arxiv.org/abs/2605.05125
摘要：Target trial emulation (TTE) enables causal questions to be studied with observational data when randomized controlled trials (RCTs) are infeasible. Yet treatment-effect methods often address causal estimation, missingness, and temporal structure separately, limiting their robustness in electronic health records (EHRs), where time-varying confounding and missing-not-at-random (MNAR) biomarkers can reach 50%--80%. We propose a two-stage pipeline for treatment effect estimation from incomplete longitudinal EHRs. First, CausalFlow-T, a directed acyclic graph (DAG)-constrained normalizing flow with long short-term memory (LSTM)-encoded patient history, performs exact invertible counterfactual inference, avoiding approximation errors from variational inference and separating confounding through explicit causal structure. Ablations on four synthetic and one semi-synthetic benchmark with known counterfactuals show that DAG constraints and exact inference address distinct failure modes: neither compensates for the other. Second, because CausalFlow-T requires completed inputs, we introduce an LLM-driven evolutionary imputer that proposes executable imputation operators rather than individual entries, and evaluate it with three large language model (LLM) backends, including two open-source models. Across 30%--80% MNAR missingness, this imputer achieves the best pooled rank over biomarker and causal metrics, leading in point-wise accuracy and temporal extrapolation while preserving average treatment effect (ATE) recovery as statistical baselines degrade. On Swiss primary-care EHRs from adults with type 2 diabetes initiating a GLP-1 receptor agonist or SGLT-2 inhibitor, the pipeline estimates a per-protocol weight-loss difference of -0.98 kg [95% CI -1.01, -0.96] favoring GLP-1 receptor agonists, consistent with randomized evidence and obtained from realistically incomplete real-world EHRs.
【3】On the Hardness of Junking LLMs
标题：论垃圾LLM的难度
链接：https://arxiv.org/abs/2605.05116
备注：27 pages, 13 figures, 2 tables
摘要：Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction and optimizing small adversarial components (e.g., suffixes or prefixes). In this setting, prompt structure is fundamental for performance, and recent results show that even simple random search can achieve strong performance when combined with sophisticated prompt design. Recently, it has been observed that harmful behaviors can be elicited even without the adversarial prompt, relying solely on optimized token sequences. This suggests the existence of natural backdoors, i.e., token sequences naturally emerged during LLMs training that trigger unsafe outputs without any meaningful instruction. However, despite these observations, this setting remains largely unexplored, and in particular the hardness of finding natural backdoors has not been assessed yet. In this work, we provide a first proof-of-concept study investigating the hardness of this task, which we refer to as the junking problem. We formalize it as the problem of finding token sequences that maximize the probability of generating a target prefix of harmful responses, propose a greedy random-search method to assess is such sequences can be discovered easily. Our results show that this problem is harder than standard jailbreak attacks, confirming the importance of semantic information in prompt design. At the same time, we find that our simple strategy is sufficient to solve it with a high success rate, suggesting that natural backdoors are present and easily recoverable. Finally, through perplexity analysis, we observe that the discovered token sequences lie in low-probability regions of the model distribution, supporting the hypothesis that they emerged implicitly from the training process.
【4】Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
标题：LLM系统中的持续知识更新：通过多时间尺度记忆动态学习
链接：https://arxiv.org/abs/2605.05097
备注：Preprint. 9 pages, 2 figures
摘要：LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics.
【5】CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels
标题
：CuBridge：一个基于LLM的框架，用于理解和重建高性能注意力核心
链接：https://arxiv.org/abs/2605.05023
备注：Accepted to ACL 2026
摘要：Efficient CUDA implementations of attention mechanisms are critical to modern deep learning systems, yet supporting diverse and evolving attention variants remains challenging. Existing frameworks and compilers trade performance for flexibility, while expert-written kernels achieve high efficiency but are difficult to adapt. Recent work explores large language models (LLMs) for GPU kernel generation, but prior studies report unstable correctness and significant performance gaps for complex operators such as attention. We present CuBridge, an LLM-based framework that adapts expert-written attention kernels through a structured lift-transfer-lower workflow. CuBridge starts from expert-written CUDA attention kernels and lifts them into an executable intermediate representation that makes execution orchestration explicit while abstracting low-level CUDA syntax. Given a user-provided PyTorch specification, CuBridge generates and verifies a target IR program, then reconstructs optimized CUDA code via reference-guided lowering. Across diverse attention variants and GPU platforms, CuBridge consistently produces correct kernels and substantially outperforms general frameworks, compiler-based approaches, and prior LLM-based methods.
【6】KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
标题：KernelBench-X：评估LLM生成的图形处理器内核的综合基准
链接：https://arxiv.org/abs/2605.04956
摘要：LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capability break down, and why? We present KernelBench-X, a benchmark designed to answer this question through category-aware evaluation of correctness and hardware efficiency across 176 tasks in 15 categories. Our systematic comparison of five representative methods yields three main findings. First, task structure determines correctness more than method design. Category explains nearly three times more variance in semantic correctness than method (9.4% vs 3.3% explained deviance), and 72% of Fusion tasks fail across all five methods while Math tasks are solved consistently. Second, iterative refinement improves correctness, but not performance. Across GEAK iterations, compile rate rises from 52.3% to 68.8% while average speedup declines from $1.58\times$ to $1.44\times$; newly rescued kernels consistently underperform persistently correct ones ($1.16\times$ vs $1.58\times$ speedup in round~0$\to$1). Third, correctness does not imply efficiency. 46.6% of correct kernels are slower than the PyTorch eager baseline, and cross-hardware speedup variance reaches $21.4\times$. Besides, quantization remains completely unsolved (0/30 successes) despite non-trivial compilation rates, revealing systematic misunderstanding of numerical computation contracts rather than surface-level syntax errors. These findings suggest that future progress depends on handling global coordination, explicitly modeling numerical precision, and incorporating hardware efficiency into generation. The code is available at https://github.com/BonnieW05/KernelBenchX
【7】Rethinking Local Learning: A Cheaper and Faster Recipe for LLM Post-Training
标题：重新思考本地学习：LLM后训练更便宜、更快的食谱
链接：https://arxiv.org/abs/2605.04913
备注：33pages
摘要：LLM post-training typically propagates task gradients through the full depth of the model. Although this end-to-end structure is simple and general, it couples task adaptation to full-depth activation storage, long-range backward dependencies and direct task-gradient access to pretrained representations. We argue that this full-depth backward coupling can be unnecessarily expensive and intrusive, particularly when post-training supervision is much narrower than pre-training. To this end, we propose \textbf{LoPT}: Local-Learning Post-Training, a simple post-training strategy that makes gradient reach an explicit design choice. LoPT places a single gradient boundary at the transformer midpoint: the second-half block learns from the task objective, while the first-half block is updated by a lightweight feature-reconstruction objective to preserve useful representations and maintain interface compatibility. LoPT shortens the task-induced backward path while limiting direct interference from narrow task gradients on early-layer representations. Extensive experiments demonstrate that LoPT achieves competitive performance with lower memory cost, higher training efficiency and better retention of pretrained capabilities. Our code is available at: https://github.com/HumyuShi/LoPT
【8】Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
标题：基于Delta的神经架构搜索：通过代码差异进行LLM微调
链接：https://arxiv.org/abs/2605.04903
备注：19 pages, 4 figures, 7 tables
摘要：Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs (deltas) to refine baseline architectures rather than synthesizing entire models. Our pipeline iteratively fine-tunes the LLM via LoRA on curated architectures from the LEMUR dataset, with MinHash-Jaccard novelty filtering for structural diversity. We evaluate three 7B-class LLMs -- DeepSeek-Coder-7B, Qwen2.5-Coder-7B, and Mistral-7B -- across six datasets (CIFAR-10, CIFAR-100, MNIST, SVHN, ImageNette, CelebA) using a 22-cycle protocol (1,100 candidates per LLM). All three substantially surpass the full-generation baseline (50.6% valid rate, 42.3% mean first-epoch accuracy): DeepSeek-Coder reaches 75.3% valid rate and 65.8% mean accuracy; Qwen2.5-Coder 72.1%/64.6%; Mistral 66.6%/66.1%. On CIFAR-10, best first-epoch accuracies reach 85.5% (Mistral), 85.2% (DeepSeek), 80.6% (Qwen) -- well above 63.98% full generation and 71.5% for the concurrent approach of Gu et al. Output lengths are 30-50 lines versus 200+ for full generation (75-85% reduction). A 50-epoch study confirms the 1-epoch proxy preserves rankings (Mistral: Spearman $ρ$ = 0.926). Delta-based generation is a token-efficient, multi-domain, LLM-agnostic alternative to full-model synthesis for LLM-driven NAS.
【9】A geometric relation of the error introduced by sampling a language model's output distribution to its internal state
标题：对语言模型的输出分布进行抽样所引入的误差与其内部状态的几何关系
链接：https://arxiv.org/abs/2605.04899
备注：12 Pages, 10 Figures, 2 Appendices. To appear in Proceedings of ICML 2026
摘要
：GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multiple tokens. Viewing this sensitivity as a geometric property, we derive an $\mathfrak{so}(n)$-valued 1-form that depends only on the geometry of the token embeddings. Despite this purely geometric origin, we show that its curvature is semantically meaningful: On chess reasoning tasks, the curvature couples to the world model of an off-the-shelf instruction-tuned model, with transformations clustering by board region and respecting piece importance. Our findings suggest that token space geometry directly reflects how models internally represent problems.
【10】FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection
标题：FairEnc：一个具有公平视野和文本编码器的公平视野语言模型，用于青光眼检测
链接：https://arxiv.org/abs/2605.04882
摘要：Automated glaucoma detection is critical for preventing irreversible vision loss and reducing the burden on healthcare systems. However, ensuring fairness across diverse patient populations remains a significant challenge. In this paper, we propose FairEnc, a fair pretraining method for vision-language models (VLMs) that enables simultaneous debiasing across multiple sensitive attributes. FairEnc jointly mitigates biases in both textual and visual modalities with respect to multiple sensitive attributes, including race, gender, ethnicity, and language. Specifically, for the textual encoder, we leverage a large language model to generate synthetic clinical descriptions with varied sensitive attributes while preserving disease semantics, and employ a contrastive alignment objective to encourage demographic-invariant representations. For the visual encoder, we propose a dual-level fairness strategy that combines mutual information regularization to reduce statistical dependence between learned features and demographic groups, with multi-discriminator adversarial debiasing. Comprehensive experiments on the publicly available Harvard-FairVLMed dataset demonstrate that FairEnc effectively reduces demographic disparity as measured by DPD and DEOdds while achieving strong diagnostic performance under both zero-shot and linear probing evaluations. Additional experiments on the private FairFundus dataset show that FairEnc consistently preserves fairness advantages under cross-domain and cross-modality settings and maintains diagnostic performance within a competitive range. These results highlight FairEnc's ability to generalize fairness under distribution shifts, supporting its potential for more equitable deployment in real-world clinical settings. Our codebase and synthetic clinical notes are available at https://github.com/Mohamed-Elhabebe/FairEnc
【11】Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models
标题：多模式大型语言模型的不确定性探索性直接偏好优化
链接：https://arxiv.org/abs/2605.04874
摘要：Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) by learning from preference pairs. One of its key challenges lies in how to transfer the sequence-level preference into fine-grained supervision on visual fidelity. To safeguard vision-related tokens that are prone to hallucination, existing methods typically allocate training emphasis according to the model's self-assessed visual sensitivity signals. However, such sensitivity, estimated by a model still under training, introduces self-referential bias: reinforcing already well-learned visual cues while neglecting hard-to-perceive but critical details, thereby limiting deeper alignment. In this work, we propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for MLLMs, which enables the model to uncover its cognitive deficiencies and actively explore for self-correction, guided by token-level epistemic uncertainty. Specifically, we first quantify the uncertainty from the model's failure to ground token predictions in the given image. Then, based on an uncertainty-aware exploration intensity, we encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples. Further, we provide a theoretical justification for our method, and extensive experiments demonstrate its effectiveness and robustness.
【12】Gyan: An Explainable Neuro-Symbolic Language Model
标题：Gyan：一种可解释的神经符号语言模型
链接：https://arxiv.org/abs/2605.04759
备注：also submitted to NeurIPS 2026
摘要：Transformer based pre-trained large language models have become ubiquitous. There is increasing evidence to suggest that even with large scale pre-training, these models do not capture complete compositional context and certainly not, the full human analogous context. Besides, by the very nature of the architecture, these models hallucinate, are difficult to maintain, are not easily interpretable and require enormous compute resources for training and inference. Here, we describe Gyan, an explainable language model based on a novel non-transformer architecture, without any of these limitations. Gyan achieves SOTA performance on 3 widely cited data sets and superior performance on two proprietary data sets. The novel architecture decouples the language model from knowledge acquisition and representation. The model draws on rhetorical structure theory, semantic role theory and knowledge-based computational linguistics. Gyan's meaning representation structure captures the complete compositional context and attempts to mimic humans by expanding the context to a 'world model'. AI model adoption critically depends on trust and transparency especially in mission critical use cases. Collectively, our results demonstrate that it is possible to create models which are trustable and reliable for mission critical tasks. We believe our work has tremendous potential for guiding the development of transparent and trusted architectures for language models.
【13】OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
标题：SSAQ：离群值自吸收实现准确低位LLM量化
链接：https://arxiv.org/abs/2605.04738
备注：ICML 2026
摘要：Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising solution by reducing model size and accelerating token generation through alleviating the memory-bound issue. Nevertheless, the presence of inherent systematic outliers in weights continues to be a major obstacle. While existing methods, such as scaling and rotation, attempt to address this issue, the performance remains unsatisfactory. In this paper, we propose Outlier Self-Absorption Quantization (OSAQ), which performs additive weight suppression guided by the second-order low-rank property for low-bit weight-only quantization of LLMs. Specifically, we observe that the Hessian exhibits low-rank consistency across different inputs, with certain directions consistently showing vanishing curvature. Leveraging this property, we identify a stable null space of the Hessian and then construct an additive weight transformation by linearly combining the vectors within this null space, thereby suppressing weight outliers without affecting the task loss. This additive transformation can be absorbed into the weights offline, requiring no inter-layer transformations and introducing no inference overhead. Moreover, the construction is efficiently achieved by a closed-form solution, without resource-intensive training or iterative procedures. Extensive experiments demonstrate that OSAQ effectively suppresses outliers and enhances low-bit quantization performance. For instance, in 2-bit quantization, OSAQ, when integrated with GPTQ, achieves over 40% lower perplexity compared to vanilla GPTQ.
【14】Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
标题：稀疏令牌就足够了：通过令牌感知梯度优化越狱音频语言模型
链接：https://arxiv.org/abs/2605.04700
摘要：Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work, we investigate the necessity of such dense optimization by analyzing the structure of token-aligned gradients in ALMs. We find that gradient energy is highly non-uniform across audio tokens, indicating that only a small subset of token-aligned audio regions dominates the optimization signal. Motivated by this observation, we propose Token-Aware Gradient Optimization (TAGO), which enables sparse jailbreak optimization by retaining only waveform gradients aligned with audio tokens that have high gradient energy, while masking the remaining gradients at each iteration. Across three ALMs, TAGO outperforms baselines, and substantial sparsification preserves strong attack success rates (e.g. on Qwen3-Omni, $\mathrm{ASR}_{l}$ remains at 86% with a token retention ratio of 0.25, compared to 87% with full token retention). These results demonstrate that dense waveform updates are largely redundant, and we advocate that future audio jailbreak and safety alignment research should further leverage this heterogeneous token-level gradient structure.
【15】A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints
标题：具有KV缓存内存约束的LLM推理稳定性分析的排队理论框架
链接：https://arxiv.org/abs/2605.04595
备注：Accepted in ICML 2026
摘要：The rapid adoption of large language models (LLMs) has created significant challenges for efficient inference at scale. Unlike traditional workloads, LLM inference is constrained by both computation and the memory overhead of key-value (KV) caching, which accelerates decoding but quickly exhausts GPU memory. In this paper, we introduce the first queueing-theoretic framework that explicitly incorporates both computation and GPU memory constraints into the analysis of LLM inference. Based on this framework, we derive rigorous stability and instability conditions that determine whether an LLM inference service can sustain incoming demand without unbounded queue growth. This result offers a powerful tool for system deployment, potentially addressing the core challenge of GPU provisioning. By combining an estimated request arrival rate with our derived stable service rate, operators can calculate the necessary cluster size to avoid both costly over-purchasing and performance-violating under-provisioning. We further validate our theoretical predictions through extensive experiments in real GPU production environments. Our results show that the predicted stability conditions are highly accurate, with deviations typically within 10%.
【16】From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
标题：从参数动态到风险评分：量化LLM微调中的样本级安全降级
链接：https://arxiv.org/abs/2605.04572
备注：Accepted by ICML 2026
摘要：Safety alignment of Large Language Models (LLMs) is extremely fragile, as fine-tuning on a small number of benign samples can erase safety behaviors learned from millions of preference examples. Existing studies attempt to explain this phenomenon by comparing parameters and hidden states before and after fine-tuning, but overlook their dynamic evolution during fine-tuning. In this paper, we uncover a critical mechanism underlying safety degradation by analyzing parameter dynamics, where benign fine-tuning causes parameters to cumulatively drift toward danger-aligned directions, progressively undermining the model's safety. This finding suggests that samples contributing more to this drift has greater fine-tuning risks. Based on this insight, we propose a method of Sample-Level Quantification of Safety Degradation (SQSD), which quantifies the influence of each training sample on safety degradation. Specifically, SQSD computes continuous risk scores to samples by measuring their induced parameter updates' projection difference between danger and safety directions. Extensive experiments across multiple models and datasets demonstrate that SQSD effectively quantifies sample-level fine-tuning risks and exhibits strong transferability across model architectures, parameter scales, and parameter-efficient methods.
【17】Benchmarking LLMs on the Massive Sound Embedding Benchmark (MSEB)
标题：对LLM进行大规模声音嵌入基准（MSEB）的基准
链接：https://arxiv.org/abs/2605.04556
摘要：The Massive Sound Embedding Benchmark (MSEB) has emerged as a standard for evaluating the functional breadth of audio models. While initial baselines focused on specialized encoders, the shift toward "audio-native" Large Language Models (LLMs) suggests a new paradigm where a single multimodal backbone may replace complex, task-specific pipelines. This paper provides a rigorous empirical evaluation of leading LLMs - including members from the Gemini and GPT families - across the eight core MSEB capabilities to assess their efficacy and audio-text parity. Our results indicate that while a significant modality gap persists regarding performance and robustness, the empirical evidence for an "optimal" modeling approach remains inconclusive. Ultimately, the choice between audionative and cascaded architectures depends heavily on specific use-case requirements and the underlying assumptions regarding latency, cost, and reasoning depth.
【18】RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation
标题：RaguTeam参加SemEval-2026任务8：Meno和Friends参加经过评审的LLM竞赛，以产生忠实的多转弯响应
链接：https://arxiv.org/abs/2605.04523
摘要：We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval
【19】Automated Formal Proofs of Combinatorial Identities via Wilf-Zeilberger Guidance and LLMs
标题：通过Wilf-Zeilberger指导和LLM实现组合身份的自动形式证明
链接：https://arxiv.org/abs/2605.04472
备注
：Accepted to ICML 2026. Preprint version
摘要：Automating formal proofs of combinatorial identities is challenging for LLM-based provers, as long-horizon proof planning is required and unconstrained search quickly explodes. Symbolic methods such as the Wilf-Zeilberger (WZ) method can achieve a mechanized proof of combinatorial identities by constructing special auxiliary functions and demonstrating that they satisfy specific recurrence relations. We propose WZ-LLM, a neuro-symbolic framework that turns WZ proof plans into executable proof sketches in Lean 4 and uses an LLM-based prover to discharge the resulting machine-checkable subgoals. We also train a dedicated WZ-Prover via a Lean-kernel-verified bootstrapping loop with expert-verified iteration, followed by DAPO-based refinement. Experiments show that WZ-LLM achieves a 34% proof success rate on LCI-Test (100 classic combinatorial identities), outperforming strong baselines such as DeepSeek-V3 and Goedel-Prover-V2, and delivering consistent gains on CombiBench and PutnamBench-Comb. These results indicate that our framework provides two complementary strengths: improved direct proving for identities beyond the scope of WZ, and substantially higher end-to-end success when WZ sketches guide a specialized prover.
【20】Stabilizing LLM Supervised Fine-Tuning via Explicit Distributional Control
标题：通过显式分布式控制稳定LLM监督微调
链接：https://arxiv.org/abs/2605.04468
摘要：Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by excessive distributional drift during optimization. Motivated by this perspective, we propose Anchored Learning, a simple framework that explicitly controls distributional updates during offline fine-tuning via a dynamically evolving moving anchor. Instead of matching a fixed reference distribution, the anchor interpolates between the current model and a frozen reference to construct an intermediate target that the model distills toward, transforming global fine-tuning into a sequence of local trust-region updates in distribution space. Theoretically, we prove this anchor-based update admits a linear KL-divergence upper bound per iteration, ensuring a stable transition between model distributions. Extensive experiments on iGSM, MedCalc, and IFEval show that Anchored Learning consistently lies on the Pareto frontier of gain-stability trade-offs, achieving near-optimal performance improvements while substantially reducing degradation compared to strong baselines. For example, while standard SFT suffers from over 53% performance degradation on iGSM and MedCalc, Anchored Learning slashes this drop to under 5% while maintaining near-optimal gains (e.g., 75.2% on iGSM).
【21】Demystifying Manifold Constraints in LLM Pre-training
标题：揭开LLM预训练中的多种约束的神秘面纱
链接：https://arxiv.org/abs/2605.04418
摘要：The empirical success of large language model (LLM) pre-training relies heavily on heuristic stabilization techniques, such as explicit normalization layers and weight decay. While recent constrained optimization approaches that explicitly restrict weights may improve numerical stability and performance, the mechanism and motivation for adding constraints still remain elusive. This paper systematically demystifies the role of explicit manifold constraints in LLM pre-training. By introducing the Msign-Aligned Constrained Riemannian Optimizer (MACRO)-a provably convergent, single-loop optimization framework-our study disentangles weight regularization heuristics from interacting mechanisms like RMS normalization and decoupled weight decay. Theoretical analyses and comprehensive empirical evaluations reveal that manifold constraints independently bound forward activation scales and enforce stable rotational equilibrium, thereby subsuming the roles of these heuristic mechanisms. Evaluations on large-scale LLM architectures demonstrate that MACRO achieves highly competitive performance while rigorously preserving the theoretical guarantees of exact Riemannian optimization.
【22】Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs
标题：Coral：通过异类云图形处理器提供经济高效的多LLM服务
链接：https://arxiv.org/abs/2605.04357
摘要：The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver comparable performance per dollar to top-tier hardware. To efficiently harness these heterogeneous resources for serving multiple LLMs concurrently, we introduce Coral, an adaptive heterogeneity-aware multi-LLM serving system. The key idea behind Coral is to jointly optimize resource allocation and the serving strategy of each model replica across all models. To keep pace with shifting throughput demand and resource availability, Coral applies a lossless two-stage decomposition that preserves joint optimality while cutting online solve time from hours to tens of seconds. Our evaluation across 6 models and 20 GPU configurations shows that Coral reduces serving cost by up to 2.79$\times$ over the best baseline, and delivers up to 2.39$\times$ higher goodput under scarce resource availability.
【23】Efficiently Aligning Language Models with Online Natural Language Feedback
标题：使用在线自然语言反馈有效地对齐语言模型
链接：https://arxiv.org/abs/2605.04356
摘要：Reinforcement learning with verifiable rewards has been used to elicit impressive performance from language models in many domains. But, broadly beneficial deployments of AI may require us to train models with strong capabilities in "fuzzy", hard-to-supervise domains. In this paper, we develop methods to align language models in fuzzy domains where human experts are still able to provide high-quality supervision signal, but only for a small number of model outputs, using online natural language feedback. Specifically, we train models by iteratively optimizing against proxy reward signals, stopping at the point of over-optimization, collecting fresh expert supervision, and updating the proxy reward. We construct proxy reward models from language models using in-context learning (ICL) and fine-tuning. We test our methods by eliciting creative writing and alignment research capabilities in Qwen3-8B and Haiku 4.5 respectively. For Qwen3-8B, ICL methods recover up to 35% of performance with 50x fewer expert samples, while fine-tuning methods recover 80% with up to 20x fewer samples and 100% with 3x fewer samples. For Haiku 4.5, ICL methods recover up to 35% of performance with 30x fewer samples, and fine-tuning methods recover 100% with 10x fewer samples. Our results suggest that online natural language feedback can substantially improve the data efficiency of expert supervision.
【24】Probing Structural Mathematical Reasoning in Language Models with Algebraic Trapdoors
标题：用代数陷阱门探索语言模型中的结构数学推理
链接：https://arxiv.org/abs/2605.04352
摘要
：We introduce a benchmark suite for evaluating structural mathematical reasoning in language models, built on subgroup-construction problems in SL(3, Z) with cryptographic-style verifier-prover asymmetry. Each instance presents a finitely generated subgroup as a list of integer matrices and asks for an arithmetic invariant -- index, surjection-at-prime, or membership -- that the construction-time information (N, K) pins down in O(1) closed form, but that the solver, lacking that information, must derive by either Aschbacher-classification analysis or by a membership query in SL(3, Z) of unknown decidability. The benchmark therefore distinguishes models with internalized algebraic priors (Aschbacher classes, McLaughlin's theorem, Property (T), the congruence subgroup property) from models that rely on general-purpose computation. We report empirical results across five representative reasoning traces from two state-of-the-art models. The headline result: on the index variant, one model spent 152 minutes of reasoning, explicitly identified the kernel-side membership question as the bottleneck, attempted constructive verification, and abstained with "DON'T KNOW" rather than commit to its computed cokernel candidate -- demonstrating calibrated meta-cognition on the open-decidability boundary that the benchmark was designed to probe. We argue that the benchmark exposes a four-way classification of model behavior (commit-correct, commit-wrong, abstain-correct, abstain-wrong) that standard answer-key scoring conflates.
【25】LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy
标题：通过自适应共形语义熵实现LLM不确定性量化
链接：https://arxiv.org/abs/2605.04295
备注：Accepted for publication in the Proceedings of IJCAI 2026, the 35th International Joint Conference on Artificial Intelligence, 12 Pages
摘要：LLMs' overconfidence, particularly when hallucinating, poses a significant challenge for the deployment of the models in safety-critical settings and makes a reliable estimation of uncertainty necessary. Existing approaches for uncertainty quantification typically prioritize lexical or probabilistic measures; however, these techniques often ignore the semantic variance of different responses with similar meaning. In this paper, we propose Adaptive Conformal Semantic Entropy (ACSE), a method for estimating prompt-level uncertainty by adaptively measuring semantic dispersion in LLMs outputs. Our uncertainty scoring function is based on clustering semantic entropy of multiple diverse responses to the same prompt. The function adaptively adjusts the uncertainty score based on semantic features of each cluster. To ensure statistical reliability of our score, we use conformal calibration to apply a decision rule to accept/abstain the prompts, providing a finite-sample, distribution-free guarantee such that the error rate among the accepted responses remains bounded by a user-specified tolerance. Our extensive experimental evaluations using different LLMs and datasets, demonstrate that our approach consistently outperforms state-of-the-art uncertainty quantification baselines using discriminative performance, conformal guarantees, and probabilistic calibration indicators. As a highlight, for TriviaQA dataset, AUROC of our approach is 0.88 compared to 0.65 produced by the token entropy approach.
【26】Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
标题：利用预训练语言模型作为Glauber Dynamics文本扩散的能量函数
链接：https://arxiv.org/abs/2605.04291
备注：To appear in ACL 2026
摘要：We present a discrete diffusion-based language model using Glauber dynamics from statistical physics. Our main insight is that instead of trying to train a discrete state space diffusion model using Glauber dynamics with a uniform transition kernel as the forward process, one can set up an ``energy function'' based on pretrained causal/masked language models. When viewed as the stationary distribution, this energy function allows us to significantly improve the quality of the generated text. Incorporating UL2 as the pretrained model into our diffusion pipeline, we outperform prior diffusion based LMs and perform competitively with autoregressive models of comparable model sizes. Furthermore, our models are competitive with or outperform prior diffusion models and GPT-2 style auto-regressive models on zero-shot common sense reasoning tasks as well as planning and search tasks like Sudoku and Zebra puzzles.
【27】Adaptive Consensus in LLM Ensembles via Sequential Evidence Accumulation: Automatic Budget Identification and Calibrated Commit Signals
标题：通过顺序证据积累在LLM集成中实现自适应共识：自动预算识别和校准的承诺信号
链接：https://arxiv.org/abs/2605.04236
摘要：Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-budget methods cannot detect this boundary. Extended-thinking architectures compound the problem: a wrong answer after 120k tokens is indistinguishable from a correct one. We introduce DASE (Deliberative Adaptive Stopping Ensemble), a stopping heuristic for iterative ensemble deliberation that commits early on genuine consensus and applies a global-frequency fallback on fragmented evidence. Two configurations are evaluated: a persistence heuristic and DASE-Spatial (arena half-width W). Three contributions. (1) DASE produces a commit-type routing partition complementary to verbalized single-call confidence. On a contamination-controlled corpus (AIME 2010-2023, N=254, 3 seeds), a 120B ensemble achieves a 24.8 pp routing gap (right-wall 97.1% vs. left-wall 73.6%), statistically equivalent to Opus 4.6 Standard verbalized confidence at coverage-matched threshold (25.7 pp gap; bootstrap CI on difference: [-12.0, +10.3] pp, p=0.873). The two mechanisms disagree on 27% of routing assignments, establishing them as complements rather than substitutes; every DASE decision is accompanied by a machine-readable deliberation record. (2) Adaptive stopping, not injection bandwidth, drives accuracy gains. On AIME-300, bandwidth accounts for only 0.3 pp (ns); on GPQA-Extended, 4.4 pp bandwidth versus 5.0 pp stopping effect. DASE-Spatial ties Debate-Dense at its optimal budget using one-tenth the injection bandwidth and identifies that budget automatically; W=8 (65.0%) significantly outperforms W=4 (59.3%) on AIME-300 (adj p=0.0042). (3) Injection-based methods exhibit a retrospective accuracy-vs-inference inverted-U on both benchmarks; this pattern is hypothesis-generating for future work.
【28】Predict-then-Diffuse: Adaptive Response Length for Compute-Budgeted Inference in Diffusion LLMs
标题：预测然后扩散：扩散LLM中计算推理的自适应响应长度
链接：https://arxiv.org/abs/2605.04215
摘要
：Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead to significant throughput advantages and superior GPU utilization over traditional autoregressive paradigm. However, this parallelism is constrained by the requirement of a fixed-size response length prior to generation. This architectural limitation imposes a severe trade-off: oversized response length results in computational waste on semantically meaningless padding tokens, while undersized response length cause output truncation requiring costly re-computations that introduce unpredictable latency spikes. To tackle this issue, we propose Predict-then-Diffuse, a simple and model-agnostic framework, that enables compute-budgeted inference per input query by first estimating the response length and then using it to run inference with D-LLM. At its core lies a Adaptive Response Length Predictor (AdaRLP) auxiliary predictor that predicts the optimal response length given an input query. As a measure against under-predicting the response length and re-running inference with a higher response length, we introduce a data-driven safety mechanism, which trades a negligible padding overhead. As a whole, our framework limits the significant waste of computation on padding tokens and preserves output quality. Experimental validation on multiple datasets demonstrate that Predict-then-Diffuse significantly reduces computational costs (FLOP) compared to the default D-LLM inference mechanism and baselines based on heuristics, while being robust to skewed data distributions.
【29】Are LLMs Ready for Conflict Monitoring? Empirical Evidence from West Africa
标题：LLM准备好进行冲突监控了吗？来自西非的经验证据
链接：https://arxiv.org/abs/2605.04177
摘要：As LLMs enter conflict monitoring, understanding systematic distortions in their outputs is critical for humanitarian accountability. We evaluate four vanilla open-weight models Gemma 3 4B, Llama 3.2 3B, Mistral 7B, and OLMo 2 7B and two domain-adapted models, AfroConfliBERT and AfroConfliLLAMA, on Nigeria and Cameroon conflict-event classification against ACLED, a gold-standard dataset with multi-stage verification. We find a bifurcated divergence in normative directionality. Open-weight models exhibit statistically significant False Illegitimation bias: Gemma misclassifies to 18.29% of legitimate battles as civilian-targeted violence while making zero False Legitimation errors. By contrast, AfroConfliBERT and AfroConfliLLAMA achieve near-directional neutrality, with Legitimization Bias differences indistinguishable from zero. Yet domain adaptation does not eliminate actor-based selection bias. Both adapted models show statistically significant actor bias comparable to vanilla LLMs; in Nigeria, state actors are legitimized 36.5% more often than non-state actors in identical tactical contexts. Open-weight outputs are also fragile to geography-specific lexical framing: delegitimizing phrases produce flip rates up to 66.7% in Cameroon and 34.2% in Nigeria, while perturbations salient in one context may not matter in another. Error trace profiling shows models mask normative bias through unfaithful rationale confabulations. In contrast, AfroConfliBERT and AfroConfliLLAMA are largely robust, with near-zero flip rates across perturbation categories. Overall, current models are not ready for unsupervised deployment in conflict monitoring. We call for fairness-aware fine-tuning to reduce actor-based selection bias, mandatory adversarial robustness evaluation against lexical manipulation, and context-specific human-in-the-loop oversight calibrated to regional difficulty.
【30】FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression
标题：FASQ：用于免校准LLM压缩的灵活加速子空间量化
链接：https://arxiv.org/abs/2605.04084
摘要：Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically requires calibration data. We present FASQ (Flexible Accelerated Subspace Quantization), a calibration-free framework that applies product quantization to LLM weight matrices. By tuning two parameters, sub-vector size and codebook cardinality, FASQ exposes a continuous design space spanning 27-49% of the original FP16 model size, filling compression gaps that fixed-bit schemes cannot reach. On Meta-Llama-3-8B, FASQ surpasses 4-bit GPTQ and AWQ in accuracy (67.1-67.7 avg.) at 37-42% model size, with consistent results on Qwen3-8B and Qwen3.5-9B-Base. To make product quantization practical at inference time, we design custom CUDA kernels: a LUT-free direct-compute GEMV for decode and an output-stationary double-buffered LUT GEMM for prefill, both with split-K parallelism. On an RTX~3090, FASQ achieves 45.2 tok/s decode at effective 4-bit (2.56x memory reduction) and 51.8 tok/s at effective 3-bit (2.80x), both surpassing FP16 tensor-core performance (43.9 tok/s) and delivering 1.6 to 1.8x the throughput of AWQ, 2.5 to 2.5x of GPTQ, and 4.3 to 5x of RTN. FASQ is the only compressed method that accelerates decode beyond FP16, offering calibration-free compression, continuous size-quality trade-offs, and real-time inference on a single consumer GPU.
【31】Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning
标题：适应蓬勃发展！改进LLM推理的自适应功率均值策略优化
链接：https://arxiv.org/abs/2605.04066
备注：Accepted to ACL 2026 (Findings)
摘要：Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities. To address this issue, we propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two main innovations: Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC). Specifically, PMPO introduces a generalized power-mean objective. This enables the model to adaptively transition from the signal-amplifying behavior of the arithmetic mean to the consistency-enforcing behavior of the geometric mean. FAC adaptively adjusts clipping bounds based on real-time reward statistics to overcome the limitations of static mechanisms. Capitalizing on these innovations, APMPO improves learning dynamics and reasoning performance. Extensive experiments on nine datasets across three reasoning tasks showcase the superiority of APMPO over state-of-the-art RLVR-based baselines. For instance, APMPO boosts the average Pass@1 score on mathematical reasoning benchmarks by 3.0 points compared to GRPO when using Qwen2.5-3B-Instruct.
【32】Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs
标题：具有自适应优势整形的自由能量驱动强化学习，用于LLM中的无监督推理
链接：https://arxiv.org/abs/2605.04065
备注：Accepted by ACL 2026
摘要：Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address this issue, we introduce FREIA, a novel RL-based algorithm built on two key innovations: (1) Free Energy-Driven Reward (FER) adapts rewards to balance consensus and exploration based on the Free Energy Principle. (2) Adaptive Advantage Shaping (AAS) adaptively adjusts learning signals based on the statistical characteristics of sampled rewards. Empirical evaluations on nine datasets across three reasoning tasks showcase that FREIA outperforms other unsupervised RL-based baselines. Notably, in mathematical reasoning tasks, FREIA surpasses other methods by an average of 0.5 to 3.5 points in Pass@1 using the DeepSeek-R1-Distill-Qwen-1.5B model.
【33】EdgeRazor: A Lightweight Framework for Large Language Models via Mixed-Precision Quantization-Aware Distillation
标题：EdgeRazor：通过混合精度量化感知蒸馏的大型语言模型轻量级框架
链接：https://arxiv.org/abs/2605.04062
摘要：Recent years have witnessed an increasing interest in deploying LLMs on resource-constrained devices, among which quantization has emerged as a promising lightweight technique that converts full-precision model weights and activations into lower-bit formats. Existing weight quantization approaches can be roughly divided into three categories: Post-Training Quantization (PTQ) that calibrates quantized parameters on a small dataset without retraining but suffers from severe performance degradation below 4-bit, Quantization-Aware Training (QAT) that searches low-bit parameters using surrogate gradients but demands substantial computational resources, and Quantization-Aware Distillation that integrates QAT with knowledge transfer from a full-precision teacher but manually selects features to distill and relies heavily on teacher-specific data. In this paper, we propose EdgeRazor, a lightweight framework for LLMs with mixed-precision and extremely low-bit weight quantization. The EdgeRazor framework contains three modules: Mixed-Precision Quantization-Aware Distillation for the fine-grained control of precision, Adaptive Feature Distillation that derives an $n$-bit student from its 16-bit teacher, and Entropy-Aware KL Divergence on both human-annotated and distilled datasets, whose forward-reverse balance is determined solely by the teacher's output distribution. Empirical investigations of EdgeRazor are conducted on base, instruction-tuned, and multimodal LLMs. Notably, EdgeRazor with 1.88-bit surpasses all contenders with the 3-bit precision, especially outperforms the leading 2-bit PTQ methods by 11.3 points, within a 4-10$\times$ lower training budget than the leading QAT approach. EdgeRazor delivers higher compression ratios at all bit width; the 1.58-bit Qwen3-0.6B reduces storage from 1.41 GB to 0.28 GB while accelerating decoding by 15.1$\times$ relative to the 16-bit baseline.
【34】Structured Progressive Knowledge Activation for LLM-Driven Neural Architecture Search
标题：LLM驱动的神经架构搜索的结构化渐进知识激活
链接：https://arxiv.org/abs/2605.04057
摘要：This paper focuses on a key challenge in Neural Architecture Search (NAS): integrating established architectural knowledge while exploring new designs under expensive evaluations. Large language models (LLMs) are a promising assistant for NAS because they can translate rich architectural and coding priors into executable code edits. However, in practice, seemingly local revisions often propagate into non-local behavioral and performance shifts because a single edit can inadvertently couple multiple interacting functional factors, a phenomenon we refer to as functional entanglement. To make LLM knowledge usable under such entanglement, we propose Structured Progressive Knowledge Activation (SPARK), which activates relevant priors by explicitly selecting the functional factor to modify and conditioning the edit on that factor. This factor-conditioned editing reduces entangled side effects and yields more targeted, reliable architecture modifications. On CLRS-DFS, SPARK achieves a 28.1x sample-efficient architecture evolution speedup and yields a 22.9 percent relative improvement in OOD accuracy.
【35】The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
标题：推理陷阱：封闭系统多步骤LLM推理的信息论界限
链接：https://arxiv.org/abs/2605.01704
备注：23 pages, 18 figures, 4 tables, 126 references. Subtitle: A Falsifiable Theorem, the Multi-Agent-Debate Instantiation, and a Triple Failure of Human Reliability
摘要：When copies of the same language model are prompted to debate, they produce diverse phrasings of one perspective rather than diverse perspectives. Multi-agent debate (MAD), and more broadly closed-system reasoning where agents iteratively transform each other's outputs, tends to preserve answer accuracy while degrading the reasoning behind those answers. We name the multi-agent case the Debate Trap and the broader phenomenon the Reasoning Trap, offering a programmatic theory of evidence-grounded reasoning failure.The framework has three parts: (i) SFS (Supported Faithfulness Score), a claim-level metric verifying decomposed atomic claims against provided evidence (decomposer-invariant rankings: Spearman rho=1.0); (ii) EGSR (Evidence-Grounded Socratic Reasoning), replacing adversarial argumentation with evidence-grounded inquiry; (iii) Theorem 1 (DPI Bound): under standard MAD, the chain E -> O^0 -> O^1 -> ... is Markov, and the Data Processing Inequality implies E[I(E;O^{t+1})] <= E[I(E;O^t)]. Three companion results -- open-system recovery (Theorem 2), EGSR accumulation (Lemma 2), and vote-aggregation floor (Proposition 1) -- partition multi-step LLM reasoning by its information-theoretic relationship to E. Across 16 conditions on SciFact (300 claims) and FEVER (1,000 claims), DebateCV (C13) preserves 88% of baseline accuracy while SFS drops 43%; majority-vote MAD (C15) reduces SFS to 1.7% of baseline (p < 10^{-6}, d = -0.96); EGSR recovers 98%. An R6 cohort study (Korean n=10x30 FEVER; English n=3x200 SciFact) finds inter-rater Fleiss kappa <= +0.018 with 0.8-1.4 Likert intra-rater shifts across language and domain -- the human agreement that faithfulness metrics have been calibrated against is not itself stable. We offer one falsifiable conjecture: any closed-system reasoning protocol preserving Theorem 1's Markov structure is, in expectation, subject to the same DPI bound.
【36】A large language model-type architecture for high-dimensional molecular potential energy surfaces
标题：用于多维分子势面的大语言模型型架构
链接：https://arxiv.org/abs/2412.03831
备注：31 pages, 35 figures
摘要：Computing high-dimensional potential energy surfaces for molecular systems and materials is considered to be a great challenge in computational chemistry with potential impact in a range of areas including the fundamental prediction of reaction rates. In this paper, we design and discuss an algorithm that has similarities to large language models in generative AI and natural language processing. Specifically, we represent a molecular system as a graph which contains a set of nodes, edges, faces, etc. Interactions between these sets, which represent molecular subsystems in our case, are used to construct the potential energy surface for a reasonably sized chemical system with 51 nuclear dimensions. For this purpose, a family of neural networks that pertain to the graph-theoretically obtained subsystems get the job done for this 51 nuclear dimensional system. We then ask if this same family of lower-dimensional graph-based neural networks can be transformed to provide accurate predictions for a 186-dimensional potential energy surface. We find that our algorithm does provide accurate results for this larger-dimensional problem with sub-kcal/mol accuracy for the higher-dimensional potential energy surface problem. Indeed, as a result of these developments, here we produce the first efforts towards a full-dimensional potential energy surface for the protonated 21-water cluster (186 nuclear dimensions) at CCSD level accuracy.
【37】Perturbation is All You Need for Extrapolating Language Models
标题：外推语言模型只需扰动即可
链接：https://arxiv.org/abs/2605.04344
备注：44 pages
摘要
：We introduce a simple yet powerful framework for training large language models. In contrast to the standard autoregressive next-token prediction based on an exact prefix, we propose a perturbation-based procedure that first transforms the prefix into a semantic neighbor and then conditions on this perturbed variant for next-token prediction. This yields a hierarchical model with a pre-post-additive noise structure. Within this framework, we develop a rigorous theory of extrapolability, namely, the capacity of a model class to make reliable predictions for token sequences that lie outside the empirical support of the training corpus. We evaluate the finite-sample performance of the proposed procedure using both synthetic and real-world language data. Results show that the proposed method consistently improves out-of-support prediction while maintaining competitive in-support performance, demonstrating that perturbation offers a practical route to language modeling.
【38】A foundation model of vision, audition, and language for in-silico neuroscience
标题：模拟神经科学的视觉、听力和语言基础模型
链接：https://arxiv.org/abs/2605.04326
摘要：Cognitive neuroscience is fragmented into specialized models, each tailored to specific experimental paradigms, hence preventing a unified model of cognition in the human brain. Here, we introduce TRIBE v2, a tri-modal (video, audio and language) foundation model capable of predicting human brain activity in a variety of naturalistic and experimental conditions. Leveraging a unified dataset of over 1,000 hours of fMRI across 720 subjects, we demonstrate that our model accurately predicts high-resolution brain responses for novel stimuli, tasks and subjects, superseding traditional linear encoding models, delivering several-fold improvements in accuracy. Critically, TRIBE v2 enables in silico experimentation: tested on seminal visual and neuro-linguistic paradigms, it recovers a variety of results established by decades of empirical research. Finally, by extracting interpretable latent features, TRIBE v2 reveals the fine-grained topography of multisensory integration. These results establish artificial intelligence as a unifying framework for exploring the functional organization of the human brain.
Graph相关(图学习|图神经网络|图优化等)(9篇)
【1】Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
标题：Graph-SND：多智能体强化学习中行为多样性的稀疏聚集
链接：https://arxiv.org/abs/2605.05020
备注：22 pages, 12 figures, 7 tables
摘要：System Neural Diversity (SND) measures behavioral heterogeneity in multi-agent reinforcement learning by averaging pairwise distances over all $\binom{n}{2}$ agent pairs, making each call quadratic in team size. We introduce Graph-SND, which replaces this complete-graph average with a weighted average over the edges of an arbitrary graph $G$. Three regimes follow: $G=K_n$ recovers SND exactly; a fixed sparse $G$ defines a localized diversity measure at $O(|E|)$ cost; and random edge samples yield an unbiased Horvitz-Thompson estimator and a normalized sample mean with $O(1/\sqrt{m})$ concentration in the sampled edge count $m$. For fixed sparse graphs we prove forwarding-index distortion bounds for expanders and a spectral refinement under low-rank distance structure; for random $d$-regular graphs we prove an unconditional probabilistic $\widetilde{\mathcal{O}}(D_{\max}/\sqrt{n})$ bound. On VMAS we verify recovery, unbiasedness, concentration, and wall-clock scaling, with a PettingZoo TVD panel checking non-Gaussian transfer. In a 500-iteration $n=100$ PPO run, Bernoulli-$0.1$ Graph-SND tracks full SND while reducing per-call metric time by about $10\times$, and frozen-policy GPU timing up to $n=500$ follows the predicted $\binom{n}{2}/|E|$ speedup. Random $d$-regular expanders empirically achieve $\mathrm{SND}_{G}^{\mathrm{u}}/\mathrm{SND} \in [0.9987, 1.0013]$ at $Θ(n \log n)$ edges. In DiCo diversity control at $n=50$, Bernoulli-$0.1$ Graph-SND preserves set-point tracking with paired reward differences indistinguishable from zero across nine matched cells while cutting per-call metric cost by ${\sim}9.5\times$. Together, these results show that the SND aggregation bottleneck can be removed without changing the metric's semantics, yielding a drop-in sparse alternative that scales beyond complete-graph SND and supports both passive measurement and closed-loop diversity control.
【2】Delving into Non-Exchangeability for Conformal Prediction in Graph-Structured Multivariate Time Series
标题：图结构多元时间序列共形预测的不可互换性研究
链接：https://arxiv.org/abs/2605.04957
摘要：Point forecasting for graph-structured multivariate time series is a fundamental problem, but rigorous uncertainty quantification for such predictions is still underexplored. Conformal prediction (CP) offers uncertainty estimation with a solid coverage guarantee under the exchangeability assumption, which requires the joint data distribution to be unchanged under permutation. However, in graph-structured time series, inherent cross-node coupling can violate the exchangeability condition, making direct application of CP unreliable. Inspired by the spectral graph theory, such coupling resides in global trends and can be characterized by the low-frequency components, while high-frequency components are nearly exchangeable. Therefore, we propose a novel concept named Spectral Graph Conditional Exchangeability (SGCE), which conditions exchangeable high-frequency components on low-frequency ones to preserve global trends and enable effective CP in the spectral domain. Based on SGCE, we further propose Spectral Conformal prediction via wAveLEt transform (SCALE). SCALE uses graph wavelets to decompose low/high-frequency components and conformalizes high-frequency residuals via adaptive gating over a low-frequency embedding. Experimental results on real-world traffic datasets show that SCALE not only achieves valid coverage but also consistently improves the coverage-efficiency trade-off over the state-of-the-art CP methods.
【3】Quantile-Free Uncertainty Quantification in Graph Neural Networks
标题：图神经网络中的无分位数不确定性量化
链接：https://arxiv.org/abs/2605.04847
备注：Accepted at the 43rd International Conference on Machine Learning (ICML 2026)
摘要：Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often relies on strong assumptions such as exchangeability, which are rarely satisfied in practice. Moreover, achieving reliable UQ typically requires costly resampling or post-hoc calibration. To address these issues, we introduce Quantile-free Prediction Interval GNN (QpiGNN), a framework that builds on quantile regression (QR) to enable GNN-based UQ by directly optimizing coverage and interval width without requiring quantile inputs or post-processing. QpiGNN employs a dual-head architecture that decouples prediction and uncertainty, and is trained with label-only supervision through a quantile-free joint loss. This design allows efficient training and yields robust prediction intervals, with theoretical guarantees of asymptotic coverage and near-optimal width under mild assumptions. Experiments on 19 synthetic and real-world benchmarks show QpiGNN achieves average 22\% higher coverage and 50\% narrower intervals than baselines, while ensuring efficiency and robustness to noise and structural shifts.
【4】Bridging Input Feature Spaces Towards Graph Foundation Models
标题：将输入特征空间与图基础模型的桥梁
链接：https://arxiv.org/abs/2605.04834
备注：33 Pages, 2 Figures, 26 Tables, ICLR 2026
摘要：Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from generalizing across datasets, limiting their use as foundation models. In this work, we propose ALL-IN, a simple and theoretically grounded method that enables transferability across datasets with different input features. Our approach projects node features into a shared random space and constructs representations via covariance-based statistics, thus eliminating dependence on the original feature space. We show that the computed node-covariance operators and the resulting node representations are invariant in distribution to permutations of the input features. We further demonstrate that the expected operator exhibits invariance to general orthogonal transformations of the input features. Empirically, ALL-IN achieves strong performance across diverse node- and graph-level tasks on unseen datasets with new input features, without requiring architecture changes or retraining. These results point to a promising direction for input-agnostic, transferable graph models.
【5】Library learning with e-graphs on jazz harmony
标题：图书馆通过电子图表学习爵士乐和声
链接：https://arxiv.org/abs/2605.04622
备注：10 pages, 7 figures, 2 listings, 1 table, no conference
摘要：Humans can acquire a highly structured intuitive understanding of musical patterns, yet these patterns often require multiple iterations of reflection and re-listening to internalize fully. To capture such an internalization process, we present a computational model for the learning of jazz harmonic patterns based on library learning. Given a corpus of harmonic progressions, our model searches over a space of programs composed of primitive harmonic relations in order to discover concise generative explanations of the corpus. The model first enumerates possible programs for each piece, and then jointly learns a library of harmonic patterns and refactored programs. To efficiently navigate the vast joint space of programs and libraries, we integrate deductive parsing with library learning on e-graphs. We explore how well our model captures aspects of human musical pattern learning by evaluating the intuitiveness of both programs and libraries, as well as similarities to human-written harmonic derivations.
【6】HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
标题：HeterSEED：异类下异类图学习的语义结构去耦合
链接：https://arxiv.org/abs/2605.04594
备注：29 pages, 9 figures
摘要：Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate messages along metapaths or meta-relations primarily based on feature similarity can propagate misleading information, since feature similarity may be misaligned with underlying relational semantics. In this paper, we propose HeterSEED, a semantics-structure decoupling framework for heterogeneous graph learning under heterophily. HeterSEED decouples representation learning into a heterogeneous semantic channel that captures type- and relation-aware local semantics and a structure-aware heterophily channel that separates homophilic and heterophilic neighborhoods via pseudo-label-guided partitioning and aggregates them using metapath-based structural weights. A node-level adaptive fusion mechanism then combines the two channels to produce context-dependent node representations. Theoretically, we establish that, on heterogeneous graphs under heterophily, HeterSEED is strictly more expressive than standard heterogeneous graph neural networks that rely primarily on feature similarity and provably reduces the prediction bias introduced by heterophilic neighbors. Experiments on five real-world heterogeneous graphs, including two large-scale networks at the million-node and hundred-million-edge scale, demonstrate that HeterSEED consistently outperforms representative heterogeneous graph neural networks and recent heterophily-aware baselines, especially in strongly heterophilic regimes.
【7】GraphPI: Efficient Protein Inference with Graph Neural Networks
标题：GraphPI：利用图神经网络进行高效蛋白质推理
链接：https://arxiv.org/abs/2605.04376
摘要：The integration of deep learning approaches in biomedical research has been transformative, enabling breakthroughs in various applications. Despite these strides, its application in protein inference is impeded by the scarcity of extensively labeled datasets, a challenge compounded by the high costs and complexities of accurate protein annotation. In this study, we introduce GraphPI, a novel framework that treats protein inference as a node classification problem. We treat proteins as interconnected nodes within a protein-peptide-PSM graph, utilizing a Graph Neural Network-based architecture to elucidate their interrelations. To address label scarcity, we train the model on a set of unlabeled public protein datasets with pseudo-labels derived from an existing protein inference algorithm, enhanced by self-training to iteratively refine labels based on confidence scores. Contrary to prevalent methodologies necessitating dataset-specific training, our research illustrates that GraphPI, due to the well normalized nature of Percolator features, exhibits universal applicability without dataset-specific fine-tuning, a feature that not only mitigates the risk of overfitting but also enhances computational efficiency. Our empirical experiments reveal notable performance on various test datasets and deliver significantly reduced computation times compared to common protein inference algorithms.
【8】Actionable Real-Time Modeling of Surgical Team Dynamics via Time-Expanded Interaction Graphs
标题：通过时间扩展的交互图对手术团队动态进行可操作的实时建模
链接：https://arxiv.org/abs/2605.04169
备注：Accepted at Hybrid Human Artificial Intelligence (HHAI) 2026
摘要：Surgical team performance arises from complex interactions between technical execution and non-technical skills, including communication and coordination dynamics. However, current surgical AI systems predominantly model visual workflow signals, lacking structured representations of intraoperative team interactions over time. We propose a real-time actionable approach for modeling surgical team dynamics using time-expanded interaction graphs, where team members are modeled as time-indexed nodes and communication exchanges define directed edges. This spatio-temporal expansion enables dynamic interaction modeling, while allowing efficient inference with a static graph neural network. The model predicts procedural efficiency as the deviation from the expected duration and supports real-time deployment. Beyond prediction, we perform a counterfactual analysis to identify minimal changes in communication structure and interpretable behavioral variables associated with improved predicted outcomes. Experiments on recorded surgical procedures show that structured modeling of team interactions improves early identification of prolonged interventions and provides coherent, actionable explanations. This work advances surgical AI toward real-time, team-aware, and actionable decision support in the operating room.
【9】Interpreting Manifolds and Graph Neural Embeddings from Internet of Things Traffic Flows
标题：从物联网流量解释Manifolies和图神经嵌入
链接
：https://arxiv.org/abs/2602.05817
摘要：The rapid expansion of Internet of Things (IoT) ecosystems has led to increasingly complex and heterogeneous network topologies. Traditional network monitoring and visualization tools rely on aggregated metrics or static representations, which fail to capture the evolving relationships and structural dependencies between devices. Although Graph Neural Networks (GNNs) offer a powerful way to learn from relational data, their internal representations often remain opaque and difficult to interpret for security-critical operations. Consequently, this work introduces an interpretable pipeline that generates directly visualizable low-dimensional representations by mapping high-dimensional embeddings onto a latent manifold. This projection enables the interpretable monitoring and interoperability of evolving network states, while integrated feature attribution techniques decode the specific characteristics shaping the manifold structure. The framework achieves a classification F1-score of 0.830 for intrusion detection while also highlighting phenomena such as concept drift. Ultimately, the presented approach bridges the gap between high-dimensional GNN embeddings and human-understandable network behavior, offering new insights for network administrators and security analysts.
Transformer(7篇)
【1】Taming Outlier Tokens in Diffusion Transformers
标题：驯服扩散Transformer中的离群代币
链接：https://arxiv.org/abs/2605.05206
备注：Under review
摘要：We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying limited local information, but their role in generative models remains underexplored. We show that this phenomenon appears in both the encoder and denoiser of modern Representation Autoencoder (RAE)-DiT pipelines: pretrained ViT encoders can produce outlier representations, and DiTs themselves can develop internal outlier tokens, especially in intermediate layers. Moreover, simply masking high-norm tokens does not improve performance, indicating that the problem is not only caused by a few extreme values, but is more closely related to corrupted local patch semantics. To address this issue, we introduce Dual-Stage Registers (DSR), a register-based intervention for both components: trained registers when available, recursive test-time registers otherwise, and diffusion registers for the denoiser. Across ImageNet and large-scale text-to-image generation, these interventions consistently reduce outlier artifacts and improve generation quality. Our results highlight outlier-token control as an important ingredient in building stronger DiTs.
【2】Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer
标题：使用transformer理解非线性回归的上下文学习：注意力作为特征化器
链接：https://arxiv.org/abs/2605.05176
摘要：Pre-trained transformers are able to learn from examples provided as part of the prompt without any weight updates, a remarkable ability known as in-context learning (ICL). Despite its demonstrated efficacy across various domains, the theoretical understanding of ICL is still developing. Whereas most existing theory has focused on linear models, we study ICL in the nonlinear regression setting. Through the interaction mechanism in attention, we explicitly construct transformer networks to realize nonlinear features, such as polynomial or spline bases, which span a wide class of functions. Based on this construction, we establish a framework to analyze end-to-end in-context nonlinear regression with the constructed features. Our theory provides finite-sample generalization error bounds in terms of context length and training set size. We numerically validate the theory on synthetic regression tasks.
【3】Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
标题：叠加不是必要的：时间序列预测的Transformer表示的机械解释性分析
链接：https://arxiv.org/abs/2605.05151
备注：13 pages, 5 tables
摘要：Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in NLP actually engage on time series data remains unexplored. The persistent competitiveness of simple linear models such as DLinear has fueled ongoing debate, but no mechanistic explanation for this phenomenon has been offered. We address this gap by applying sparse autoencoders (SAEs), a tool from mechanistic interpretability, to probe the internal representations of PatchTST. We first establish that a single-layer, narrow-dimensional transformer matches the forecasting performance of deeper configurations across commonly used benchmarks. We then train SAEs on the post-GELU intermediate FFN activations with dictionary sizes ranging from 0.5x to 4.0x the native dimensionality. Expanding the dictionary yields negligible downstream performance change (average 0.214%), with large portions of overcomplete dictionaries remaining inactive. Targeted causal interventions on dominant latent features produce minimal forecast perturbation. Across all evaluated settings, we observe no empirical evidence that the analyzed FFN representations rely on strong superposition. Instead, the representations remain sparse, stable under aggressive dictionary expansion, and largely insensitive to latent interventions. These results demonstrate that superposition is not necessary for competitive performance on standard forecasting benchmarks, suggesting they may not demand the rich compositional representations that drive transformer success in language modeling, and helping explain the persistent competitiveness of simple linear models
【4】Average Attention Transformers and Arithmetic Circuits
标题：平均注意力Transformer和算术电路
链接：https://arxiv.org/abs/2605.04683
摘要：We analyse the computational power of transformer encoders as sequence-to-sequence functions on vectors. We show that average hard attention can be used to simulate arithmetic circuits if they are given as an input to an encoder. The circuit families that can be simulated this way have constant depth while using unbounded addition, binary multiplication and sign gates. The transformers we use have arithmetic circuits instead of feed-forward networks. With typical average attention the functions they compute are also computed by the same class of circuit families. Our results hold for transformers over the reals, rationals and any ring in between the two.
【5】HEXST: Hexagonal Shifted-Window Transformer for Spatial Transcriptomics Gene Expression Prediction
标题：HEXST：用于空间转录组学基因表达预测的六边形移动窗口Transformer
链接：https://arxiv.org/abs/2605.04682
摘要：Spatial transcriptomics offers spatially resolved gene expression profiling within tissue sections, but its cost and limited throughput hinder large-scale deployment. To extend this capability to routine practice, recent computational methods aim to infer spatial gene expression directly from ubiquitous hematoxylin and eosin-stained histology slides. However, most existing models assume Cartesian or geometry-agnostic locality, despite the hexagonal sampling of widely used spot-array platforms, and point-wise regression objectives often yield over-smoothed gene expression profiles, obscuring gene-specific spatial heterogeneity. To address these, we propose HEXST, a geometry-aligned Transformer for spatial gene expression prediction from histology. HEXST operates directly on hexagonal spot coordinates to enable efficient local-to-global contextual modeling via tailored shifted-window attention mechanism and hexagonal rotary positional encoding. To enhance gene-wise spatial contrast, HEXST complements point-wise regression with a contrast-sensitive differential objective and transcriptomic priors from a pretrained single-cell foundation model during training. Across seven spatial transcriptomics datasets, HEXST consistently outperforms state-of-the-art models, providing accurate and robust spatial gene expression predictions while preserving gene-wise contrast and spatial heterogeneity.
【6】FLUID: Continuous-Time Hyperconnected Sparse Transformer for Sink-Free Learning
标题：TUID：用于无水槽学习的连续时间超连接稀疏Transformer
链接：https://arxiv.org/abs/2605.04421
摘要：Continuous-time (CT) Transformers improve irregular and long-range modeling over CT-RNNs by exploiting inputs or outputs embeddings with continuous dynamics. However, the core scaled-dot-product-attention (SDPA) mechanism remains inherently discrete. We propose FLUID (Flexible Unified Information Dynamics), a CT Transformer that incorporates continuous dynamics directly into the attention computation by replacing it with Liquid Attention Network (LAN). LAN reinterprets attention logits as continuous dynamical system and reformulates them as the solution to a linear ODE modulated by input-dependent nonlinear recurrent gates. Theoretically, we establish stability guarantees for LAN dynamics and show that it serves as an interpolating middle ground between SDPA and CT-RNNs, recovering each as special case under well-defined parameterization of its gating functions. LAN also introduces an explicit attention-sink gate to eliminate disproportionate attention mass on uninformative nodes. FLUID replaces standard residual connections with input-dependent Liquid Hyper-Connections to adaptively regulate interlayer information flow. Empirically, we evaluate FLUID on a broad set of learning tasks, including (i) irregular time-series, (ii) long-range modeling, (iii) lane-keeping control of autonomous vehicles, and (iv) learning physical dynamics under a scarce data regime. Across all the tasks, FLUID consistently matches or outperforms CT baselines, achieving improvements of up to 47% in certain scenarios and enhancing generalization under distributional shifts. Additionally, FLUID demonstrates superior noise robustness and a self-correcting inductive bias in autonomous vehicle control. We also provide a detailed analysis of key hyperparameters to guide tuning and show that FLUID occupies an intermediate position among competing approaches in terms of runtime and memory efficiency.
【7】Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
标题：复杂性控制的关键窗口：当Transformer决定推理或小型化时
链接：https://arxiv.org/abs/2605.04396
摘要：Recent work has shown that Transformers' compositional generalization is governed by \emph{complexity control}, initialization scale and weight decay, which steers training toward low-complexity reasoning solutions rather than high-complexity memorization. Existing analyses, however, treat complexity control as a single static hyperparameter choice, leaving open \emph{when} during training this control is actually decisive. We show that the memorization-versus-reasoning fate of a Transformer is determined within a sharp, identifiable window of training. On a controlled compositional task we find that (i)~weight decay applied for a single 25\%-of-training window matches full-training weight decay in out-of-distribution (OOD) accuracy ($0.93$ vs $0.91$); (ii)~holding total regularization budget constant, placing it in the middle of training yields $5{-}9\times$ higher OOD accuracy than placing it early; (iii)~the boundary of the critical window is remarkably sharp, window onset shifted by as little as $100$ optimization steps causes mean OOD to jump from chance ($0.15$) to reasoning-regime ($0.61$); (iv)~the window's position depends systematically on initialization scale, but the basin of attraction for reasoning solutions \emph{shrinks} at small initialization, contradicting the prevailing recommendation that smaller initialization is uniformly better. We further show that the critical-window phenomenon is task-specific: it does not appear on grokking with modular arithmetic, where properly tuned constant weight decay matches scheduled weight decay.
GAN|对抗|攻击|生成相关(8篇)
【1】Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation
标题：流行音乐和爵士乐混音比例对流派适应性和弦一代的实证研究
链接：https://arxiv.org/abs/2605.04998
备注：3 figures, 5 tables. Companion HuggingFace models: https://huggingface.co/PearlLeeStudio
摘要：Chord progression generation is practically important but understudied. Most large-scale symbolic music systems target melody, multi-track arrangement, or audio synthesis, and chord-only models tend to be relegated to conditioning components inside larger pipelines. This paper treats chord generation as a standalone task and addresses a question that arises whenever such a model is adapted across genres: how much old-domain data must be retained during fine-tuning to acquire a new domain without forgetting the old? I study jazz fine-tuning starting from a pop-pretrained 25M-parameter Music Transformer (84.24% top-1 chord accuracy on a held-out pop test set). The available jazz corpus is an order of magnitude smaller than the pop corpus, so every fine-tune run uses all 1,513 jazz training sequences. The swept variable is the volume of pop "rehearsal" data mixed alongside, taking values in {0, 1K, 2.5K, 5K, 10K}. Every fine-tuned model gains 7 to 9 points of jazz top-1. Pop accuracy collapses by 2.14 points under jazz-only fine-tuning, recovers to baseline at approximately 2.5K rehearsal samples (1.65x the jazz volume), and saturates beyond that point. A complementary observation: the metric-best run (F3, 2.5K mix) is not always the perceptually preferred one. The pop-leaning (10K) and jazz-leaning (1K) endpoints carry more committed stylistic identities that the author more often selects as finished output in informal listening. I discuss what this suggests for music co-creation tools but make no perceptual claim, since no formal listening study has been conducted. All six checkpoints are released on the HuggingFace Hub at https://huggingface.co/PearlLeeStudio.
【2】Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning
标题：通过上下文学习打破表格数据生成中的质量-隐私权衡
链接：https://arxiv.org/abs/2605.04911
摘要
：Tabular data synthesis aims to generate high-quality data while preserving privacy. However, we find that existing tabular generative models exhibit a clear tradeoff in the small-data regime: improving data quality typically comes at the cost of increased memorization of training samples, thereby weakening privacy protection. This tradeoff arises because small training sets make it difficult for dataset-specific generative models to distinguish generalizable structure from sample-specific patterns. To address this, we propose DiffICL, which formulates tabular data generation as an in-context learning problem. Instead of fitting each dataset from scratch,DiffICL leverages pretrained structural priors learned from a large collection of datasets, enabling it to infer data distributions from limited context rather than memorizing individual samples. We evaluate DiffICL on 14 real-world datasets. Results show that DiffICL improves both data quality and privacy, and generate synthetic data that provides effective data augmentation. Our findings suggest that the quality-privacy tradeoff can be improved through better training paradigms.
【3】Conditional Flow-VAE for Safety-Critical Traffic Scenario Generation
标题：用于安全关键交通场景生成的有条件流VAE
链接：https://arxiv.org/abs/2605.04366
备注：ICRA 2026
摘要：Safety-critical scenarios are essential for the development of autonomous vehicles (AVs) but are rare in real-world driving data. While simulation offers a way to generate such scenarios, manually designed test cases lack scalability, and adversarial optimization often produces unrealistic behaviors. In this work, we introduce a conditional latent flow matching approach for scalable and realistic safety-critical scenario generation. Our method uses distribution matching to transform nominal scenes into safety-critical rollouts. Furthermore, we demonstrate that incorporating both simulation and real-world data enables our framework to efficiently generate diverse, data-driven scenarios. Experimental results highlight that our approach is able to more consistently and realistically generate novel safety-critical scenarios, making it a valuable tool for training and benchmarking AV systems.
【4】Laundering AI Authority with Adversarial Examples
标题：用敌对例子清洗人工智能权威
链接：https://arxiv.org/abs/2605.04261
摘要：Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content as they do. We show that adversarial examples break this assumption, enabling \emph{AI authority laundering}: an attacker subtly perturbs an image so that the VLM produces confident and authoritative responses about the \emph{wrong} input. Unlike jailbreaks or prompt injections, our attacks do not compromise model alignment; the attack operates entirely at the perceptual level. We demonstrate that standard attacks against publicly available CLIP models transfer reliably to production VLMs -- including GPT-5.4, Claude Opus~4.6, Gemini~3, and Grok~4.2. Across four attack surfaces, we show that authority laundering can amplify misinformation, disparage individuals, evade content moderation, and manipulate product recommendations. Our attacks have high success rates: In hundreds of attacks targeting identity manipulation and NSFW evasion, we measure success rates of $22 - 100\%$ across six models. No novel attack algorithm is required: basic techniques known for over a decade suffice, establishing a lower bound on attacker capability that should concern defenders. Our results demonstrate that visual adversarial robustness is now a practical -- and still largely unsolved -- safety problem.
【5】Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
标题：在统一的多模式理解和生成中唤醒空间智能
链接：https://arxiv.org/abs/2605.04128
摘要：We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing. JoyAI-Image couples a spatially enhanced Multimodal Large Language Model (MLLM) with a Multimodal Diffusion Transformer (MMDiT), allowing perception and generation to interact through a shared multimodal interface. Around this architecture, we build a scalable training recipe that combines unified instruction tuning, long-text rendering supervision, spatially grounded data, and both general and spatial editing signals. This design gives the model broad multimodal capability while strengthening geometry-aware reasoning and controllable visual synthesis. Experiments across understanding, generation, long-text rendering, and editing benchmarks show that JoyAI-Image achieves state-of-the-art or highly competitive performance. More importantly, the bidirectional loop between enhanced understanding, controllable spatial editing, and novel-view-assisted reasoning enables the model to move beyond general visual competence toward stronger spatial intelligence. These results suggest a promising path for unified visual models in downstream applications such as vision-language-action systems and world models.
【6】Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering
标题：基于检索的文档问题解答内上下文学习的成员推断攻击
链接：https://arxiv.org/abs/2605.04116
备注：https://satml.org/program/
摘要：We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-inference attacks even when the service provider and users are separate parties. We propose two black-box membership inference attacks that exploit query text prefixes to distinguish member from non-member inputs. The first attack uses a reference model to estimate an otherwise unavailable loss metric. The second attack improves upon it by eliminating the reference model and instead computing a membership statistic through a simple but novel weighted-averaging scheme. Our comprehensive empirical evaluations consider a stricter case in which the adversary has a paraphrased version of the text in the queries and show that our attacks can exhibit stronger resilience to paraphrasing and outperform three prior attacks in many cases with small number of prefixes. We also adapt an existing ensemble prompting defense to our setting, demonstrating that it substantially mitigates the privacy leakage caused by our second attack.
【7】FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing
标题：FlatASCEnd：具有连续时间预测和基于关联的药理学测试的自回归临床序列生成
链接：https://arxiv.org/abs/2605.04071
备注：22 pages, 2 figures, 12 tables
摘要
：Autoregressive models can predict clinical events, but generating patient-conditioned multi-step trajectories that respond to intervention tokens and testing whether those responses preserve known pharmacological associations has received limited attention. We present FlatASCEND, a 14.5M-parameter autoregressive clinical sequence model using flat composite tokens and a zero-inflated log-normal time head. Standard distributional metrics (Jaccard 0.889-0.954) do not distinguish FlatASCEND from trivial baselines; the model's value lies in conditional generation from patient-specific prefixes. A prompt-shuffle ablation shows patient-specific conditioning amplifies mechanistic pharmacological effects (2.0-2.2x for steroid to glucose, diuretic to potassium) while leaving confounding-driven associations unchanged (0.9x for insulin to glucose). An incident-user framework assesses directional consistency against prior pharmacological knowledge on MIMIC-IV (N=500 per comparison): 4/10 recover correct mechanistic directions, 2 reproduce treatment-context associations, 4 are incorrect (9/10 significant, Wilcoxon p<0.05). This pattern - partial recovery under residual confounding - is consistent with learned observational associations without causal distinction. Direct preference optimisation with surrogate reward destroys all correct associations (3/3 to 0/3), illustrating reward exploitation when reward and evaluation share an outcome domain. Generative evidence is strongest for short-horizon ICU data; outpatient temporal fidelity is weaker (median 10 vs 154 days on INSPECT), and zero-shot cross-site transfer degrades without adaptation.
【8】Hypergraph Generation via Structured Stochastic Diffusion
标题：通过结构化随机扩散生成超图
链接：https://arxiv.org/abs/2605.05024
摘要：Hypergraphs model higher-order interactions, but realistic hypergraph generation remains difficult because incidence, hyperedge-size heterogeneity, and overlap structure are not faithfully captured by pairwise reductions. We propose \HEDGE, a generative model defined directly on relaxed incidence matrices via a structured stochastic diffusion. The forward process combines a hypergraph-specific two-sided heat operator with an Ornstein--Uhlenbeck component, preserving structure-aware noising near the data while yielding an explicit Gaussian terminal law. Conditional on an observed hypergraph, this forward process is linear-Gaussian, so conditional means, covariances, scores, and reverse-drift targets are available in closed form. We therefore learn a permutation-equivariant state-only reverse-drift field in incidence space by regressing onto exact conditional targets, and generate samples by simulating a learned reverse-time SDE from the Gaussian base law. We establish exactness in the ideal state-only setting together with finite-horizon stability guarantees, and empirically show improved hypergraph generation quality relative to strong baselines.
半/弱/无/有监督|不确定性|主动学习(9篇)
【1】FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
标题：FAAST：通过封闭形式快速权重进行纯前向关联学习，用于测试时间监督适应
链接：https://arxiv.org/abs/2605.04651
备注：9 pages, 6 figures, 10 tables
摘要：Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning. We propose FAAST, a forward-only associative adaptation method that analytically compiles labeled examples into fast weights in a single pass. By eliminating memory or context dependence, FAAST achieves constant-time inference and decouples task adaptation from pretrained representation. Across image classification and language modeling benchmarks, FAAST matches or exceeds backprop-based adaptation while reducing adaptation time by over 90\% and is competitive to memory/context-based adaptation while saving memory usage by up to 95\%. These results demonstrate FAAST as a highly efficient, scalable solution for supervised task adaptation, particularly for resource-constrained models. We release the code and models at https://github.com/baoguangsheng/faast.
【2】Probabilistic Classification and Uncertainty Quantification of Sahara Desert Climate Using Feedforward Neural Networks
标题：利用前向神经网络对撒哈拉沙漠气候进行概率分类和不确定性量化
链接：https://arxiv.org/abs/2605.04286
摘要：Climate classification plays a vital role in agricultural planning, hydrological studies, and climate science. One of the most widely used systems for classifying global climate zones is the Köppen-Trewartha (KT) classification. However, the KT classification is fundamentally deterministic, offering discrete labels to spatial locations without accounting for uncertainties in classification. In this paper, we provide a framework for probabilistic modeling of climatic zones. We implement a feedforward artificial neural network (ANN) for classification, allowing for efficient, uncertainty-aware categorization of climatic regions, thereby offering a more nuanced understanding of transitional climate zones compared to traditional deterministic methods. We apply this method to the Sahara Desert region over the 30-year period of 1960 - 1989, using data at more than 400,000 space-time locations from the first 11 years to train our model. We assess the model's short- and long-term classification capabilities to evaluate its stability and accuracy over time. We also compare the probabilistic classification from our model with the traditional KT classification. In addition, we use fluctuation analysis methods to highlight the temporal evolution of climatic zones across the Sahara region and identify areas undergoing significant flux of probabilities of their climate classes, providing insights into broader trends in desertification.
【3】A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
标题：边界检测的平均弯曲方法：无监督学习的几何见解
链接：https://arxiv.org/abs/2605.04274
备注：26 pages, 6 tables, 8 figures
摘要：Accurate boundary detection in high-dimensional data remains a central challenge in unsupervised learning, particularly in the presence of non-linear structures and heterogeneous densities. In this work, we introduce Mean Curvature Boundary Points (MCBP), a novel geometric framework grounded in Geometric Machine Learning that departs from traditional density-based approaches by explicitly modeling the intrinsic curvature of the data manifold. The method relies on a discrete approximation of the shape operator, estimated from local k-nearest neighbor patches, to compute pointwise mean curvature without requiring explicit manifold parametrization. The key insight of MCBP is to use mean curvature as a principled descriptor of boundary structure: high-curvature regions naturally correspond to transitions between clusters, geometric irregularities, and low-density interfaces. This yields a unified geometric interpretation of boundary, outlier, and transition points. We further introduce an adaptive percentile-based thresholding scheme that enables multiscale boundary extraction without relying on ad hoc density parameters. Beyond detection, we propose a curvature-driven data decomposition that separates samples into smooth (low-curvature) and boundary (high-curvature) subsets, effectively acting as a non-linear geometric filtering mechanism. This representation enhances cluster separability and improves the robustness of downstream unsupervised algorithms. Extensive experiments on synthetic and real-world datasets demonstrate that MCBP consistently improves clustering performance, particularly in complex and high-dimensional scenarios. These results position MCBP as a concrete contribution to Geometric Machine Learning, highlighting the potential of curvature-aware analysis as a unifying paradigm bridging differential geometry and data-driven modeling.
【4】HUGO-CS: A Hybrid-Labeled, Uncertainty-Aware, General-Purpose, Observational Dataset for Cold Spray
标题
：HUGO-CS：混合标签、具有不确定性的通用冷喷雾观察数据集
链接：https://arxiv.org/abs/2605.04257
备注：22 pages, 8 figures, 4 tables
摘要：Cold spraying is an increasingly common approach for repairing and manufacturing components due to its solid-state manufacturing capabilities. However, process optimization remains difficult due to many interdependent parameters and the lack of large-scale, machine-readable data to support modeling. While the scientific literature contains many relevant experiments, results are inconsistently reported (often in tables and figures) and use non-uniform units, limiting utilization at scale. To address these limitations, this work presents HUGO-CS, a literature-derived dataset of 4,383 cold-spray experiments with 144 features from 1,124 sources, exceeding the previous largest dataset (137 samples) by 30x. With completely manual extraction requiring an average of 91 minutes per document, this work designs and leverages a Hybrid-labeled, Uncertainty-aware, General-purpose, Observational extraction framework, called HUGO, to support this extraction. HUGO combines automated LLM-based labeling with targeted manual label refinement to handle this experimental result extraction process from scientific literature. To balance labeling efficiency with extraction accuracy, HUGO introduces a Hierarchical Risk Mitigation (HRM) to route LLM outputs with a high risk of potential errors for manual review, while retaining low-risk records as auto-labeled. Lastly, HUGO post-processing consolidates categorical descriptors, maps reported feedstock chemistries into structured continuous compositions, and normalizes units across sources. Of the 4,383 reported experiments, 1,765 are hand-labeled, providing a high-quality labeled subset for benchmarking, error analysis, and higher-fidelity data points. All code to replicate this work, along with the complete HUGO-CS dataset, are released under a CC-BY license at https://github.com/sprice134/HUGO.
【5】RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
标题：RetentiveKV：用于不确定性感知多模式KV缓存驱逐的状态空间存储器
链接：https://arxiv.org/abs/2605.04075
摘要：Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the visual KV cache when processing long visual contexts. Existing KV cache compression methods typically rely on the "persistence of importance" hypothesis to prune tokens. However, this approach proves fragile in multimodal settings due to two key issues: 1) Visual tokens display "deferred importance," initially exhibiting low salience but becoming pivotal during later decoding, which can lead to premature eviction. 2) Discrete pruning disrupts the inherent spatial continuity of visual cues. To address these challenges, we propose RetentiveKV, an entropy-driven KV cache optimization method that reformulates KV eviction from "discrete context truncation" to "continuous memory evolution" based on State Space Models. Our method leverages information entropy to quantify the information potential of low-attention tokens and integrates tokens scheduled for eviction into a continuous state space through entropy-guided state transitions, enabling their dynamic reactivation when semantic relevance arises during subsequent decoding. Extensive experiments on multimodal benchmarks demonstrate that RetentiveKV achieves 5.0 times KV cache compression and 1.5 times decoding acceleration.
【6】LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment
标题：法律：象征性地从实际工作负载中学习--用于神经推理、机器人技术和边缘部署的自我认证参数化缓存架构
链接：https://arxiv.org/abs/2605.04069
备注：45 pages. Companion paper to arXiv:2604.06228 (Probabilistic Language Tries)
摘要：We introduce LAWS (Learning from Actual Workloads Symbolically), a self-certifying inference caching architecture that builds a growing library of certified expert functions from deployment observations. Each expert covers a region of input space defined by a node in the Probabilistic Language Trie (PLT) of the base model and carries a formal error bound holding uniformly over all inputs. The central result is a self-certification theorem: for any input x, the LAWS approximation error is bounded by epsilon_fit + 2*Lambda(W)*C_E, where Lambda(W) is the model Lipschitz constant, C_E is the maximum embedding diameter, and epsilon_fit is the expert training error -- all checkable at deployment time without ground truth. We prove that LAWS generalizes both Mixture-of-Experts and KV prefix caching as special cases and is strictly more expressive than any fixed-K MoE or finite cache. Further results include a monotone hit rate theorem (any-match routing ensures coverage only increases), an expert library growth rate of O(2^H log N) where H is workload entropy, a fleet learning convergence theorem with Omega(K) speedup for K-unit fleets, and an over-the-air update bandwidth bound. We conjecture that LAWS is acquisition-optimal among stationary online caching algorithms and that the effective Lipschitz constant on the training distribution grows polynomially rather than exponentially in depth. Applications are developed for LLM inference, robotic control, and multi-agent edge deployment.
【7】Improving Medical VQA through Trajectory-Aware Process Supervision
标题：通过轨迹感知过程监督改进医疗VQA
链接：https://arxiv.org/abs/2605.04064
摘要：Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanations. We address this by generating reasoning trajectories for six medical VQA benchmarks using the COMCTS algorithm with open-source vision-language models, with an LLM serving as the verification judge. Building on these generated datasets, we propose a two-stage training framework: supervised fine-tuning followed by Group Relative Policy Optimization (GRPO) with a novel process-based reward. While standard approaches rely solely on exact-match rewards for final answers, we introduce a trajectory-aware reward that measures the similarity between generated and ground-truth reasoning processes. Specifically, we embed reasoning steps using sentence transformers and compute the Dynamic Time Warping (DTW) distance between the resulting vector sequences. Experiments across six benchmarks demonstrate that combining the DTW-based process reward with exact-match reward consistently outperforms SFT-only training, raising mean accuracy from 0.598 to 0.689, mean BERTScore from 0.845 to 0.881, and mean ROUGE-L from 0.665 to 0.748. Our results highlight the importance of process supervision in training reasoning-capable medical VLMs. We make our code and generated reasoning datasets publicly available at https://anonymous.4open.science/r/MICCAI-R1-MED-VQA-code-B14B/
【8】A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay
标题：一种具有组自适应学习率和权值衰减的自注意元优化算法
链接：https://arxiv.org/abs/2605.04055
摘要
：Adaptive optimizers like AdamW apply uniform hyperparameters across all parameter groups, ignoring heterogeneous optimization dynamics across layers and modules. We address this limitation by proposing MetaAdamW - a new optimizer that integrates a self-attention mechanism to dynamically modulate per-group learning rates and weight decay. The modulation factors are produced by a lightweight Transformer encoder that operates on statistical features (gradient norms, momentum norms, correlations) extracted from each parameter group. To train the attention module, we introduce a meta-learning objective that combines gradient alignment, loss decrease, and generalization gap. A key novel contribution is the extension of homoscedastic uncertainty weighting (HUW) with task-specific priorities that directly scale the regularization terms - enabling domain knowledge to guide automatic loss balancing. Extensive experiments on five diverse tasks-time series forecasting (ETT), language modeling (WikiText-2), machine translation (Multi30k), image classification (CIFAR-10), and sentiment analysis (IMDB) - demonstrate that MetaAdamW consistently outperforms the standard AdamW baseline in terms of validation loss, accuracy, or perplexity. Depending on the task, MetaAdamW either reduces overall training time (by up to 17.11%) or improves performance (by up to 11.08%) while introducing only moderate overhead; in some cases, it can also mitigate issues of insufficient convergence caused by premature early stopping. Ablation studies validate the effectiveness of each component, including feature versions, grouping strategies, and the proposed priority-injected uncertainty weighting.
【9】Meta-LegNet: A Transferable and Interpretable Framework for Surface Adsorption Prediction via Self-Defined Adsorption-Environment Learning
标题：Meta-LegNet：通过自定义的吸附环境学习进行表面吸收预测的可转移和可解释框架
链接：https://arxiv.org/abs/2605.04102
摘要：A central challenge in computational catalysis is the identification of low-energy and chemically plausible adsorption configurations, as these directly affect adsorption energies, reaction pathways, and catalytic performance. Existing approaches generally rely on enumerating candidate adsorption sites followed by iterative refinement through density functional theory calculations or machine-learning-based relaxations. However, such workflows remain computationally expensive and are difficult to scale to complex surfaces or multi-adsorbate systems. Here, we introduce Meta-LegNet, a graph learning framework that combines SE(3)-equivariant atom-level message passing with voxel-based multiscale aggregation and cross-domain meta-learning to learn transferable representations of local adsorption environments across diverse catalyst--adsorbate systems. Rather than following a conventional regression-only paradigm, Meta-LegNet encodes local chemical environments using invariant radial features and equivariant directional information, and further incorporates broader structural context through coordinate-frame voxel pooling, assignment-based upsampling, and gated feature fusion. The resulting local-global decomposition produces atom-resolved attribution maps, which are processed to identify adsorption-relevant local environments in an interpretable manner. Based on the learned representations, we further construct an adsorption-environment database and develop a template-matching strategy to propose likely adsorption sites on previously unexplored surfaces without exhaustive site enumeration. Overall, our results suggest that learning transferable adsorption environments provides an accurate, interpretable, and practical route for accelerating catalyst screening.
迁移|Zero/Few/One-Shot|自适应(15篇)
【1】Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
标题：离线到在线强化学习交互预算下的自适应策略选择和微调
链接：https://arxiv.org/abs/2605.05123
摘要：In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limited online interactions. In a typical O2O-RL pipeline, candidate policies trained with offline RL are evaluated via either off-policy evaluation (OPE) or online evaluation (OE). The policy with the highest estimated value is then deployed and continually fine-tuned. However, this setup has two main issues. First, OPE can be unreliable, making it risky to deploy a policy based solely on those estimates, whereas OE may identify a viable policy with substantial online interaction, which could have been used for fine-tuning. Second--and more importantly--it is also often not possible to determine a priori whether a pretrained policy will improve with post-deployment fine-tuning, especially in non-stationary environments. As a result, procedures committing to a single deployed policy are impractical in many real-world settings. Moreover, a naive remedy that exhaustively fine-tunes all candidates would violate interaction budget constraints and is likewise infeasible. In this paper, we propose a novel adaptive approach for policy selection and fine-tuning under online interaction budgets in O2O-RL. Following the standard pipeline, we first train a set of candidate policies with different offline RL algorithms and hyperparameters; we then perform OPE to obtain initial performance estimates. We next adaptively select and fine-tune the policies based on their predicted performance via an upper-confidence-bound approach thereby making efficient use of online interactions. We demonstrate that our approach improves upon O2O-RL baselines with various benchmarks.
【2】Order Matters: Improving Domain Adaptation by Reordering Data
标题：顺序很重要：通过重新排序数据来改善领域适应性
链接：https://arxiv.org/abs/2605.05084
摘要：Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this by minimising domain discrepancy during training, but the discrepancy estimates suffer from high variance in stochastic settings, which can stifle the theoretical benefits of the method. This paper proposes Optimal Reordering of Data for Error-Reduced Estimation of Discrepancy (ORDERED), a novel unbiased stochastic variance reduction technique which reduces the discrepancy estimation error by optimising the order in which the training data are sampled. We consider two specific domain discrepancy losses (correlation alignment and the maximum mean discrepancy), formulate their stochastic estimation error as a function of the data sampling order, and propose a practical optimisation algorithm. Our simulations demonstrate reduced variance compared to related methods, and experiments on two domain shift image classification benchmarks show improved target domain accuracy.
【3】Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework
标题：基于AoA的户外定位的自适应学习策略：一个全面的框架
链接：https://arxiv.org/abs/2605.05055
摘要
：Localization in 5G and 6G networks is essential for important use cases such as intelligent transportation, smart factories, and smart cities. Although deep learning has enabled improving localization accuracy, depending on the deployment scenario and the effort required for dataset collection campaigns on a given infrastructure, the training process for localization models can vary significantly. Furthermore, with respect to feature selection, recent works have demonstrated the robustness of angle-of-arrival (AoA) based localization. In view of these two points, we propose an adaptive framework for AoA-based localization that consists of two alternative learning strategies, each suited either for large or small training datasets. The proposed framework is evaluated on a real, massive multiple input multiple output (mMIMO) orthogonal frequency division multiplexing (OFDM) outdoor channel state information (CSI) dataset. First, we investigate offline learning when large training datasets are available; we propose a hierarchical framework that first distinguishes between line of sight (LoS) and non line of sight (NLoS) regions and then moves to more fine grained localization in the respective region. This approach provides high-performance localization through accumulated batch retraining and an integrated hyperparameter optimization mechanism. Second, when only a small training dataset is available, an online learning framework is proposed, using incremental tree-based and ensemble-based models for handling streaming data and continuously updating mode, as well as an online few-shot learning model for rapidly initializing new classes from a limited labeled support set. These results showcase that highly accurate robust localization can be achieved incrementally during network operation by exploiting online learning, alleviating the need for large dataset collection campaigns.
【4】Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
标题：直接产品流匹配：将辐射和角度动力学脱钩以实现Few-Shot适应
链接：https://arxiv.org/abs/2605.05054
摘要：Recent flow matching (FM) methods improve the few-shot adaptation of vision-language models, by modeling cross-modal alignment as a continuous multi-step flow. In this paper, we argue that existing FM methods are inherently constrained by incompatible geometric priors on pre-trained cross-modal features, resulting in suboptimal adaptation performance. We first analyze these methods from a polar decomposition perspective (i.e., radial and angular sub-manifolds). Under this new geometric view, we identify three overlooked limitations in them: 1) Angular dynamics distortion: The radial-angular coupling induces non-uniform speed on the angular sub-manifold, leading to regression training difficulty and extra truncation errors. 2) Radial dynamics neglect: Feature normalization discards modality confidence, failing to distinguish out-of-distribution and in-distribution data, and abandoning crucial radial dynamics. 3) Context-agnostic unconditional flow: Dataset-specific information loss during pre-trained cross-modal feature extraction remains unrecovered. To resolve these issues, we propose warped product flow matching (WP-FM), a unified Riemannian framework that reformulates alignment on a warped product manifold. Within this framework, we derive direct product flow matching (DP-FM) by introducing a constant-warping metric, which yields a decoupled cylindrical manifold (i.e., direct product manifold). DP-FM enables independent radial evolution and constant-speed angular geodesic transport, effectively eliminating angular dynamics distortion while preserving radial consistency. Meanwhile, we incorporate classifier-free guidance by conditioning the flow on the pre-trained VLMs' hidden states to inject missing dataset-specific information. Extensive results across 11 benchmarks have demonstrated that DP-FM achieves a new state-of-the-art for multi-step few-shot adaptation.
【5】Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts
标题：粒度混合专家的自适应反索引路由算法
链接：https://arxiv.org/abs/2605.04952
摘要：Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests that performance improves with increasingly granular experts, i.e., many small experts instead of a few large ones. However, this regime substantially increases routing cost, which can dominate computation. We introduce adaptive inverted-index routing for MoE (AIR-MoE), an inverted-index-inspired routing architecture based on vector quantization (VQ). In a first stage, AIR-MoE performs coarse shortlisting by assigning tokens to VQ codewords to construct a candidate set of experts. In a second stage, fine scoring computes exact routing scores restricted to this shortlist. This two-stage procedure approximates true top-k routing while avoiding full expert scoring and, in contrast to prior work, imposing no structural constraints on expert parameters. AIR-MoE serves as a drop-in replacement for standard routers and requires no modifications to the model architecture or loss function. We further provide a lower bound on the mass recall achieved by AIR-MoE that yields insights into its inner workings. Empirically, we demonstrate that AIR-MoE achieves improved performance compared to existing routing approaches in granular MoE settings.
【6】A Foundation Model for Zero-Shot Logical Rule Induction
标题：Zero-Shot逻辑规则归纳的基础模型
链接：https://arxiv.org/abs/2605.04916
备注：Camera-ready version accepted at IJCAI 2026, with full appendices
摘要：Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer.
【7】Gaze4HRI: Zero-shot Benchmarking Gaze Estimation Neural-Networks for Human-Robot Interaction
标题：Gaze4HRI：Zero-Shot基准凝视估计用于人机交互的神经网络
链接：https://arxiv.org/abs/2605.04770
备注：Accepted to the 2026 IEEE International Conference on Automatic Face and Gesture Recognition (FG 2026)
摘要
：While zero-shot appearance-based 3D gaze estimation offers significant cost-efficiency by directly mapping RGB images to gaze vectors, its reliability in Human-Robot Interaction (HRI) settings remains uncertain. Existing benchmarks frequently overlook fundamental HRI conditions, such as dynamic camera viewpoints and moving targets in video. Furthermore, current cross-dataset evaluations often suffer from a complexity gap, where methods trained on diverse datasets are tested on significantly smaller and less varied sets, failing to assess true robustness. To bridge these gaps, we introduce Gaze4HRI, a large-scale dataset (50+ subjects, 3,000+ videos, 600,000+ frames) designed to evaluate state-of-the-art performance against critical HRI variables: illumination, head-gaze conflict, as well as the motion of camera and gaze target in video. Our benchmark reveals that all evaluated methods fail in at least one condition, identifying steeply-downward gaze as a universal failure point. Notably, PureGaze trained on the ETH-X-Gaze dataset uniquely maintains resilience across all other conditions. These results challenge the recent focus in the literature on complex spatial-temporal modeling and Transformer-based architectures. Instead, our findings suggest that extensive data diversity, as exemplified by the ETH-X-Gaze dataset, serves as the primary driver of zero-shot robustness in unconstrained environments, while resilience-enhancing frameworks, such as PureGaze's self-adversarial loss for gaze feature purification, provide a substantial further improvement. Ultimately, this study establishes a rigorous benchmark that provides practical guidelines for practitioners as well as reshaping future research. The dataset and codes are available at https://gazeforhri.github.io.
【8】Temporal Structure Matters for Efficient Test-Time Adaptation in Wearable Human Activity Recognition
标题：时间结构对于可穿戴人类活动识别中有效的测试时间自适应至关重要
链接：https://arxiv.org/abs/2605.04617
摘要：Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled test streams, yet existing methods largely inherit assumptions from vision tasks and underexploit the inherent inter-window temporal structure in WHAR streams. In this paper, we revisit such temporal structure as a feature-conditioned inference signal rather than merely an output-space smoothing prior. We derive the insight that temporal continuity and observation-induced feature deviations provide complementary cues for determining when to preserve or release temporal inertia and where to route prediction refinement during likely transitions. Building upon this insight, we propose SIGHT, a lightweight and backpropagation-free TTA framework for WHAR, enabling real-time edge deployment. SIGHT estimates predictive surprise by comparing the current feature with a prototype-based expected state, and then uses the resulting feature deviation to guide geometry-aware transition routing based on prototype alignment and stream-level marginal habit tracking. Evaluations on real-world datasets confirm that SIGHT outperforms existing TTA baselines while reducing computational and memory costs.
【9】YOTOnet: Zero-Shot Cross-Domain Fault Diagnosis via Domain-Conditioned Mixture of Experts
标题：YOTOnet：通过领域条件混合专家进行Zero-Shot跨领域故障诊断
链接：https://arxiv.org/abs/2605.04528
摘要：Mechanical equipment forms the critical backbone of modern industrial production, yet domain shift severely limits the generalization of deep learning based fault diagnosis models across different equipment and operating conditions.Inspired by the success of foundation models in achieving zero-shotgeneralization, we propose YOTOnet (You Only Train Once), a novel architecture specifically designed for cross-domain fault diagnosis in mechanical equipment.YOTOnet comprises three core components: (1) a physics-aware Invariant Feature Distiller that extracts domain-agnostic representations using multi-scale dilated convolutions and FFT-based time-frequency fusion,(2) Domain-Conditioned Sparse Experts (DC-MoE) that adaptively route inputs to specialized processors via learned gating without external meta-data, and (3) a dual-head classification system with auxiliary supervision.Extensive validation on five public bearing datasets (CWRU, MFPT, XJTU,OTTAWA, HUST) through 30 cross-dataset protocols demonstrates the superiority of YOTOnet compared with other state-of-the-art methods. Critically, we observe a clear scaling effect-average test F1 improves from 0.5339(1 training dataset) to 0.705 (4 datasets), with a clear gain when moving from 3 to 4 datasets. These findings provide empirical evidence that foundation model principles can enable robust, train-once deployment for industrial fault diagnosis.
【10】FL-Sailer: Efficient and Privacy-Preserving Federated Learning for Scalable Single-Cell Epigenetic Data Analysis via Adaptive Sampling
标题：FL-Sailer：通过自适应采样进行可扩展单细胞表观遗传数据分析的高效和隐私保护联邦学习
链接：https://arxiv.org/abs/2605.04519
摘要：Single-cell ATAC-seq (scATAC-seq) enables high-resolution mapping of chromatin accessibility, yet privacy regulations and data size constraints hinder multi-institutional sharing. Federated learning (FL) offers a privacy-preserving alternative, but faces three fundamental barriers in scATAC-seq analysis: ultra-high dimensionality, extreme sparsity, and severe cross-institutional heterogeneity. We propose FL-Sailer, the first FL framework designed for scATAC-seq data. FL-Sailer integrates two key innovations: (i) adaptive leverage score sampling, which selects biologically interpretable features while reducing dimensionality by 80%, and (ii) an invariant VAE architecture, which disentangles biological signals from technical confounders via mutual information minimization. We provide a convergence guarantee, showing that FL-Sailer converges to an approximate solution of the original high-dimensional problem with bounded error. Extensive experiments on synthetic and real epigenomic datasets demonstrate that FL-Sailer not only enables previously infeasible multi-institutional collaborations but also surpasses centralized methods by leveraging adaptive sampling as an implicit regularizer to suppress technical noise. Our work establishes that federated learning, when tailored to domain-specific challenges, can become a superior paradigm for collaborative epigenomic research.
【11】Gradient Scaling Effects in Adaptive Spectral PINNs for Stiff Nonlinear ODEs
标题：刚性非线性ODE自适应谱PinN中的梯度缩放效应
链接：https://arxiv.org/abs/2605.04502
备注：8 pages, 4 figures, 1 table. This work appeared at the ICLR 2026 AI&PDE Workshop on OpenReview
摘要：Physics-Informed Neural Networks (PINNs) often struggle to train reliably on stiff and oscillatory dynamical systems due to poor optimization conditioning. While prior work has emphasized representational remedies such as spectral parameterizations, the optimization implications of initial-condition (IC) embeddings in adaptive spectral PINNs have not been well characterized. In this work, we show that the choice of IC gating function induces explicit time-dependent gradient scaling, which interacts with spectral representations during training. Using a nonlinear stiff spring-pendulum ODE as a controlled benchmark, we compare exponential and linear IC gates in combination with fixed and adaptive Fourier spectral trunks. We observe stiffness-dependent changes in relative dominance for adaptive PINNs: at moderate stiffness ($k=20$), exponential gating often yields lower error but exhibits heterogeneous behavior across random seeds, whereas at higher stiffness ($k=60$), linear gating becomes preferable, with additional reversals observed at larger $k$. These trends hold for both relative $L^2$ error and maximum pointwise error and are confirmed by paired Wilcoxon signed-rank tests with Holm correction. Overall, our results demonstrate that IC embeddings are not a neutral design choice in PINNs: the induced gradient scaling materially shapes optimization conditioning in stiff regimes, with distinct sensitivity patterns in baseline and adaptive spectral models.
【12】One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving
标题：一个池，两个缓存：自适应HBM分区加速生成推荐服务
链接：https://arxiv.org/abs/2605.04450
摘要
：Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memory to one improves its efficiency but degrades the other. Existing systems optimize them in isolation, overlooking that the optimal EMB-KV allocation ratio can shift by up to 0.35 across workload regimes, leaving 20-30\% latency improvement unrealized. While online reallocation is required to close this gap, naive approaches introduce H2D refill traffic on the critical path, causing P99 SLO violations. To address this, we present HELM, which jointly manages HBM allocation and request routing at runtime through two key components: (1) Adaptive Memory Allocation, a three-layer PPO-based controller (frozen base policy, online residual adapter, and burst-aware recovery controller) that achieves $32\,\mathrm{μs}$ decision latency while staying within 0.024-0.029 of the offline-optimal ratio; and (2) EMB-KV-Aware Scheduling, which routes requests by jointly considering KV residency, embedding locality, and node load to avoid routing inefficiencies under heterogeneous allocations. Evaluations on three production-scale datasets over a 32-node A100 cluster show that HELM reduces P99 latency by 24-38\% over the best static policy and achieves 93.5-99.6\% SLO satisfaction across Steady, Trend, and Burst workloads, significantly outperforming state-of-the-art baselines without sacrificing throughput.
【13】DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptation
标题：DeFed-GMM-DaDiL：一个用于域适应的去中心化联邦框架
链接：https://arxiv.org/abs/2605.04324
摘要：Decentralized multi-source domain adaptation seeks to transfer knowledge from multiple heterogeneous and related source domains to an unlabeled target domain in a decentralized setting. We address this challenge through a fully decentralized federated approach, DeFed-GMM-DaDiL, an extension of the GMM-Dataset Dictionary Learning (DaDiL) framework. Each client models its dataset as a Gaussian Mixture Model (GMM), and the federation jointly approximates them via labeled Wasserstein barycenters of shared, learnable GMM atoms. This design enables adaptation without a central server while preserving clients' privacy. We empirically study the stability of the learned representations in scenarios where the target domain has missing classes. Empirical results demonstrate that DeFed-GMM-DaDiL maintains stable and consistent shared representations across clients, effectively reconstructs missing classes, and achieves competitive performance on multi-source domain adaptation benchmarks.
【14】QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization
标题：QUIVER：代理人辅助进化多目标优化中的成本感知自适应偏好查询
链接：https://arxiv.org/abs/2605.04267
备注：Accepted at Genetic and Evolutionary Computation Conference (GECCO '26)
摘要：Interactive multi-objective optimization systems face a budget allocation dilemma: one can spend resources on expensive objective evaluations or on eliciting decision-maker preferences that identify the relevant region of the Pareto set. Moreover, preference elicitation itself spans modalities with different information content and cognitive burden, ranging from cheap, noisy pairwise preference statements (PS) to richer but costlier indifference adjustments (IA). We study cost-aware optimization under an unknown scalarization and introduce QUIVER (Query-Informed Value Estimation for Regret), a surrogate-assisted evolutionary multi-objective optimizer that adaptively chooses between objective evaluations and heterogeneous preference queries. At each step, QUIVER selects the next action by maximizing the expected decision-quality improvement per unit total cost. Across DTLZ and WFG benchmarks under synthetic decision-maker models, QUIVER achieves the lowest final utility regret on challenging WFG problems (utility regret of 2.14 on WFG4, 2.82 on WFG9: a 25% improvement over baselines), outperforming all single-modality baselines. We analyze how the optimal mix of PS and IA adapts to problem difficulty: on easy problems (DTLZ2), QUIVER selects 80\% PS queries; on hard problems (WFG9), it shifts to 35% IA queries. This adaptive modality selection demonstrates cost-aware preference learning in action.
【15】MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
标题：MP-ISMoE：混合精确交互式专家混合，实现高效的迁移学习
链接：https://arxiv.org/abs/2605.04058
备注：AAAI2026 Accepted
摘要：Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significantly reducing trainable parameters yet suffering from substantial memory overhead caused by gradient backpropagation during fine-tuning. While memory-efficient transfer learning (METL) circumvents this challenge by bypassing backbone gradient computation via lightweight small side networks, its stringent memory constraint severely limits learning capacity of side networks, thereby significantly compromising performance. To address these limitations, we propose a novel Mixed-Precision Interactive Side Mixture-of-Experts framework (MP-ISMoE). Specifically, we first propose a Gaussian Noise Perturbed Iterative Quantization (GNP-IQ) scheme to quantize weights into lower-bits while effectively decreasing quantization errors. By leveraging memory conserved from GNP-IQ, we subsequently employ Interactive Side Mixture-of-Experts (ISMoE) to scaling up side networks without sacrificing overall memory efficiency. Different from conventional mixture-of-experts, ISMoE learns to select optimal experts by interacting with salient features from frozen backbones, thus suppressing knowledge forgetting and boosting performance. Extensive experiments across diverse vision-language and language-only tasks demonstrate that MP-ISMoE remarkably promotes accuracy compared to state-of-the-art METL approaches, while maintaining comparable parameter and memory efficiency.
强化学习(8篇)
【1】Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning
标题：多臂强盗中分布遗憾的统一框架和强化学习
链接：https://arxiv.org/abs/2605.05102
备注：Accepted at the Conference of Learning Theory (COLT) 2026
摘要：We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all confidence levels $δ\in (0,1]$, thereby characterizing the regret distribution across the full range of $δ$. We present a simple UCBVI-style algorithm with exploration bonus $\min\{c_{1,k}/N, c_{2,k}/\sqrt{N}\}$, where $N$ denotes the visit count and $(c_{1,k},c_{2,k})$ are user-specified parameters. For arbitrary parameter sequences, we derive general gap-independent and gap-dependent distributional regret bounds, yielding a principled characterization of how the parameters control the trade-off between expected performance, tail risk, and instance-dependent behavior. In particular, our bounds achieve optimal trade-offs between expected and distributional regret in both minimax and instance-dependent regimes. As a special case, for multi-armed bandits with $A$ arms and horizon $T$, we obtain a distributional regret bound of order $\mathcal{O}(\sqrt{AT}\log(1/δ))$, confirming the conjecture of Lattimore & Szepesvári (2020, Section 17.1) for the first time.
【2】Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization
标题：强化学习用于成分概括和结果级优化
链接：https://arxiv.org/abs/2605.04920
摘要：Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approaches often rely on supervised fine-tuning, which encourages models to imitate target outputs. This token-level training paradigm fails to capture the global compositional structure required for generalizing to unseen combinations. In this work, we investigate whether compositional generalization can instead be improved through outcome-level reinforcement learning. We adopt Group Relative Policy Optimization to optimize models based on feedback on their final outputs. Within this framework, we explore both a simple binary outcome reward and a composite reward that provides additional composition feedback. Experiments on multiple compositional benchmarks show that reinforcement learning improves compositional generalization compared to supervised fine-tuning. Further analysis reveals that supervised models tend to overfit frequent training compositions, whereas reinforcement learning improves compositional generalization by reshaping the output distribution, particularly for more complex composition types.
【3】A Harmonic Mean Formulation of Average Reward Reinforcement Learning in SMDPs
标题：SMDP中平均奖励强化学习的调和平均公式
链接：https://arxiv.org/abs/2605.04880
摘要：Recent research has revived and amplified interest in algorithms for undiscounted average reward reinforcement learning in infinite-horizon, non-episodic (continuing) tasks. Semi-Markov decision processes (SMDPs) are of particular interest. In SMDPs, discrete actions stochastically generate both rewards and durations, and the objective is to optimize the average reward rate. Existing algorithms approach this by optimizing the ratio of rewards to durations. However, when rewards and durations are non-stationary (in the infinite horizon), this can be incorrect. This paper presents a novel modified harmonic mean operator that correctly computes reward rates even under such conditions. This yields model-free learning algorithms that can work with SMDPs, while maintaining robustness to non-stationary reward and duration distributions over time. We prove theoretical properties of the modified harmonic mean operator, and empirically demonstrate its efficacy in comparison to existing algorithms.
【4】SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning
标题：SPHERE：缓解深度强化学习专家混合中谱可塑性的损失
链接：https://arxiv.org/abs/2605.04712
备注：Accepted to ICML 2026
摘要：In deep reinforcement learning (DRL), an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from plasticity loss: their ability to learn new skills from new experiences diminishes over training. Recently, Mixture-of-Experts (MoE) networks have been reported to enable scaling laws and facilitate the learning of diverse skills. However, in continual reinforcement learning settings, their performance can degenerate as learning proceeds, indicating a loss of plasticity. To address this, building on Neural Tangent Kernel (NTK) theory, we formalize the plasticity loss in MoE policies as a loss of spectral plasticity. We then derive a tractable proxy for spectral plasticity, one expressible in terms of individual expert feature matrices. Leveraging this proxy, we introduce SPHERE, a practical Parseval penalty tailored for MoE-based policies that alleviates the loss of spectral plasticity. On MetaWorld and HumanoidBench, SPHERE improves average success under continual RL by 133% and 50% over an unregularized MoE baseline, while maintaining higher spectral plasticity throughout training.
【5】Data-dependent Exploration for Online Reinforcement Learning from Human Feedback
标题：基于数据依赖的在线反馈强化学习探索
链接：https://arxiv.org/abs/2605.04477
摘要：Online reinforcement learning from human feedback (RLHF) has emerged as a promising paradigm for aligning large language models (LLMs) by continuously collecting new preference feedback during training. A foundational challenge in this setting is exploration, which requires algorithms that enable the LLMs to generate informative comparisons that improve sample-efficiency in online RLHF. Existing exploration strategies often derive bonuses via on-policy expectations, which are difficult to estimate reliably from the limited historical preference data available during training; as a result, the policy can prematurely down-weight under-explored regions that may contain high-value behaviors. In this paper, we propose data-dependent exploration for preference optimization (DEPO), a simple and scalable method that leverages historical data to construct an extra uncertainty bonus for high-uncertainty regions, encouraging exploration toward potentially high-value data. Theoretically, we provide a data-dependent regret bound for the proposed algorithm, showing that it adapts to the hardness of the learning task itself and can be tighter than worst-case bounds in practice. Empirically, the proposed method consistently outperforms strong baselines across benchmarks, demonstrating improved sample efficiency.
【6】Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies
标题：用于提取黑匣子强化学习策略的分层支持载体状态划分
链接：https://arxiv.org/abs/2605.04254
备注：Accepted for poster presentation at HHAI 2026
摘要：We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies. By partitioning a distillation dataset of state action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4\% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8\% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1\%. Our results pave the path towards a more flexible form of distillation where both the decision boundary and surrogate models can be chosen within a margin of the original black box behavior.
【7】Constraint-Enhanced Reinforcement Learning Based on Dynamic Decoupled Spherical Radial Squashing
标题：基于动态解耦球面径向挤压的约束增强强化学习
链接：https://arxiv.org/abs/2605.04185
备注：27 pages, 60 figures
摘要
：When deploying reinforcement learning policies to physical robots, actuator rate constraints -- hard limits on how fast each joint can move per control step -- are unavoidable. These limits vary substantially across joints due to differences in motor inertia, power bandwidth, and transmission stiffness, creating pronounced heterogeneity that existing methods fail to handle geometrically: the per-joint feasible region forms a high-dimensional box in action-increment space, yet QP projection and spherical parameterization methods impose isotropic ball-shaped constraints, exponentially under-covering the true feasible set as heterogeneity grows. This paper proposes Dynamic Decoupled Spherical Radial Squashing (DD-SRad), which resolves this mismatch by computing a position-adaptive radius independently for each actuator, achieving tight alignment with the true per-joint feasible region. DD-SRad satisfies per-step hard constraints with probability~1, preserves well-conditioned gradients throughout training, and admits exact policy gradient backpropagation with zero runtime solver overhead. MuJoCo benchmark experiments demonstrate the highest task return at zero constraint violation -- matching the unconstrained upper bound -- with 30%--50% improvement in constraint-space coverage over spherical baselines. High-fidelity IsaacLab simulations with Unitree H1 and G1 humanoid robots confirm end-to-end optimality parameterized directly from official joint specifications, validating a systematic pathway from hardware datasheets to safe deployment.
【8】Designing a double deep reinforcement learning selection tool for resilient demand prediction
标题：设计用于弹性需求预测的双深度强化学习选择工具
链接：https://arxiv.org/abs/2605.04068
摘要：The use of artificial intelligence in supply chain forecasting has attracted many scientific studies for several decades. However, the process of selecting an appropriate forecasting solution becomes a daunting task. This complexity arises due to the distinct features inherent to each dataset. Research to tackle this issue has been performed since the eighties but recent development of demand forecasting has opened new perspectives. This research aims to enhance automatic forecasting model selection by proposing a novel architecture that acts as a double deep reinforcement learning agent, selecting automatically a forecasting model from the forecasting committee at the time of prediction. Moreover, a novel early-stopping approach based on average reward convergence has been introduced to expedite training time. To evaluate the model's performance, an empirical study was conducted utilizing grocery sales datasets and snack demands datasets. The experimental results demonstrate the robustness of the proposed approach when compared to state-of-the-art methods.
符号|符号学习(1篇)
【1】ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor
标题：ANDRE：一个基于注意力的神经符号可区分规则提取器
链接：https://arxiv.org/abs/2605.04193
备注：35 pages, 8 figures, 10 tables
摘要：Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings. Classical ILP relies on discrete combinatorial rule search and is brittle under uncertainty, while differentiable ILP methods typically depend on predefined rule templates or inaccurate fuzzy operators that suffer from vanishing gradients or poor approximation of logical structure when reasoning over probabilistic predicate valuations. This paper proposes an Attention-based Neuro-symbolic Differentiable Rule Extractor (ANDRE), a novel ILP framework that learns first-order logic programs by optimizing over a continuous rule space with attention-based logical operators. ANDRE replaces both rule templates and logical operators with fully differentiable, attention-driven conjunction and disjunction operators that approximate logical min-max semantics, enabling accurate, stable, and interpretable reasoning over probabilistic data. By softly selecting, negating, or excluding predicates within each rule, ANDRE supports flexible rule induction while preserving symbolic structure. Extensive experiments on classical ILP benchmarks, large-scale knowledge bases, and synthetic datasets with probabilistic predicates and noisy supervision demonstrate that ANDRE achieves competitive or superior predictive performance while reliably recovering correct symbolic rules under uncertainty. In particular, ANDRE remains robust to moderate label noise, substantially outperforming existing differentiable ILP methods in both rule extraction quality and stability.
医学相关(8篇)
【1】Conditional outlier detection for clinical alerting
标题：临床警报的有条件异常值检测
链接：https://arxiv.org/abs/2605.05124
备注：AMIA 2010 Annual Symposium proceedings, pp. 286-290. Homer R. Warner Best Paper Award
摘要：We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management actions using past patient cases stored in an electronic health record (EHR) system. Our hypothesis is that patient-management actions that are unusual with respect to past patients may be due to a potential error and that it is worthwhile to raise an alert if such a condition is encountered. We evaluate this hypothesis using data obtained from the electronic health records of 4,486 post-cardiac surgical patients. We base the evaluation on the opinions of a panel of experts. The results support that anomaly-based alerting can have reasonably low false alert rates and that stronger anomalies are correlated with higher alert rates.
【2】Vol-Mark: A Watermark for 3D Medical Volume Data Via Cubic Difference Expansion and Contrastive Learning
标题：Vol-Mark：通过立方差扩展和对比学习的3D医疗体积数据的水印
链接：https://arxiv.org/abs/2605.04705
摘要：Today, advances in medical technology extensively utilize 3D volume data for accurate and efficient diagnostics. However, sharing these data across networks in telemedicine poses significant security risks of data tampering and unauthorized copying. To address these challenges, this paper proposes a novel reversible-zero watermarking approach, termed Vol-Mark, for medical volume data to protect their ownership and authenticity in telemedicine. The proposed Vol-Mark method offers two key benefits: 1) it designs a volume data feature extractor that leverages contrastive learning to efficiently extract discriminative and stable volumetric features, ensuring robustness against 3D attacks; 2) it introduces the cubic difference expansion (c-DE) technique, which leverages the 3D integer wavelet transform to embed watermark bits into neighboring voxels within cubes at low-frequency coefficients. The voxel differences within each cube are expanded to create embedding space, and a majority voting mechanism is employed during extraction to enhance reliability. The embedding process incurs low distortion and supports lossless removal, thereby preserving the integrity and diagnostic accuracy of medical volume data. Through these two benefits, Vol-Mark enables both integrity verification and ownership verification. Integrity verification is first performed, and ownership verification through hypothesis testing is further conducted to enhance reliability, particularly under data tampering or watermark removal attacks. Comprehensive experimental results show the effectiveness of the proposed method and its superior robustness against conventional, geometric, and hybrid attacks on medical volume data. In particular, through multiple tasks evaluations, Vol-Mark consistently achieves an ACC above 0.90 in most attack scenarios, outperforming existing methods by a clear margin.
【3】Evidence-based anomaly detection in clinical domains
标题
：临床领域的基于证据的异常检测
链接：https://arxiv.org/abs/2605.04664
备注：Published at AMIA Annual Symposium 2007. PDF-only submission; LaTeX source not available (paper was authored in Word)
摘要：Anomaly detection methods can be very useful in identifying interesting or concerning events. In this work, we develop and examine new probabilistic anomaly detection methods that let us evaluate management decisions for a specific patient and identify those decisions that are highly unusual with respect to patients with the same or similar condition. The statistics used in this detection are derived from probabilistic models such as Bayesian networks that are learned from a database of past patient cases. We apply our methods to the problem of identifying unusual patient-management decisions in post-surgical cardiac patients.
【4】Event-Based Early Warning of Vineyard Disease Risk from Environmental Time Series
标题：环境时间序列基于事件的葡萄园疾病风险预警
链接：https://arxiv.org/abs/2605.04548
摘要：Accurate early warning of vineyard disease risk from environmental observations is essential for timely intervention and more sustainable crop protection. However, many existing studies formulate disease prediction as daily presence classification, which can favor persistence-driven predictions and provide only limited support for actionable short-horizon warning. In this paper, we present an event-based approach for early warning of vineyard disease risk from environmental time series and evaluate it through a vineyard case study. Rather than predicting daily disease status, the task is reformulated to predict transitions into annotated disease-risk periods within a future window of 3-7 days. To reduce fragmentation caused by short interruptions in the binary labels, new events are defined only after a minimum disease-free gap. This formulation encourages models to capture environmental precursors associated with upcoming risk periods instead of merely reproducing temporal persistence. Using multi-year agro-meteorological data, we construct input representations that capture humidity dynamics, rainfall accumulation, temperature variability, and seasonal structure through cyclic temporal encoding. We evaluate representative methods from classical machine learning and deep learning, including XGBoost, Long Short-Term Memory (LSTM) networks, and Temporal Convolutional Networks (TCNs), using both standard classification metrics and an event-oriented early warning protocol. The results show that the event-based formulation supports practical short-horizon warning, while the compared models exhibit distinct trade-offs between event recall, lead time, and false-alert behavior. Overall, the study underscores the importance of problem formulation in environmental time-series learning and demonstrates the value of event-based prediction for vineyard disease warning systems.
【5】DALight-3D: A Lightweight 3D U-Net for Brain Tumor Segmentation from Multi-Modal MRI
标题：DALight-3D：用于从多模式MRI中进行脑肿瘤分割的轻量级3D U-Net
链接：https://arxiv.org/abs/2605.04518
摘要：Automatic brain tumor segmentation from multi-modal MRI remains challenging because volumetric models often incur substantial computational cost. This paper presents DALight-3D, a compact 3D U-Net variant that combines depthwise separable 3D convolutions, identifier-conditioned normalization, cross-slice attention, and adaptive skip fusion. The method is evaluated on the Medical Segmentation Decathlon Task01 BrainTumour benchmark under matched optimization settings against standard 3D U-Net, Attention U-Net, Residual 3D U-Net, and V-Net baselines. In the reported 50-epoch comparison, DALight-3D achieves a mean Dice of 0.727 with 2.22M parameters, compared with 0.710 Dice and 3.20M parameters for Residual 3D U-Net. Component-wise ablations show consistent performance degradation when SepConv, identifier-conditioned normalization, CSA, or SSFB is removed. These results indicate that DALight-3D offers a favorable accuracy-efficiency trade-off within the present benchmark setting.
【6】Efficient Handwriting-Based Alzheimer,s Disease Diagnosis Using a Low-Rank Mixture of Experts Deep Learning Framework
标题：使用低级别混合专家深度学习框架进行高效的基于手写的阿尔茨海默病诊断
链接：https://arxiv.org/abs/2605.04079
备注：26 pages, 6 figures, and 17 tables
摘要：Early and reliable detection of Alzheimer's disease (AD) is crucial for timely clinical intervention and improved patient management. It also supports the evaluation of emerging therapeutic strategies. In this paper, we propose a Low-Rank Mixture of Experts (LoRA-MoE) deep learning framework for Alzheimer's disease diagnosis based on handwriting analysis. Handwriting signals provide a non-invasive and scalable digital biomarker that captures subtle cognitive-motor impairments associated with early AD progression. The proposed architecture allows multiple experts to specialize in different handwriting patterns while sharing a common base network. This design enables efficient learning of general representations while reducing interference between experts. Each expert is equipped with lightweight low-rank adapters. This mechanism significantly reduces the number of trainable parameters compared with standard Mixture of Experts (MoE) models and improves training stability. The proposed framework is evaluated on the Diagnosis AlzheimeR WIth haNdwriting (DARWIN) dataset. Extensive experiments are conducted, including ablation studies on key architectural parameters such as hidden dimension size, number of experts, and LoRA rank. The method is compared with multilayer perceptron (MLP) and conventional MoE architectures. In addition, stacking ensemble strategies (StackMean and StackMax) are investigated to improve robustness and predictive performance. Experimental results show that the LoRA-MoE framework achieves powerful diagnostic performance while activating significantly fewer parameters during inference. These results highlight the potential of the proposed approach as an accurate and computationally efficient solution for handwriting-based Alzheimer's disease screening and digital health applications.
【7】Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
标题：临床序列模型表示的稀疏自动编码器分解：特征复杂性、任务专业化和死亡率预测
链接：https://arxiv.org/abs/2605.04072
备注：17 pages, 4 figures, 7 tables
摘要
：Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter autoregressive clinical sequence model, at all 10 residual stream extraction points on INSPECT (outpatient) and MIMIC-IV (ICU). SAE decomposition reveals progressive abstraction across transformer depth: layer-0 features are near-perfect token detectors (45.7% singleton), while layer-6 features span approximately 30 token types across multiple clinical categories (0.5% singleton). Under full-sequence simple linear probes, SAE features outperform dense representations for discrete event prediction (mortality) while dense representations outperform for continuous magnitude prediction (length of stay) - a probe-level representational phenomenon that does not extend to clinically relevant leakage-safe windows, where dense representations match or exceed SAE features across all tested settings (eICU-CRD 48-hour AUC: SAE 0.871 versus dense 0.880; base model zero-shot, SAE dictionaries trained on eICU activations; MIMIC-IV: 0.836 versus 0.914; INSPECT 1-year/3-year: 0.697 versus 0.800). A delta-mode intervention method reduces SAE perturbation noise by 86x, enabling cleaner feature-level experiments, though the resulting perturbation effects are larger than random controls in 3 of 4 conditions but not formally significant. Feature reproducibility across random seeds is 21%, and individual features should be interpreted as illustrative rather than stable.
【8】Investigating Trustworthiness of Nonparametric Deep Survival Models for Alzheimer's Disease Progression Analysis
标题：调查阿尔茨海默病进展分析的非参数深度生存模型的可信度
链接：https://arxiv.org/abs/2605.04063
备注：12 pages, 6 figures, 2 tables, IEEE/ACM Conference on Connected Health: Applications, Systems, and Engineering Technologies
摘要：Alzheimer's Dementia (AD) is a progressive neurodegenerative disease marked by irreversible decline, making reliable modeling of its progression essential for effective patient care. Progression-aware methods such as survival analysis are therefore crucial tools for the early detection and monitoring of AD. Recent advancements in deep learning have demonstrated remarkable performance in survival tasks, but alarmingly fewer studies have been conducted in the domain of AD. Further, the studies that do exist do not consider learned bias within the model itself, which could result in unfair and unreliable predictions toward certain marginalized groups. As such, we conduct a rigorous study of fairness in AD progression analysis along with a thorough feature importance study to determine the characteristics which are most important for reliable AD predictions. Furthermore, we propose two novel fairness metrics, called Time-Dependent Concordance Impurity and Kaplan-Meier Fairness, to quantify bias with respect to sensitive attributes such as sex, race, and education in nonparametric survival models. Our study demonstrates that while deep learning powered survival models are robust tools which can aid clinicians in AD care decisions, they often exhibit considerable bias, representing important avenues for future research.
蒸馏|知识提取(6篇)
【1】Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
标题：基于偏好的自蒸馏：通过奖励正则化超越KL匹配
链接：https://arxiv.org/abs/2605.05040
摘要：On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a stronger external teacher has driven recent work on on-policy self-distillation, where the same model serves as both teacher and student under different prompt contexts. Yet, existing self-distillation methods largely reduce learning to KL matching toward the context-augmented teacher model. This approach often suffers from training instability and can degrade reasoning performance over time. Moreover, self-distillation from the same model with prompt augmentation lacks the exploratory diversity provided by a genuine external teacher. To address these limitations, we move beyond fixed-teacher KL matching and propose \textbf{P}reference-\textbf{B}ased \textbf{S}elf-\textbf{D}istillation (\textbf{PBSD}), which revisits on-policy self-distillation through a reward-regularized perspective. Instead of directly matching the teacher distribution, we derive a reward-regularized objective whose analytic optimum is a reward-reweighted teacher distribution, yielding a target policy provably superior to the original teacher under this objective. Practically, PBSD optimizes preference gaps between teacher and student samples while maintaining on-policy student sampling. We support this framework with a statistical analysis of the induced preference-learning problem, formally establishing when on policy self-distillation is preferable to learning from an external teacher in our setting. Experiments on mathematical reasoning and tool-use benchmarks across multiple model scales demonstrate that PBSD consistently achieves the strongest average performance among comparable baselines, showing improved training stability over prior self-distillation baselines while preserving token efficiency.
【2】Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
标题：配电桥采样、自奖励RL和自蒸馏
链接：https://arxiv.org/abs/2605.04542
摘要：Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as effective ways to improve LLM performance. However, the relationship among RL, distillation, and sampling remains unclear. In this study, we focus on the power distribution, the target distribution of power sampling, and show that the power distribution bridges sampling, self-reward KL-regularized RL, and self-distillation. From the sampling perspective, we show that inexpensive local approximations cannot reproduce sequence-level power without information about possible suffixes. From the RL perspective, the power distribution is the closed-form optimizer of KL-regularized RL when the model's sequence-level log-probabilities are used as the reward. This identification leads to power self-distillation, an offline distillation surrogate that shares the same target distribution and amortizes the cost of power sampling into supervised training on teacher samples. We further show that power self-distillation can achieve self-reward sharpening, while improvement in a downstream true reward is governed by the covariance between true reward and self-reward under the power distribution. Experiments on reasoning tasks support our analysis: power sampling raises self-reward, true-reward gains depend on alignment with self-reward, and power self-distillation can match or exceed the performance of power sampling at much lower inference cost.
【3】Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference
标题：推荐LoRA：蒸馏作为高效推理的结构化计算分配
链接：https://arxiv.org/abs/2605.04341
备注：Preprint. 9 pages main text, 18 pages total, 2 figures, 9 tables
摘要
：We study distillation for large language models under explicit compute constraints, with the goal of producing student models that are not only cheaper to train, but structurally efficient at inference time. While prior approaches to parameter-efficient distillation, such as LoRA, reduce adaptation cost, they leave the dense backbone unchanged and therefore fail to deliver meaningful inference savings. We propose Budgeted LoRA, a distillation framework that treats model compression as a structured compute allocation problem. Instead of using a fixed student architecture, we introduce a global compute budget that sets the final target fraction of dense computation retained. Under this constraint, the model redistributes capacity across dense and low-rank pathways via (i) module-level dense retention coefficients, (ii) adaptive low-rank allocation, and (iii) post-training compression that selectively removes, approximates, or preserves dense components. This formulation yields a family of students controlled by a single budget dial. Empirically, Budgeted LoRA matches standard LoRA perplexity at a moderate budget with a 1.74x compressed-module speedup; at an aggressive budget it achieves a 4.05x speedup with moderate perplexity degradation, and it preserves higher accuracy on function-style in-context learning probes. These results suggest that, under compute-constrained distillation, retaining behavior is less about matching perplexity or removing more parameters than it is about controlling how dense computation is transferred to low-rank pathways.
【4】Hardware-Aware Neural Feature Extraction for Resource-Constrained Devices
标题：资源受限设备的硬件感知神经特征提取
链接：https://arxiv.org/abs/2605.04282
备注：This paper has been accepted for publication at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2026. \c{opyright}IEEE
摘要：Visual SLAM is a core component of spatial computing systems, yet deploying learned local feature extractors on microcontroller-class hardware remains challenging due to memory, bandwidth, and quantization constraints. While modern neural descriptors provide strong robustness, their practical adoption is often hindered by system-level bottlenecks that are not captured by FLOP-based efficiency metrics. In this work, we introduce Gideon, a hardware-aware neural feature extractor explicitly designed for resource-constrained devices. Our approach combines relational knowledge distillation from a SuperPoint teacher with differentiable neural architecture search (DNAS) under strict memory and operator constraints. Unlike conventional design pipelines, we treat quantization stability and dynamic-range compactness as first-class objectives. We show that architectural choices such as replacing Batch Normalization with affine layers significantly improve INT8 robustness, and that descriptor dimensionality directly governs quantization resilience. Deployed on STM32N6, Gideon achieves 9.003 ms inference time (111 fps) while remaining below a 1.5 MB memory footprint. Remarkably, INT8 quantization induces negligible degradation and occasionally matches full-precision performance. These results demonstrate that robust learned feature extraction can be reconciled with embedded hardware constraints through holistic hardware-algorithm co-design.
【5】Validity-Calibrated Reasoning Distillation
标题：有效性校准推理蒸馏
链接：https://arxiv.org/abs/2605.04078
摘要：Reasoning distillation aims to transfer multi-step reasoning capabilities from large language models to smaller, more efficient ones. While recent methods have shown promising gains, they typically rely on static teacher-student hierarchies and frame distillation as trajectory imitation. This is misaligned with the structure of reasoning, where intermediate steps are often locally under-specified: global correctness constrains the final answer, but does not uniquely determine each intermediate move. We propose validity-calibrated reasoning distillation, a framework that treats reasoning distillation as a problem of local learning-signal allocation rather than path alignment. Instead of enforcing token-level imitation, we compare the student's and teacher's proposed next-step actions under the same prefix and use their relative local validity to modulate the strength of the distillation update. This yields a dynamic, context-dependent supervision mechanism that preserves the teacher's structural guidance while adapting update strength to local reasoning quality. Across mathematical reasoning, code generation, and instruction-following benchmarks, our method consistently outperforms strong distillation baselines. These results indicate that effective LLM reasoning distillation is governed not by rigid trajectory imitation, but by principled, locally calibrated allocation of learning signal.
【6】Continual Distillation of Teachers from Different Domains
标题：不同领域教师的不断升华
链接：https://arxiv.org/abs/2605.04059
备注：Accepted to CVPR 2026
摘要：Deep learning models continue to scale, with some requiring more storage than many large-scale datasets. Thus, we introduce a new paradigm: Continual Distillation (CD), where a student learns sequentially from a stream of teacher models without retaining access to earlier teachers. CD faces two challenges: teacher training data is unavailable, and teachers have varying expertise. We show that external unlabeled data enables Unseen Knowledge Transfer (UKT), allowing the student to acquire information from domains not present in the training data, while known to the teacher. We also show that sequential distillation causes Unseen Knowledge Forgetting (UKF) when transferred knowledge is lost after training on later teachers. To better trade off between UKT and UKF, we propose Self External Data Distillation (SE2D), a method that preserves logits on external data to stabilize learning across heterogeneous teachers. Experiments on multiple benchmarks show that SE2D reduces UKF and improves cross-domain generalization. The code and implementation for this work are publicly available at: https://github.com/Nicolas1203/continual_distillation.
推荐(1篇)
【1】Rethinking Convolutional Networks for Attribute-Aware Sequential Recommendation
标题：重新思考卷积网络以实现属性感知顺序推荐
链接：https://arxiv.org/abs/2605.04723
备注：Accepted at IJCAI-ECAI 2026
摘要：Attribute-aware sequential recommendation entails predicting the next item a user will interact with based on a chronologically ordered history of past interactions, enriched with item attributes. Existing methods typically leverage self-attention mechanisms to aggregate the entire sequence into a unified representation used for next-item prediction. While effective, these models often suffer from high computational complexity and memory consumption, limiting their ability to process long user histories. This constraint restricts the model's capacity to fully capture long-term user preferences. In some scenarios, modeling item interactions purely through attention may also not be the most effective approach to extract sequential patterns. In this work, we propose ConvRec, an alternative method with linear computational and memory complexity that employs convolutional layers in a hierarchical, down-scaled fashion to generate compact, yet expressive sequence representations. To further enhance the model's ability to capture diverse sequential patterns, each layer aggregates the neighboring items gradually to reach a comprehensive sequence representation. Extensive experiments on four real-world datasets demonstrate that our approach outperforms state-of-the-art sequential recommendation models, highlighting the potential of convolution-based architectures for efficient and effective sequence modeling in recommendation systems. Our implementation code and datasets are available here https://github.com/ismll-research/ConvRec.
超分辨率|去噪|去模糊|去雾(1篇)
【1】Learning-based Statistical Refinement for Denoising
标题：基于学习的去噪统计细化
链接：https://arxiv.org/abs/2605.04332
摘要
：This work proposes a learning-based statistical refinement method for improving the denoising results of a given denoiser without knowing the precise noise distribution or accessing clean images or calibration data. While there are many existing successful denoising approaches for handling different kinds of noise, they typically require accurate modelling of the images and the noise (implicitly or explicitly), and hence the denoising results can be suboptimal due to different practical factors such as imperfect models, unreliable noise assumptions, or low quality data. In particular, when clean image samples are not available and there is a lack of knowledge of the underlying noise distribution, which is the case in various practical situations, the results may not well align with the noise statistics. The unawareness of the useful statistical information leads to suboptimal results. This work aims to make the best use of the statistical information to improve the consistency between the given denoising results and the noise statistics, under the assumption that the noise is conditionally pixel-wise independent given the clean signal. A method, based on a Bayesian formulation of an auxiliary signal in the noisy data, is proposed for evaluating the consistency of the denoising results, without precise information on noise distribution. By leveraging the statistical information from noisy data, the method enhances the statistical noise consistency and improves denoising quality.
自动驾驶|车辆|车道检测等(3篇)
【1】Physiologically Grounded Driver Behavior Classification: SHAP-Driven Elite Feature Selection and Hybrid Gradient Boosting for Multimodal Physiological Signals
标题：生理基础驾驶员行为分类：SHAP驱动的精英特征选择和多峰生理信号的混合梯度增强
链接：https://arxiv.org/abs/2605.05120
摘要：An interpretable and scalable framework for decoding driving behaviors from multimodal physiological signals is proposed in this study. We utilize multimodal physiological driving behavior large-scale dataset comprising synchronized electroencephalogram (EEG), electromyography (EMG), and galvanic skin response (GSR) signals. Our approach involves rigorous preprocessing followed by a domain-specific feature extraction pipeline targeting time-domain, frequency-domain, and derived physiological indices. To address high dimensionality, we employ SHAP-based elite feature selection, retaining the top 250 features to reduce computational overhead while preserving predictive power. Hyperparameter optimization for extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM) models is conducted using Bayesian optimization via Optuna. Finally, a weighted soft-voting ensemble is constructed to leverage the complementary strengths of both gradient boosting frameworks. The results demonstrate that the proposed ensemble achieves a test accuracy of 80.91% and a macro-F1 score of 0.79, significantly outperforming single-modality baselines and traditional machine learning models. Ablation studies confirm an 8% performance gain over the best single modality (EEG), validating the necessity of multimodal fusion. SHAP analysis further validates the physiological plausibility of the model, revealing that the EEG contributes the majority of predictive weight, GSR and EMG features provide critical discriminatory signals for high-arousal and motor-intensive maneuvers.
【2】Federated Learning for Early Prediction of EV Charging Demand
标题：联邦学习用于电动汽车充电需求的早期预测
链接：https://arxiv.org/abs/2605.04993
摘要：Accurate forecasting of electric vehicle (EV) charging demand is critical for grid stability, infrastructure planning, and real-time charging optimization. In this work, we study the problem of early prediction of charging demand, where the total energy of a session is estimated using only information available at plug-in time and during the first minutes of charging. This enables actionable decisions while the session is still in progress, which is of direct importance for EV network operators. We construct a session-level dataset from the Adaptive Charging Network (ACN), combining session metadata with early-window charging measurements, and derive tabular features capturing user intent, temporal patterns, and initial charging behavior. We focus on a single operational depot, Caltech, and model intra-depot heterogeneity through station-level client partitions while evaluating multiple model families in a federated learning (FL) setting. Our results show that federated models can approach centralized predictive performance while keeping data in-depot, enabling privacy-enhanced training across distributed charging infrastructures. Overall, we demonstrate that reliable demand estimates can be obtained early in the session with minimal data, and that FL provides a practical pathway toward scalable and privacy-aware analytics for EV charging networks. Code is available at https://github.com/Indigma-Innovations/federated-learning-ev-charging-demand.
【3】CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
标题：CRAFT：反事实到互动的强化驾驶政策微调
链接：https://arxiv.org/abs/2605.04470
摘要：Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit fundamental trade-offs: closed-loop RL fine-tuning provides grounded feedback from executed actions but is constrained by the sparsity of informative events, whereas counterfactual fine-tuning provides dense supervision over candidate futures but inherits bias from imperfect future estimates. We introduce Counterfactual-to-Interactive Reinforcement Fine-Tuning (CRAFT), an on-policy framework that formulates closed-loop post-training as proxy-residual optimization. CRAFT uses group-normalized counterfactual advantages as a dense proxy for real closed-loop advantages and aligns this proxy with the closed-loop world through grounded residual correction from interaction-critical events. To stabilize adaptation, CRAFT regularizes the online policy toward an EMA teacher via asymmetric KL self-distillation. Theoretically, CRAFT decomposes the real closed-loop policy gradient into proxy and residual terms under the same visited-state distribution, reducing residual variance with an aligned proxy while mitigating proxy bias through grounded residual approximation. Empirically, CRAFT achieves the strongest closed-loop gains on Bench2Drive across hierarchical planning, vision-language-action, and vocabulary-scoring architectures. Ablations, scaling behavior, stability analyses, and transfer results further validate the complementary roles of dense counterfactual proxy and grounded residual correction. Project page: https://currychen77.github.io/CRAFT.
点云|SLAM|雷达|激光|深度RGBD相关(1篇)
【1】Quadrature-TreeSHAP: Depth-Independent TreeSHAP and Shapley Interactions
标题：Quadrature-TreeSHAP：深度独立TreeSHAP和Shapley相互作用
链接：https://arxiv.org/abs/2605.04497
摘要
：Shapley values are a standard tool for explaining predictions of tree ensembles, with Path-Dependent SHAP being the most widely used variant. Despite substantial progress, existing methods still exhibit trade-offs between depth-dependent runtime, numerical stability, and support for higher-order interactions. To address these challenges, we introduce Quadrature-TreeSHAP, a quadrature-based reformulation of Path-Dependent TreeSHAP that is numerically stable, naturally extends to any-order Shapley interaction values and is practically insensitive to tree depth. Our implementation supports both CPU and GPU and is integrated into XGBoost. Our method is based on a weighted-Banzhaf interaction polynomial, which expresses Banzhaf interaction values as expectations under a feature participation probability $p$. Shapley values and any-order interaction values are then recovered by integrating these polynomials over $p$ from 0 to 1. We evaluate these integrals using Gauss-Legendre quadrature, and show that, in practice, only 8 fixed quadrature points are sufficient to reach machine precision. In fact, Quadrature-TreeSHAP with 8 fixed points achieves greater numerical stability than TreeSHAP. This fixed-point formulation removes depth dependence from the inner computation and enables efficient SIMD execution. We confirm these advantages empirically. On 12 XGBoost benchmarks, Quadrature-TreeSHAP computes Shapley values 1.06x-10.59x faster than TreeSHAP on CPU and 1.84x-6.95x faster than GPUTreeSHAP on GPU. Shapley pairwise interactions are 3.80x-58.11x faster on CPU, with higher-order interactions achieving speedups of up to 1200x compared to TreeSHAP-IQ.
联邦学习|隐私保护|加密(2篇)
【1】Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity
标题：注释质量差异下的可信联合标签分布学习
链接：https://arxiv.org/abs/2605.04827
摘要：Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambiguity, but its success relies on high-fidelity label distributions that are costly to obtain and thus often noisy. Motivated by privacy-sensitive applications, we study Federated Label Distribution Learning (Fed-LDL), where data isolation further induces heterogeneous annotation quality across clients, making local updates unevenly reliable and breaking sample-size-based aggregation (e.g., FedAvg). To address this trust dilemma, we propose FedQual, a quality-aware Fed-LDL framework with two coupled mechanisms: (i) quality-adaptive client training guided by a global semantic anchor that calibrates low-quality clients while preserving high-quality autonomy, and (ii) reliability-aware server aggregation that reweights client contributions by effective reliable information rather than raw sample size. To enable rigorous evaluation, we construct four new Fed-LDL benchmarks (FER-LDL, FI-LDL, PIPAL-LDL, and KADID-LDL) with controlled annotation quality disparity. We further provide a theoretical guarantee showing that under heterogeneous supervision quality, client-specific calibration is strictly better than any uniform calibration. Extensive experiments on the proposed benchmarks demonstrate the effectiveness of FedQual.
【2】Knowledge-Free Correlated Agreement for Incentivizing Federated Learning
标题：激励联邦学习的无知识相关协议
链接：https://arxiv.org/abs/2605.04747
摘要：We introduce Knowledge-Free Correlated Agreement (KFCA) to reward client contributions in federated learning (FL) without relying on ground truth, a public test set, or distribution knowledge. Under categorical reports and an honest majority, KFCA is strictly truthful, addressing the label-flipping vulnerability of Correlated Agreement (CA). We evaluate KFCA on federated LLM adapter tuning and a real-world PCB inspection task, showing efficient real-time reward computation suitable for decentralized and blockchain-based incentive designs.
推理|分析|理解|解释(9篇)
【1】Gated Multimodal Learning for Interpretable Property Energy Performance Prediction and Retrofit Scenario Analysis
标题：门控多模式学习用于可解释的物业能源性能预测和改造场景分析
链接：https://arxiv.org/abs/2605.05088
摘要：Achieving resilient and sustainable cities requires scalable approaches to decarbonising residential buildings, which account for about 20% of UK greenhouse gas emissions and 25% of energy-related emissions in the European Union. Energy Performance Certificates (EPCs) support regulation and retrofit planning, but their reliance on on-site inspections limits timely city-scale assessment. This study introduces a gated multimodal model to predict Standard Assessment Procedure (SAP) energy efficiency and Environmental Impact (EI) scores by integrating EPC tabular variables, assessor-written free text, and Geographic Information System (GIS)-derived spatial features describing footprint geometry, height, area, and orientation. Sample-wise gating learns property-specific modality weights, while an auxiliary band classification head stabilises training. In a Westminster, London case study, the model predicts SAP and EI scores with MAEs of 4.03 and 4.76 points and R2 values of 0.757 and 0.748, respectively, achieving a mean MAE of 4.39. Ablation results show that full multimodal fusion outperforms unimodal and bimodal baselines for both score prediction and band-level classification. Interpretability analyses provide decision-relevant evidence: gating weights indicate strong reliance on assessor text; SHAP highlights main fuel, built form, and construction age band; text occlusion prioritises roof and wall fields; and spatial attribution is dominated by height and footprint area, with sensitivity to footprint shape. The validated framework is further applied to retrofit scenarios for wall insulation, roof insulation, and window glazing upgrades, indicating projected improvements in SAP, EI, annual energy cost, and equivalent CO2 emissions. Overall, the framework provides scalable property-level evidence for retrofit screening, intervention prioritisation, and net-zero housing transitions.
【2】Agentic Vulnerability Reasoning on Windows COM Binaries
标题：Windows COM二进制文件上的突出漏洞推理
链接：https://arxiv.org/abs/2605.05000
摘要：Windows Component Object Model (COM) services run with elevated privileges and are widely accessible to authenticated users, making race conditions in these binaries a critical surface for local privilege escalation. We present SLYP, an end-to-end agentic pipeline that discovers race condition vulnerabilities in COM binaries and generates debugger-verified proof-of-concept (PoC) code. SLYP exposes binary exploration, COM inspection, and dynamic debugging as reusable tool interfaces, giving agents the static context, COM activation metadata, and debugger feedback needed to move from vulnerability discovery to verified PoC generation. On a benchmark of 20 COM objects covering 40 vulnerability cases, SLYP achieves 0.973 F1, outperforming production coding agents by up to 0.208 F1 and the state-of-the-art static analyzer by 3.3x in bug discovery. For PoC generation, production coding agents in their default setup (without our COM inspection and dynamic debugging tools) verify essentially no cases on either frontier model, whereas SLYP's interactive toolsets enable it to autonomously synthesize working PoCs for 67.5% of cases on the strongest configuration. Deployed on production Windows services, SLYP discovers 28 previously unknown vulnerabilities across nine COM services, all confirmed by the Microsoft Security Response Center (MSRC) with 16 CVEs assigned and $140,000 in bounties. Furthermore, SLYP is designed with generalizable binary analysis and debugging interfaces, making it readily applicable to other commercial off-the-shelf (COTS) binaries beyond Windows COM services.
【3】When Does Gene Regulatory Network Inference Break? A Controlled Diagnostic Study of Causal and Correlational Methods on Single-Cell Data
标题：基因调节网络推理何时破裂？单细胞数据因果关系方法的对照诊断研究
链接：https://arxiv.org/abs/2605.04930
备注：19 pages, 10 figures
摘要：Despite theoretical advantages, causal methods for Gene Regulatory Network (GRN) inference from single-cell RNA-seq data consistently fail to match or outperform correlation-based baselines in many realistic benchmarks, a persistent puzzle which casts doubt on the value of causality for this task. We argue that existing benchmarks are insufficiently controlled to answer this question because they evaluate on real or semi-real data where multiple pathologies co-occur, confounding failure modes, and obscuring the specific conditions under which different inference methods excel or fail. To address this gap, we introduce a controlled diagnostic framework that isolates seven biologically motivated pathologies (dropout, latent confounders, cell-type mixing, feedback loops, network density, sample size, and pseudotime drift) and measure how six representative methods spanning three inference paradigms degrade as each pathology intensifies. Across 6,120 controlled experiments, we find that causal methods genuinely dominate in clean and structurally favorable regimes, but specific pathologies (notably dropout and latent confounders) selectively neutralize their advantages. We further introduce an error-type decomposition that reveals methods with similar aggregate accuracy commit qualitatively different errors. To probe whether single-pathology effects persist when multiple stressors co-occur, we perform an interaction sweep over the three most impactful pathologies and find that their joint effects are sub-additive, while also exposing density-conditional cross-overs invisible to single-dial analysis. Our findings offer a nuanced understanding of when and why different methods succeed or fail for GRN inference, providing actionable insights for method development and practical guidance for practitioners.
【4】Feature importance analysis for patient management decisions
标题：患者管理决策的特征重要性分析
链接：https://arxiv.org/abs/2605.04666
备注：Published at MEDINFO 2010. doi:10.3233/978-1-60750-588-4-861. PDF-only submission; LaTeX source not available
摘要：The objective of this paper is to understand what characteristics and features of clinical data influence physician's decision about ordering laboratory tests or prescribing medications the most. We conduct our analysis on data and decisions extracted from electronic health records of 4486 post-surgical cardiac patients. The summary statistics for 335 different lab order decisions and 407 medication decisions are reported. We show that in many cases, physician's lab-order and medication decisions can be well predicted from a small subset of all features.
【5】Capabilities of Auto-encoders and Principal Component Analysis of the Reduction of Microstructural Images; Application on the Acceleration of Phase-Field Simulations
标题：自动编码器的能力和微结构图像缩减的主成分分析;在相场模拟加速中的应用
链接：https://arxiv.org/abs/2605.04229
备注：21 pages, 8 figures. Preprint version of article published in Computational Materials Science
摘要：In this work, a data-driven framework based on Phase-Field simulations data is proposed to highlight the capabilities of neural networks to ensure accurate low dimensionality reduction of simulated microstructural images and to provide time-series analysis. The dataset was indeed constructed from high-fidelity Phase-Field simulations. Analyses demonstrated that the association of auto-encoder neural networks and principal component analyses leads to ensure efficient and significant dimensionality reduction: 1/196 of reduction ratio with more than 80% of accuracy. These findings give insight to apply analyses on data from the latent dimension. Application of Long Short Term Memory (LSTM) neural networks showed the possibility of making next frame predictions; that makes possible the acceleration of Phase-Field simulation without the need of high computing resources. We discussed the application of such a framework on various areas of research. Different methods are proposed from the conducted analyses, in order to ensure dimensionality reduction, including auto-encoders, principal component analysis and Artificial Neural Networks, and time-series analysis, including LSTM and Gated Recurrent Unit (GRU).
【6】Model synthesis and identifiability analysis of stiff chemical reaction systems with inVAErt networks
标题：具有inVaErt网络的刚性化学反应系统模型综合与可识别性分析
链接：https://arxiv.org/abs/2605.04134
摘要：We consider the problem of learning data-driven replicas for stiff systems of ordinary differential equations arising in chemical kinetics that can be evaluated with high computational efficiency. We first focus on training emulators for families of reaction equations under varying reaction rates, using conditional residual networks or long-short term memory architectures. We then apply a recently proposed data-driven framework known as ``inVAErt networks'' to address the ill-posed inverse problem of inferring reaction rates, integration time, and possibly initial conditions from a target set of species concentrations - a problem that has received relatively little attention in the literature. The proposed approach is demonstrated on chemical systems with reversible and irreversible kinetics, spanning 2 to 20 differential equations, 3 to 20 chemical species, and 3 to 25 reaction rate parameters. Relative root mean squared errors produced by the proposed emulators range from $10^{-5}$ for lower-dimensional systems to $10^{-4}$ and $10^{-3}$ for an air pollution model and a hydrogen-air reaction system, respectively. Manifolds of non-identifiable reaction rates recovered by the proposed approach can be analytically verified for simple systems and are consistent with local identifiability analysis in higher dimensions.
【7】Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
标题：平衡聚合：理解和修复GRPO中的聚合偏差
链接：https://arxiv.org/abs/2605.04077
摘要
：Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for its simplicity and effectiveness. However, an important design choice remains underexplored: how token-level policy gradient terms are aggregated within each sampled group. Standard GRPO uses sequence aggregation, while recent work has advocated token aggregation as a better alternative. We show that these two rules induce different optimization biases: token aggregation introduces sign-length coupling, while sequence aggregation implicitly downweights longer responses through sequence-level equal weighting. To address this tension, we propose \textbf{Balanced Aggregation (BA)}, a simple drop-in replacement that computes token-level means separately within the positive and negative subsets and then combines them with sequence-count-based weights. Experiments with Qwen2.5-Math-7B and Qwen3-1.7B on DAPO-17k and Polaris, evaluated on six reasoning and coding benchmarks, show that BA consistently improves training stability and final performance over standard token and sequence aggregation. Our analysis further shows that the relative effectiveness of token and sequence aggregation is largely governed by response-length variation and the positive-negative length gap, highlighting aggregation as a critical design dimension in GRPO-style RLVR.
【8】Scalable inference of spatial regions and temporal signatures from time series
标题：从时间序列中可扩展地推断空间区域和时间特征
链接：https://arxiv.org/abs/2605.05008
摘要：Regionalization aims to partition a spatial domain into contiguous regions that share similar characteristics, enabling more effective spatial analysis, policy making, and resource management. Existing approaches for spatial regionalization typically rely on static spatial snapshots rather than evolving time series. Meanwhile, most time series clustering methods ignore spatial structure or enforce spatial continuity through ad hoc regularization, constraining the number of inferred regions a priori either explicitly or implicitly. Utilizing the minimum description length principle from information theory, here we propose an efficient and fully nonparametric framework for the regionalization of spatial time series. Our method jointly infers a spatial partition along with a set of representative time series archetypes ("drivers") that best compress a spatiotemporal dataset, with a runtime log-linear in the number of time series. We demonstrate that this method can accurately recover planted regional structure and drivers in synthetic time series, and can extract meaningful structural regularities in large-scale empirical air quality and vegetation index records. Our method provides a principled and scalable framework for spatially contiguous partitioning, allowing interpretable temporal patterns and homogeneous regions to emerge directly from the data itself.
【9】BOOOM: Loss-Function-Agnostic Black-Box Optimization over Orthonormal Manifolds for Machine Learning and Statistical Inference
标题：BOOOM：用于机器学习和统计推断的正交流形上的损失函数不可知黑箱优化
链接：https://arxiv.org/abs/2605.04087
摘要：Optimization over the Stiefel manifold $\mathrm{St}(p,d)$, the set of $p \times d$ column-orthonormal matrices, is fundamental in statistics, machine learning, and scientific computing, yet remains challenging in the presence of non-convex, non-smooth, or black-box objectives. Existing methods largely rely on either convex relaxations or gradient-based Riemannian optimization, limiting applicability in derivative-free and highly multimodal settings. We propose \textsc{BOOOM} (Black-box Optimization Over Orthonormal Manifolds), a general-purpose framework for loss-function-agnostic optimization on $\mathrm{St}(p,d)$. The key idea is a global Givens rotation-based parametrization that maps the manifold to an unconstrained Euclidean angle space while preserving feasibility exactly. Building on this representation, BOOOM employs a structured, parallelizable, derivative-free search based on Recursive Modified Pattern Search, enabling systematic exploration through plane-wise rotations without requiring gradient information and facilitating escape from poor local optima. We establish a unified theoretical framework showing equivalence between angle-space and manifold optimization, transfer of stationarity, and global convergence in probability under mild conditions. Empirical results across diverse problems, including heterogeneous quadratic optimization, low-rank and sparse matrix decomposition, independent component analysis, and orthogonal joint diagonalization, among other widely studied settings, demonstrate strong performance relative to state-of-the-art methods, particularly in non-smooth and highly multimodal regimes. We further illustrate its practical utility through a novel supervised PCA formulation applied to metabolomics data in colorectal cancer.
检测相关(2篇)
【1】PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation
标题：SemEval-2026上的SK任务9：使用带合成数据增强的Ensemble Gemma模型进行多语言极化检测
链接：https://arxiv.org/abs/2605.05159
摘要：We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per language using Low-Rank Adaptation (LoRA), augmented with synthetic data generated by a large language model (LLM). We employ three synthetic data strategies (direct generation, paraphrasing, and contrastive pair creation) using GPT-4o-mini, with a multi-stage quality filtering pipeline including embedding-based deduplication. We find that per-language threshold tuning on the development set yields 2 to 4\% F1 improvements without retraining. We also use weighted ensembles of 12B and 27B model predictions with per-language strategy selection. Our final system achieves a mean macro-F1 of 0.811 across all 22 languages, ranking 2nd overall of the participating teams, with 1st place finishes in 3 languages and top-3 in 8 languages. We also find that alternative architectures (XLM-RoBERTa, Qwen3) that showed strong development set performance suffered 30 to 50\% F1 drops on the test set, highlighting the importance of generalization.
【2】A Regulatory Governance Framework for AI-Driven Financial Fraud Detection in U.S. Banking: Integrating OCC, SR 11-7, CFPB, and FinCEN Compliance Requirements for Model Development, Validation, and Monitoring Lifecycles
标题：美国银行业人工智能驱动的金融欺诈检测的监管治理框架：集成OSC、SR 11-7、CFPB和FinCEN合规要求，以实现模型开发、验证和监控生命周期
链接：https://arxiv.org/abs/2605.04076
备注：38 pages, submitted to Cogent Business & Management (Taylor & Francis), currently under peer review
摘要：U.S. financial institutions deploying AI-based fraud detection face a fragmented compliance landscape spanning four regulatory frameworks -- OCC Bulletin 2011-12, SR 11-7, the CFPB AI circular, and FinCEN BSA/SAR requirements -- with no integrated governance life cycle connecting these requirements to model development, validation, and monitoring practice. This paper presents the Regulatory Governance Framework for AI-Driven Financial Fraud Detection (RGF-AFFD), a three-tier governance architecture empirically anchored in a multi-study empirical program. Using the IEEE-CIS dataset (590,540 transactions) and ULB benchmark (284,807 transactions), we benchmark six architectures including an LSTM+XGBoost ensemble, and conduct ablation, temporal drift, SHAP interpretability, and BISG fairness analyses. The LSTM+XGBoost ensemble achieves ROC-AUC of 0.9289 (F1: 0.6360) with a benefit-cost ratio of 6:1. XGBoost demonstrates the strongest temporal stability (delta-AUC = -0.0017 versus -0.0626 for LSTM). The RDT-FG Regulatory Digital Twin meta-model translates metrics into four regulator-specific health scores and a composite Regulatory Fitness Index for continuous compliance monitoring. The RGF-AFFD is the first integrated deployment blueprint to simultaneously satisfy OCC, SR 11-7, CFPB, and FinCEN requirements, supported by a community bank implementation vignette and four evidence-based policy recommendations.
分类|识别(3篇)
【1】Koopman Identification of Nonlinear Systems via Reservoir Liftings
标题：通过水库蓄水进行非线性系统的Koopman识别
链接：https://arxiv.org/abs/2605.04917
摘要：Learning tractable linear representations of nonlinear dynamical systems via Koopman operator theory is often hindered by dictionary selection, temporal memory encoding, and numerical ill-conditioning. Inspired by Reservoir Computing (RC) paradigm, this paper introduces the RC-Koopman framework, which interprets reservoir as a stateful, finite-dimensional Koopman dictionary whose temporal depth is explicitly controlled by its spectral radius. We show that the Echo State Property (ESP) guarantees well-posedness and favorable numerical conditioning of the lifted Koopman approximation. A correlation-based spectral radius selection algorithm aligns reservoir memory with dominant system timescales. Analysis reveals how the finite memory of the reservoir determines which Koopman eigenfunctions remain observable from the lifted features. Evaluation on synthetic benchmarks demonstrates that RC-Koopman achieves a favorable balance between reconstruction accuracy of the underlying nonlinear dynamics and dynamical stability, compared to Extended Dynamic Mode Decomposition (EDMD) and Hankel-based lifting approaches. Code available at: https://github.com/NEAR-the-future/RC-Koopman.git
【2】To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition
标题：删除还是删除？双路径学习解决多模式情感识别中的模式冲突
链接：https://arxiv.org/abs/2605.04877
摘要：Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucially, conflicts differ in resolvability: benign conflicts stem from missing, weak, or ambiguous cues and can be mitigated by cross-modal calibration, while severe conflicts arise from intrinsically contradictory (e.g., sarcasm) or misleading signals, for which forced fusion may amplify errors. Recognizing this, we propose Dual-Path Conflict Resolution (DCR), a unified framework that learns when to fuse and when to drop modalities. Path I (Affective Fusion Distiller, AFD) performs reverse distillation from audio/visual teachers to a textual student using temporally weighted class evidence, thereby enhancing representation-level calibration and improving fusion when alignment is beneficial. Path II (Affective Discernment Agent, ADA) formulates MER as a contextual bandit that selects among fusion and unimodal predictions based on a dual-view state and a calibration-aware reward, enabling decision-level arbitration under irreconcilable conflicts without requiring per-modality reliability labels. By taking into account the full multimodal context and coupling soft calibration with hard arbitration, DCR reconciles conflicts that can be aligned while bypassing misleading modalities when fusion is harmful. Across five benchmarks covering both dialogue-level and clip-level MER, DCR consistently outperforms competitive baselines or achieves highly competitive results. Further ablations, conflict-specific subset evaluation, and modality-selection analysis verify that AFD and ADA are complementary and jointly improve robust conflict-aware emotion recognition.
【3】Sequential Strategic Classification with Multi-Stage Selective Classifiers
标题：具有多阶段选择性分类器的顺序策略分类
链接：https://arxiv.org/abs/2605.04202
备注：Shorter version presented as a poster at GameNets 2026
摘要：Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes made by classifiers, typically turning to dishonest actions when they are less costly than genuine efforts. Prior works have demonstrated a fundamental inability to get out of this conundrum by only focusing on the design of a classifier. We note that prior work also heavily focuses on either one-shot settings or repeated interaction with the same classifier. Real-world decision making is often multi-stage, involving a sequence of potentially different classifiers as an agent progresses. This paper introduces a sequential, stochastic, multi-stage model of strategic classification, by capturing how agents adapt their behavior, through improvement actions (enhancing both observable features and true attributes) and gaming actions (enhancing only observable features), over multiple levels of classification with increasing difficulty as well as reward. For each level, we adopt a selective classifier that can abstain from making a prediction at low confidence. Consequently, a positive (resp. negative) outcome leads to promotion (resp. demotion) of the agent to the next higher (resp. lower) level, while abstention keeps the agent at the same level. We fully characterize the agent's optimal instantaneous action under selective classifiers and compare the long-term properties and utility of the agent repeatedly following an optimal myopic policy of either no-improvement (never choose the improvement action) or no-gaming (never choose the gaming action). We further examine design principles over the sequence of classifiers that yield higher long-term utility for the latter policy, thereby effectively incentivizing genuine effort in the long run.
表征(5篇)
【1】Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
标题：总管转向揭示了神经网络表示和行为的共享几何结构
链接：https://arxiv.org/abs/2605.05115
摘要：Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space defined by different geometries, and measure the behavioral trajectories they induce. In particular, we test whether interventions that respect the geometry of activation space will yield behaviors close to those the model exhibits naturally. Concretely, we first fit an activation manifold $M_h$ to representations and a behavior manifold $M_y$ to output probability distributions. We then test the link $M_h \leftrightarrow M_y$ via interventions: we find that steering along $M_h$, which we term manifold steering, yields behavioral trajectories that follow $M_y$, while linear steering -- which assumes a Euclidean geometry -- cuts through off-manifold regions and hence produces unnatural outputs. Moreover, optimizing interventions in activation space to produce paths along $M_y$ recovers activation trajectories that trace the curvature of $M_h$. We demonstrate this bidirectional relationship between the geometry of representation and behavior across tasks and modalities. In language models, we use reasoning tasks with cyclic and sequential geometries as well as in-context learning tasks with more complex graph geometries. In a video world model, we use a task with geometry corresponding to physical dynamics. Overall, our work shows that geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals. This recasts the core problem of steering from finding the right direction to finding the right geometry.
【2】Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs
标题：通过条款-文字超图上的两极感知表示学习进行不饱和的核心预测
链接：https://arxiv.org/abs/2605.04819
备注：Accepted at ICML 2026. Camera-ready version coming soon
摘要
：Graph neural networks have been widely used in Boolean satisfiability (SAT) tasks to learn structural information from SAT formulas. The goal of these studies is to solve SAT instances or to enhance SAT solvers, including tasks such as unsat-core prediction. However, most existing approaches model a SAT formula as a bipartite graph or a directed acyclic graph, which are less expressive in capturing higher-order interactions among literals and clauses. Moreover, these approaches are limited in modeling intrinsic polarity-related properties of SAT, such as the complementary relationship between the positive and negative literals of a variable. To address these limitations, we propose a polarity-aware representation learning framework over clause-literal hypergraphs. We model SAT formulas as clause-literal hypergraphs augmented with a clause incidence graph to capture higher-order structural interactions. We then introduce a polarity-aware decomposed mechanism that separates variable representations into polarity invariant and equivariant components, explicitly modeling the relationship between positive and negative literals, with the resulting literal representations propagated along the hypergraph structure. We further incorporate a polarity-inversion consistency regularization to reinforce polarity-consistent representations during training. Experimental results on multiple SAT datasets demonstrate the effectiveness of the proposed approach.
【3】Beyond Rigid Geometries: The Spline-Pullback Metric for Universal Diffeomorphic SPD Representation Learning
标题：超越刚性几何：泛半纯SPD表示学习的样条回拉度量
链接：https://arxiv.org/abs/2605.04406
摘要：The integration of Symmetric Positive Definite (SPD) matrices into deep learning has historically relied on fixed algebraic Riemannian metrics. Analogous to hand-crafted features in classical machine learning, these static formulations impose rigid geometries limiting network expressivity and adaptability. Recent attempts to parameterize these geometries often violate the axioms of primary matrix functions through unconstrained powers or rank-dependent scaling, inviting spatial folding, loss of global surjectivity, and gradient collapse at spectral singularities. In this paper, we introduce the Spline-Pullback Metric (SPM), instantiated as Spectral-SPM and Cholesky-SPM, marking a paradigm shift from static metric selection to universal geometric approximation. By parameterizing the global diffeomorphism via a rank-invariant, monotonically constrained B-spline, SPM acts as a dense universal approximator for strictly increasing $C^1$ diffeomorphisms and theoretically subsumes existing pullback metrics while enabling localized non-linear spectral modelling. Topologically, SPM provides a globally bijective pullback geometry precluding rank-swapping discontinuities and gradient instabilities. Empirically, SPM achieves a state-of-the-art performance across 3 datasets utilizing Linear Probes, SPDNets, and deep Riemannian ResNets.
【4】Intermediate Representations are Strong AI-Generated Image Detectors
标题：中间表示是强大的人工智能生成图像检测器
链接：https://arxiv.org/abs/2605.04358
摘要：The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for effective AI-generated image detectors. However, current training-based detection techniques are typically computationally costly and can hardly be generalized to unseen data domains, while training-free methods fall short in detection performance. To bridge this gap, we propose a search-based method employing data embedding sensitivity in intermediate layers to detect AI-generated images. Given a set of real and AI-generated images, our method examines the similarity between original image embeddings and perturbed image embeddings, and detects AI-generated images based on the similarity. We examine the proposed method on two comprehensive benchmarks: GenImage and Forensics Small. Our method exhibits improved performance across different datasets compared to both training-free and training-based state-of-the-art methods. On average, our method achieves the largest performance gain on the Forensics Small benchmark by 39.61% compared to the best training-free method and 5.14% compared to the best training-based method in AUROC score.
【5】LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems
标题：LUCAS-MEGA：一个用于土壤-环境系统表示学习的大规模多模态数据集
链接：https://arxiv.org/abs/2605.04323
备注：27 pages, 7 figures, 1 table
摘要：Understanding soil is fundamental to agriculture, carbon cycling, and environmental sustainability, yet progress is limited by fragmented and heterogeneous datasets that constrain modeling to small-scale predictive settings rather than high-dimensional representation learning. We introduce LUCAS-MEGA, a large-scale multimodal dataset constructed through systematic data fusion of European soil-environment observations, with the LUCAS survey as its backbone. The fused dataset comprises over 70,000 samples and more than 1,000 features spanning physical, chemical, environmental, biological, and visual attributes, aggregated from 68 source datasets. To enable integration at scale, we develop SoilFuser, a multi-agent, human-in-the-loop data fusion pipeline that standardizes heterogeneous data formats and measurement protocols, resolves inconsistencies and invalid entries (e.g., unit inconsistencies, codebook mismatches, and erroneous values), incorporates natural language annotations, and harmonizes multimodal attributes and metadata into a unified, machine learning-ready feature space. The resulting dataset captures key characteristics of real-world soil observations, including multimodality, uneven feature coverage, and heterogeneous uncertainty. To demonstrate the usability of LUCAS-MEGA for data-driven modeling, we pretrain a multimodal tabular transformer (SoilFormer) using a self-supervised objective based on feature masking, achieving stable training, strong predictive performance, and representations that support uncertainty-aware prediction. We further show that the learned representations recover relationships consistent with established soil processes. LUCAS-MEGA is released with open access and is accompanied by composable, agent-friendly APIs that support structured querying and data-driven workflows.
编码器(2篇)
【1】Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding
标题：考虑边缘比特覆盖的One-Hot编码初始训练数据设计改进FMQA
链接：https://arxiv.org/abs/2605.04825
摘要
：Factorization machine with quadratic-optimization annealing (FMQA) is a black-box optimization method that combines a factorization machine (FM) surrogate with QUBO-based search by an Ising machine. When FMQA is applied to integer or discretized continuous variables via one-hot encoding, uniform random initial sampling can leave many binary variables never active in the initial training data, and the corresponding FM parameters receive no direct gradient updates from the observed responses. We address this by designing the initial training data to achieve complete marginal bit coverage, namely, ensuring that every binary variable obtained by one-hot encoding takes the value one at least once. We use two space-filling sampling methods, Latin hypercube sampling (LHS) and the Sobol' sequence, yielding LHS-FMQA and Sobol'-FMQA. On the human-powered aircraft wing-shape optimization benchmark with 17 and 32 design variables, both proposed methods achieved numerically higher mean final cruising speeds than the baseline FMQA, with the advantage more pronounced on the 32-variable problem.
【2】Jordan-RoPE: Non-Semisimple Relative Positional Encoding via Complex Jordan Blocks
标题：Jordan-RoPE：通过复Jordan块的非半简单相对位置编码
链接：https://arxiv.org/abs/2605.04217
备注：15 pages, 4 figures, 6 tables; code available at https://github.com/ybzhang-nxu/jordan_rope
摘要：Relative positional encodings determine which functions of query-key lag can enter the primitive attention logit. RoPE supplies a rotary phase, while ALiBi supplies an additive distance bias. Motivated by group-theoretic views of linear translation-invariant positional encodings, we study a non-semisimple case in which a complex rotary eigenvalue and a nilpotent response live in the same defective Jordan block. The resulting relative operator generates oscillatory-polynomial features such as $e^{-γd}\cos(ωd)$, $e^{-γd}\sin(ωd)$, $d e^{-γd}\cos(ωd)$, and $d e^{-γd}\sin(ωd)$, for causal lag $d=i-j\geq 0$. Thus the construction realizes a distance-modulated phase basis $d e^{iωd}$, rather than merely adding a separate distance channel to RoPE. We formulate Exact Jordan-RoPE as a non-semisimple one-parameter representation, give its real block form, and specify the contragredient query action required by non-orthogonal positional maps. We also distinguish this exact representation from stabilized variants whose bounded shear improves numerical behavior but breaks the exact group law. Kernel-level diagnostics and a Jordan-friendly synthetic language-model task show that the coupled Jordan basis is useful when the target contains distance-modulated phase interactions. On a small WikiText-103 byte language model, a scaled-exact variant improves over RoPE and direct-sum baselines within the Jordan family, while RoPE+ALiBi remains strongest overall. The evidence is structural rather than a broad performance claim.
优化|敛散性(12篇)
【1】Reliable Modeling of Distribution Shifts via Displacement-Reshaped Optimal Transport
标题：通过位移重塑的最佳运输进行分配转移的可靠建模
链接：https://arxiv.org/abs/2605.04965
摘要：Optimal transport (OT) is a central framework for modeling distribution shifts. Because OT compares distributions directly in input space, a well-designed ground metric between observations is essential to ensure that the optimizer does not violate the true geometry of change. We propose Displacement-Reshaped Optimal Transport (ReshapeOT), a method that reshapes the ground metric by integrating observed sample displacements as an additional source of knowledge. Technically, ReshapeOT replaces the Euclidean metric with a Mahalanobis distance estimated from displacement second moments. This effectively carves expressways through the input space, inviting transport solutions that better align with observed displacements. Our method is computationally lightweight, integrates seamlessly into any OT solver that operates on a cost matrix, and can be kernelized for further flexibility. Experiments on synthetic and real-world data show that ReshapeOT achieves substantial gains in transport reliability. We further demonstrate our method's usefulness in two practical use cases.
【2】EP-GRPO: Entropy-Progress Aligned Group Relative Policy Optimization with Implicit Process Guidance
标题：EP-GRPO：具有隐性流程指导的、具有熵进步一致的集团相对政策优化
链接：https://arxiv.org/abs/2605.04960
备注：15 pages, 6 figures
摘要：Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO suffers from three credit assignment failures: uniform token-level granularity that ignores heterogeneous informational value, uniform polarity that penalizes correct steps and rewards incorrect ones, and zero-variance collapse that erases outcome-driven gradients. We systematically quantify these failures, revealing highly non-uniform token informativeness, widespread step-level polarity misalignment, and substantial training waste. To address these limitations, we propose Entropy-Progress Aligned GRPO (EP-GRPO), a framework that mines the model's intrinsic information flow for dense, self-supervised guidance. EP-GRPO integrates entropy-gated modulation to prioritize high entropy decision pivots, implicit process signals from policy divergence anchored to outcome advantages for directional token-level feedback without external reward models, and cumulative entropy mapping that enables progress-aligned advantage normalization, naturally maintaining gradient flow under zero reward variance. Extensive experiments on mathematical reasoning benchmarks demonstrate that EP-GRPO achieves superior accuracy and efficiency compared to GRPO and its variants. The code will be available.
【3】On the Influence of the Feature Computation Budget on Per-Instance Algorithm Selection for Black-Box Optimization
标题：特征计算预算对黑盒优化算法选择的影响
链接：https://arxiv.org/abs/2605.04954
摘要：Per-instance algorithm selection (PIAS) takes advantage of complementarity between a set of algorithms by deciding which algorithm to run on a given instance. This decision is based on features of the instances, which, in the context of black-box optimization (BBO), require a part of the optimization budget to be computed. This raises two questions: (a) from which fraction of the budget spent on feature computation does PIAS become worth it for BBO, and (b) which fraction of the budget optimizes the tradeoff between feature accuracy and PIAS performance. To this end, we perform a broad study where PIAS with varying sampling budgets for feature computation is compared to the single best algorithm on a broad range of algorithm selection scenarios. These scenarios consist of two portfolio sizes, three problem sets, 4 dimensionalities, and 10 target budgets. We find that PIAS is viable for the majority of tested scenarios, even when as much as a quarter of the total budget is spent on feature computation. The tradeoff for the fraction of the budget spent on feature computation to maximize the benefit of PIAS is highly dependent on the specific AS scenario. Further, on average 20 percent of PIAS loss to the virtual best solver is explained by the budget spent on feature computation, highlighting the importance of properly accounting for the feature budget.
【4】Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization
标题：多上下文Bayesian优化中的区域条件评估
链接：https://arxiv.org/abs/2605.04895
备注：42 pages, 9 figures. NeurIPS 2026 submission
摘要
：Published transfer-BO comparisons often estimate an average treatment effect of acquisition choice over hidden regime variables, while practitioners need the conditional effect for their specific prior quality, budget ratio, and metric. An audit of 40 transfer-BO papers from NeurIPS, ICML, ICLR, AISTATS, UAI, TMLR, JMLR, and AutoML-Conf (2022-2025) finds that 98% never vary B/|A| as a controlled axis. On the same GDSC2 benchmark, changing only the budget reverses the ranking: at B=50, Greedy outperforms UCB by 0.050 Hit@1, while at B=100, UCB outperforms Greedy by 0.035. We capture this transition with the Portable Regime Score PRS=(B/|A|)(1-rho), where rho is the prior rank correlation and can be estimated from pilot contexts before the main comparison. Across 79 conditions spanning chemistry, drug-response biology, and HPO, a hierarchical model gives beta=0.50 (p=1.1e-9), and 19% of conditions fall in an equivalence zone where |advantage|<0.01 Hit@1. In five published reversal cases, PRS predicts the winner from pre-comparison observables. A No-Free-Leaderboard proposition explains why unconditional rankings are unstable: when CATE changes sign across regimes, the reported ATE becomes a function of benchmark mixture. RegimePlanner, which estimates rho online and switches acquisition accordingly, wins all 16 HPO-B search spaces at B=100 and exceeds the matched {Greedy,UCB} per-context oracle on GDSC2 by 18%. Pre-registered predictions achieve 27/40=67.5% overall accuracy and above 90% within EMA prior families. The practical protocol is simple: report B/|A|, rho, K, and metric alongside any claimed acquisition advantage.
【5】Threshold-Guided Optimization for Visual Generative Models
标题：视觉生成模型的约束引导优化
链接：https://arxiv.org/abs/2605.04653
备注：Accepted to ICML 2026
摘要：Aligning large visual generative models with human feedback is often performed through pairwise preference optimization. While such approaches are conceptually simple, they fundamentally rely on annotated pairs, limiting scalability in settings where feedback is collected as independent scalar ratings. In this work, we revisit the KL-regularized alignment objective and show that the optimal policy implicitly compares each sample's reward to an instance-specific baseline that is generally intractable. We propose a threshold-guided alignment framework that replaces this oracle baseline with a data-driven global threshold estimated from empirical score statistics. This formulation turns alignment into a binary decision task on unpaired data, enabling effective optimization directly from scalar feedback. We also incorporate a confidence weighting term to emphasize samples whose scores deviate strongly from the threshold, improving sample efficiency. Experiments across both diffusion and masked generative paradigms, spanning three test sets and five reward models, show that our method consistently improves preference alignment over previous methods. These results position our threshold-guided framework as a simple yet principled alternative for aligning visual generative models without paired comparisons.
【6】Geometry-Aware Neural Optimizer for Shape Optimization and Inversion
标题：形状优化和倒置的几何感知神经优化器
链接：https://arxiv.org/abs/2605.04474
备注：To appear in ICML2026
摘要：Geometry is central to PDE-governed systems, motivating shape optimization and inversion. Classical pipelines conduct costly forward simulation with geometry processing, requiring substantial expert effort. Neural surrogates accelerate forward analysis but do not close the loop because gradients from objectives to geometry are often unavailable. Existing differentiable methods either rely on restrictive parameterizations or unstable latent optimization driven by scalar objectives, limiting interpretability and part-wise control. To address these challenges, we propose Geometry-Aware Neural Optimizer (GANO), an end-to-end differentiable framework that unifies geometry representation, field-level prediction, and automated optimization/inversion in a single latent-space loop. GANO encodes shapes with an auto-decoder and stabilizes latent updates via a denoising mechanism, and a geometry-injected surrogate provides a reliable gradient pathway for geometry updates. Moreover, GANO supports part-wise control through null-space projection and uses remeshing-free projection to accelerate geometry processing. We further prove that denoising induces an implicit Jacobian regularization that reduces decoder sensitivity, yielding controlled deformations. Experiments on three benchmarks spanning 2D Helmholtz, 2D airfoil, and 3D vehicles show state-of-the-art accuracy and stable, controllable updates, achieving up to +55.9% lift-to-drag improvement for airfoils and ~7% drag reduction for vehicles.
【7】Layerwise LQR for Geometry-Aware Optimization of Deep Networks
标题：分层LQR用于深度网络的几何感知优化
链接：https://arxiv.org/abs/2605.04230
摘要：Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners usually impose structural approximations early, often discarding cross-layer interactions induced by the network computation. We introduce Layerwise LQR (LLQR), a framework for learning structured inverse preconditioners under a global layerwise optimal-control objective. The starting point is an exact equivalence: the steepest-descent step under a broad class of divergence-induced quadratic models--including Newton, Gauss-Newton, Fisher/natural-gradient, and intermediate-layer metrics--can be written as a finite-horizon Linear Quadratic Regulator (LQR) problem. This formulation serves as a reference that exposes the layerwise dynamics and cost matrices encoding the original dense geometry. We then derive a scalable relaxation that learns diagonal, (E-)Kronecker-factored, or other structured inverse preconditioners by minimizing the LQR objective and reusing them across iterations. The resulting optimizer wraps standard methods while retaining a principled connection to second-order geometry, without forming or inverting the global curvature matrix. Experiments on ResNets and Transformers show that LLQR improves optimization dynamics and often translates these gains into improved final test performance, while adding only modest wall-clock overhead. It establishes LLQR as a practical framework for geometry-aware second-order methods and a reference for evaluating scalable approximations.
【8】A Provably Convergent and Practical Algorithm for Gromov--Wasserstein Optimal Transport
标题：Gromov的一种可证明收敛且实用的算法--Wasserstein最优运输
链接：https://arxiv.org/abs/2605.04175
备注：21 Pages, 6 figures
摘要：Gromov--Wasserstein optimal transport (GWOT) aligns metric measure spaces by matching their within-domain relational structures, but large-scale GWOT remains challenging because its objective is nonconvex and projection onto the transport polytope is often solved only approximately in practice. This leads to a gap between practical projected-gradient implementations and convergence theory, which typically assumes exact projections. For squared-loss GWOT, we propose an inexact projected-gradient framework with a verifiable feasibility-residual-based inexact condition for the projection subproblem. This condition is directly computable and avoids unknown quantities such as the exact projection point. Under this implementable condition, we prove subsequential convergence to stationary points and, with a mild tolerance-decay condition, convergence of the whole sequence. The resulting method retains the simplicity and sparsity of projected-gradient schemes while providing rigorous convergence guarantees, turning projected-gradient methods into a principled and scalable approach for GWOT with provable reliability.
【9】Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
标题：适应或忘记：非平稳优化中Adam和Singapore之间的可证明权衡
链接：https://arxiv.org/abs/2605.04269
备注：39 pages, 11 figures, 1 table
摘要：We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-preconditioned mean-gradient operator, and high-probability projected stationarity guarantees under general $L$-smooth objectives. In the tracking regime, we derive finite-time expected and high-probability bounds that decompose sharply into four components: initialization, objective drift, a first-moment tracking error governed by $β_1$, and a preconditioner perturbation governed by $β_2$. We characterize the burn-in time to reach Adam's irreducible tracking floor under constant and step-decay schedules. We also prove a high-probability bound on the average projected stationarity gap for Adam under distribution shift. Across both analyses, our bounds reveal a noise--drift tradeoff: in noise-dominated regimes, first-moment averaging and adaptive preconditioning can improve the high-probability error, whereas in drift-dominated regimes, stale first-moment information and preconditioner perturbations can compound the cost of nonstationarity, allowing vanilla SGD to achieve a smaller tracking floor. Our explicit $(β_1,β_2,ε)$-dependent bounds delineate when adaptive step-sizing is beneficial versus harmful, and provide a theoretical mechanism for Adam's empirical instability and stabilization under distribution shift.
【10】Entropic Riemannian Neural Optimal Transport
标题：熵Riemann神经最优传输
链接：https://arxiv.org/abs/2605.04255
摘要：Many machine learning problems involve data supported on curved spaces such as spheres, rotation groups, hyperbolic spaces, and general Riemannian manifolds, where Euclidean geometry can distort distances, averages, and the resulting optimal transport (OT) problem. Existing manifold OT methods have pursued amortized out-of-sample maps, while entropic regularization has made discrete OT more scalable, but these advantages have remained largely disjoint. We propose Entropic Riemannian Neural Optimal Transport (Entropic RNOT), a unified framework that combines intrinsic entropic OT with amortized out-of-sample evaluation on Riemannian manifolds. Our method learns a single target-side Schrödinger potential through a neural pullback parameterization, recovers the induced Gibbs coupling, and uses the resulting conditional laws to construct intrinsic transport surrogates. These include barycentric projections on Cartan-Hadamard manifolds and heat-smoothed conditional surrogates on stochastically complete manifolds, the latter turning possibly atomic target laws into absolutely continuous ones. For fixed regularization $\varepsilon>0$, we prove that the proposed hypothesis class recovers the entropic optimal coupling in strong probabilistic metrics. As consequences, barycentric surrogates converge in $L^2$, while heat-smoothed surrogates are stable at fixed heat time and asymptotically unbiased as the heat time vanishes. The guarantees hold for compactly supported data on possibly noncompact manifolds. Empirically, our method matches or improves over Euclidean, tangent-space, and log-Euclidean baselines on benchmarks over $\mathbb{S}^2$, $\mathrm{SO}(3)$, $\mathrm{SPD}(3)$, $\mathrm{SE}(3)$, and $\mathbb{H}^2$, scales favorably relative to discrete manifold Sinkhorn, and in a protein-ligand docking application, refines poses on $\mathrm{SE}(3)$ without retraining or per-instance optimization.
【11】Globally Solving Unbalanced Optimal Transport and Density Control for Gaussian Distributions
标题：全局求解高斯分布的不平衡最优输运和密度控制
链接：https://arxiv.org/abs/2605.04246
备注：28 pages; submitted to a journal
摘要：In this article, we study unbalanced optimal transport (UOT) and establish a control-theoretic dynamical extension, which we call the unbalanced density control (UDC), for a class of Gaussian reference measures. In the static setting, we consider UOT with quadratic transport cost and Kullback--Leibler penalties on the marginals relative to prescribed Gaussian measures. We show that the infinite-dimensional variational problem admits an exact Gaussian reduction, yielding a finite-dimensional optimization over masses, means, and covariances, together with a closed-form expression for the optimal transported mass. We then formulate UDC for discrete-time linear systems, where the initial and terminal state measures are imposed softly through KL penalties and the intermediate evolution is governed by controlled linear dynamics with quadratic control cost. For this problem, we prove that any feasible solution can be replaced, without loss of optimality, by a Gaussian initial measure and an affine-Gaussian control policy. This leads to an exact finite-dimensional reformulation and, after a standard covariance-steering lifting, to an SDP-based optimization for fixed mass, again coupled with a closed-form mass update. We further establish existence of optimal solutions and identify a sufficient condition under which the affine-Gaussian UDC policy is deterministic. These results provide globally optimal solution methods for both Gaussian UOT and Gaussian UDC. Finally, we illustrate our results with several numerical examples.
【12】A Consistency-Centric Approach to Set-Based Optimization with Multiple Models of Unranked Fidelity
标题：基于一致性中心的多模型集合优化方法
链接：https://arxiv.org/abs/2605.04051
备注：26 pages, 6 figures
摘要：In complex real-world settings, optimization is challenged by the presence of diverse models of differing fidelity. In many optimization problems, a single model is treated as the most accurate representation of the underlying system, while other models are evaluated primarily by their agreement with this presumed most accurate model. Yet in real-world applications, model accuracy is rarely known a priori and assuming a single most accurate model can be misleading. This paper addresses this gap by proposing a flexible set-based optimization methodology called Set-Based Optimization with Multiple Models (S-BOMM) that works with multiple models without the assumption of a most accurate high-fidelity model. Unlike traditional optimization approaches that focus on finding an optimal solution according to the high-fidelity model, our methodology utilizes consistency between models to identify good solutions across multiple models. A probabilistic analysis of the consistency method is provided that bounds the likelihood of the methodology producing correct or incorrect results. Empirical results demonstrate the effectiveness of S-BOMM on test problems. By focusing on the consistency across models rather than relying on a single best solution, this set-based approach offers a practical alternative to optimization problems where multiple models must be considered without assuming a single most accurate high-fidelity model.
预测|估计(10篇)
【1】Human-AI Co-Mentorship in Project-Based Learning: A Case Study in Financial Forecasting
标题：基于项目的学习中的人机联合导师：财务预测领域的案例研究
链接：https://arxiv.org/abs/2605.05144
备注：Accepted for publication in 2026 ASEE Annual Conference & Exposition
摘要
：This paper reflects on a AI research project carried out by a team of high-school and early-undergraduate students under the mentorship of graduate researchers and ably assisted by AI tools. We share our experience in not only on the learning experience for the high school students, but also on how AI tools accelerated the process that enabled the high school students to focus on higher order problem formulation and solution. Although the participants entered the project with limited background in both AI and finance, they showed strong enthusiasm for technical market analysis and ETF price prediction. Traditional learning settings would first teach the necessary methods in a classroom setting and only later let students apply them. In contrast, our project emphasized workflow design: students identified the sequence of steps needed to address the problem and then used AI-driven tools to execute each step. We note that the high school students developed the necessary code through iterating with the AI tools, and we used our daily stand-ups to debug and answer conceptual questions. Each of the student was able to dig deeper into their area of interest whether computer science or finance, while collaboratively making a significant advance over the summer of 2025. This project was an important pedagogical exercise on how AI tools can be used for mentoring high school students, allowing them to focus on their specific interests and using the daily stand-ups to focus on problem definition and conceptual understanding. Despite their limited technical qualifications, the students were able to leverage AI tools to build meaningful models with real-world application.
【2】The Predictive-Causal Gap: An Impossibility Theorem and Large-Scale Neural Evidence
标题：预测因果差距：不可能性定理和大规模神经证据
链接：https://arxiv.org/abs/2605.05029
备注：15 pages, 5 figures, 3 tables. Supplemental Material included (Sections S1-S10)
摘要：We report a systematic failure mode in predictive representation learning. Across 2695 neural network configurations trained to predict linear-Gaussian dynamics, the optimal encoder tracks the environment rather than the system it is meant to model. The mean causal fidelity -- the fraction of encoder sensitivity allocated to system degrees of freedom -- is 0.49, and only 2.5% of configurations exceed 0.70. The failure intensifies with dimension: at N=100, the optimal encoder becomes causally blind (fidelity ~10^{-8}) while achieving 92% lower prediction error than the causal representation. We prove this is not an optimization artifact but a structural property of the predictive objective: when environment modes are slower or less noisy than system modes, every minimizer of the population risk encodes the former. The set of dynamics exhibiting this predictive-causal gap is open and of positive measure in parameter space. In a nonlinear Duffing-GRU sweep, unconstrained predictors learn environment-dominant representations in 55% of tasks (95% CI 41--68%) versus 24% under operational grounding (p=2.3e-3); the median out-of-distribution MSE inflation under environment shift is 1.82x versus 1.00x. Operational grounding -- restricting the loss to system observables -- partially suppresses the gap, but causal fidelity is never recovered without an explicit system-environment boundary. The results identify the predictive-causal gap as a structural limit of learning, with implications for self-supervised representation learning, world models, and the scaling paradigm.
【3】A Biased Nonnegative Block Term Tensor Decomposition Model for Dynamic QoS Prediction
标题：一种用于动态服务质量预测的有偏非负块项张量分解模型
链接：https://arxiv.org/abs/2605.04813
摘要：With the rapid development of cloud computing and Web services, Quality of Service (QoS) has become a key criterion for service selection and recommendation. Tensor latent feature analysis provides an effective way to model multidimensional QoS data, and most existing QoS prediction methods are mainly based on Canonical Polyadic (CP) decomposition or Tucker decomposition. However, constrained by their inherent structural properties, these methods cannot accurately capture the complex and dynamic dependencies in user-service interactions, which limits their prediction performance. To address this issue, this paper proposes a dynamic QoS prediction framework based on the Biased Nonnegative Block Term Tensor Decomposition Model, termed BNBT. Specifically, the proposed framework is developed from three aspects: (1) block term tensor decomposition is employed to enhance the representation capability of latent feature learning; (2) linear bias terms are incorporated to further improve prediction accuracy; and (3) a tensor-oriented single-element-dependent nonnegative multiplicative update algorithm, called SLF-NMUT, is designed for efficient parameter estimation. Extensive experiments on real-world QoS datasets demonstrate that the proposed BNBT framework consistently outperforms several state-of-the-art QoS prediction methods in terms of prediction accuracy.
【4】MixINN: Accelerating Plant Breeding by Combining Mixed Models and Deep Learning for Interaction Prediction
标题：MixINN：通过结合混合模型和深度学习进行相互作用预测来加速植物育种
链接：https://arxiv.org/abs/2605.04744
备注：11 pages, 1 figure
摘要：Plant breeding underpins global food security through incremental, accumulating improvements in crop yield, quality and sustainability, achieved via repeated cycles of crop ranking, selection and crossing. Climate change disrupts this process by altering local growing conditions, thereby shifting the relative performance of crop genotypes. Predicting these relative changes in yield is critical for food security. Yet, this problem remains an open challenge in plant breeding, and relatively unexplored within the AI community. We propose MixINN, an approach that first isolates high-quality genotype-environment interaction labels using mixed models, and then predicts these interactions for new crop varieties in future environmental conditions with a deep neural network. We evaluate our method on a corn multi-environment trial across the continental United States and show improved prediction of genotype ranking over current plant breeding methods. MixINN demonstrated superior performance in identifying the 20% most productive corn genotypes, leading to a 5.8% higher average yield, which further improved to 7.2% when targeting specific growing environments. These are competitive results for real-world breeding programs, demonstrating the potential of AI research in accelerating the development of climate-adapted crops, and improving future food security under climate change.
【5】Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination
标题：Dream-MPC：具有潜在想象力的基于对象的模型预测控制
链接：https://arxiv.org/abs/2605.04568
摘要
：State-of-the-art model-based Reinforcement Learning (RL) approaches either use gradient-free, population-based methods for planning, learned policy networks, or a combination of policy networks and planning. Hybrid approaches that combine Model Predictive Control (MPC) with a learned model and a policy prior to leverage the advantages of both paradigms have shown promising results. However, these approaches typically rely on gradient-free optimization methods, which can be computationally expensive for high-dimensional control tasks. While gradient-based methods are a promising alternative, recent works have empirically shown that gradient-based methods often perform worse than their gradient-free counterparts. We propose Dream-MPC, a novel approach that generates few candidate trajectories from a rolled-out policy and optimizes each trajectory by gradient ascent using a learned world model, uncertainty regularization and amortization of optimization iterations over time by reusing previously optimized actions. Our results on 24 continuous control tasks show that Dream-MPC can significantly improve the performance of the underlying policy and can outperform gradient-free MPC and state-of-the-art baselines. We will open source our code and more at https://dream-mpc.github.io.
【6】Online Nonstochastic Prediction: Logarithmic Regret via Predictive Online Least Squares
标题：在线非随机预测：通过预测在线最小平方的对数遗憾
链接：https://arxiv.org/abs/2605.04364
摘要：We study online prediction for marginally stable, partially observed linear dynamical systems under nonstochastic disturbances. Our objective is to minimize the cumulative squared prediction loss and compete with the best-in-hindsight Luenberger predictor. Standard online learning methods typically rely on bounded domains/gradients, and thus their guarantees may fail to deal with potentially unbounded trajectories in marginally stable systems. In this paper, we introduce an unconstrained online least squares method that stabilizes the learning process via tailored predictive hints. With model knowledge, we prove that hints constructed from any stabilizing Luenberger predictor render the hint residuals uniformly bounded, achieving logarithmic regret despite unbounded trajectory growth. We also discuss model-free prediction and introduce a simple universal hint for symmetric systems, under which logarithmic regret is maintained without model knowledge. Our results provide an adaptive, instance-wise optimal online predictor compared to classical fixed-gain observers under nonstochastic disturbances.
【7】Imagery Dataset for Remaining Useful Life Estimation of Synthetic Fibre Ropes
标题：合成纤维绳索剩余使用寿命估计的图像数据集
链接：https://arxiv.org/abs/2605.04262
备注：7 pages, 2 figures, 1 table
摘要：Remaining useful life (RUL) estimation of synthetic fibre ropes (SFRs) is critical for safe operation in offshore-crane, wind turbine installation, and heavy-load handling applications, where rope failure can result in catastrophic safety incidents and costly downtime. Despite growing research interest in data-driven condition monitoring, there is no publicly available image dataset that captures the complete degradation lifecycle of SFRs under controlled cyclic fatigue loading. To address this gap, we present a novel image dataset comprising approximately 34,700 high-resolution images of eleven Dyneema SK75/78 high-modulus polyethylene (HMPE) rope samples subjected to cyclic fatigue on a sheave-bend test stand at seven distinct axial load levels ranging from 60 kN to 280 kN. Ropes were loaded until mechanical failure, with fatigue lifetimes ranging from 695 cycles to 8,340 cycles. After every fixed number of sheave cycles (an inspection burst), ten images were captured at different cross-sectional positions along the rope, providing spatially representative sampling of surface degradation throughout the rope's entire service life. The images obtained from each load are annotated with the corresponding elapsed cycle count, enabling a direct computation of RUL for any rope in the sequence. This dataset aims to support a broad range of machine learning (ML) tasks including RUL regression, damage progression modelling, anomaly detection, and load-conditioned prognostics. The dataset is intended to serve as a benchmark resource for the development and comparison of vision-based condition monitoring (CM) and prognostics algorithms for SFRs.
【8】Road Risk Monitor: A Deployable U.S. Road Incident Forecasting System with Live Weather and Road-Level Tiles
标题：道路风险监测：一个可部署的美国道路事故预测系统，具有实时天气和道路水平瓷砖
链接：https://arxiv.org/abs/2605.04242
摘要：Nationwide road-incident forecasting is a systems problem before it is a modeling problem. A usable service must connect historical incident archives, historicalandliveweather,nationalroadgeometry, offline model training, tile generation, web serving and runtime handoff. This paper presents Road Risk Monitor, a U.S.-wide road-safety stack that combines a nationwide H3 baseline trained on FARS fatal-crash data with a road-segment forecasting pipeline trained from TIGER/Line geometry and US-Accidents events, then serves predictions through live APIs, raster tiles, JSON road tiles, and a public web application.
【9】A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers
标题：用于人工智能数据中心短期图形处理器功耗预测的物理感知框架
链接：https://arxiv.org/abs/2605.04074
摘要：AI data centers experience rapid fluctuations in power demand due to the heterogeneity of computational tasks that they have to support. For example, the power profile of inference and training of large language models (LLMs) is quite distinct and big divergences can result in the instability of the underlying electricity grid. In this paper we propose, to the best of our knowledge, the first physics-informed DLinear time-series model that can accurately forecast power utilization of an AI data center 5-80 minutes (short-term forecasting) into the future. The physics, based on a multi-node lumped thermal resistance-capacitance (RC) network consistent with Newton's law of cooling, is captured using newly derived time-dependent ordinary differential equations (ODE) that separately models and interlinks power consumption with the GPU compute and memory utilization and temperature. The resulting model, that we refer to as PI-DLinear, trained and evaluated on a real AI data center dataset and is not only more accurate than the state-of-the-art (SOTA) models tested, but the forecast profile respects the underlying physics under power throttling and load transient events. Relative to the SOTA transformer-based and non-transformer-based models, improvements in forecasting accuracy (averaged across all look-back and prediction windows) range from 0.782%-39.08% for MSE, 0.993%-51.82% for MAE, and 0.370%-22.28% for RMSE.
【10】Predictive and Prescriptive AI toward Optimizing Wildfire Suppression
标题：优化野火抑制的预测性和规定性人工智能
链接：https://arxiv.org/abs/2605.04510
摘要
：Intense wildfire seasons require critical prioritization decisions to allocate scarce suppression resources over a dispersed geographical area. This paper develops a predictive and prescriptive approach to jointly optimize crew assignments and wildfire suppression. The problem features a discrete resource-allocation structure with endogenous wildfire demand and non-linear wildfire dynamics. We formulate an integer optimization model with crew assignments on a time-space-rest network, wildfire dynamics on a time-state network, and linking constraints between them. We develop a two-sided branch-and-price-and-cut algorithm based on: (i) a two-sided column generation scheme that generates fire suppression plans and crew routes iteratively; (ii) a new family of cuts exploiting the knapsack structure of the linking constraints; and (iii) novel branching rules to accommodate non-linear wildfire dynamics. We also propose a data-driven double machine learning approach to estimate wildfire spread as a function of covariate information and suppression efforts, mitigating observed confounding between historical crew assignments and wildfire growth. Extensive computational experiments show that the optimization algorithm scales to otherwise intractable real-world instances; and that the methodology can enhance suppression effectiveness in practice, resulting in significant reductions in area burned over a wildfire season and guiding resource sharing across wildfire jurisdictions.
其他神经网络|深度学习|模型|建模(45篇)
【1】On the Wasserstein Gradient Flow Interpretation of Drifting Models
标题：漂移模型的Wasserstein梯度流解释
链接：https://arxiv.org/abs/2605.05118
摘要：Recently, Deng et al. (2026) proposed Generative Modeling via Drifting (GMD), a novel framework for generative tasks. This note presents an analysis of GMD through the lens of Wasserstein Gradient Flows (WGF), i.e., the path of steepest descent for a functional in the space of probability measures, equipped with the geometry of optimal transport. Unlike previous WGF-based contributions, GMD can be thought of as directly targeting a fixed point of a specific WGF flow. We demonstrate three main results: first, that one algorithm proposed by Deng et al. (2026) corresponds to finding the limiting point of a WGF on the KL divergence, with Parzen smoothing on the densities. Second, that the algorithm actually implemented by Deng et al. (2026) corresponds to a different procedure, which bears some resemblance to the fixed point of a WGF on the Sinkhorn divergence, but lacks certain desirable properties of the latter. Third, the same same idea can be extended to the limiting point of other WGFs, including the Maximum Mean Discrepancy (MMD), the sliced Wasserstein distance, and GAN critic functions.
【2】Provable imitation learning for control of instability in partially-observed Vlasov--Poisson equations
标题：部分观察Vlasov-Poisson方程不稳定性控制的可证明模仿学习
链接：https://arxiv.org/abs/2605.05081
摘要：We consider the stabilization of Vlasov--Poisson plasma dynamics, a central control problem in nuclear fusion. Our focus is the gap between what an ideal controller would use and what experiments can actually observe: while optimal policy may rely on the full phase-space state, practical feedback is typically limited to sparse macroscopic diagnostics. We therefore study imitation learning methods that distill a fully observed expert policy into controllers operating only on macroscopic measurements. We show the stability guarantees of the learned policy, where the error floor depends on the minimal behavior cloning loss achievable under the observation constraints. We further characterize this minimal loss in terms of a notion of entropy that quantifies the complexity of the initial distribution. Our results demonstrates the theoretical feasibility of learning stabilizing feedback policies for kinetic plasma dynamics from macroscopic observations, and exhibits the adaptivity of the learning approach to low-complexity structures. Through extensive numerical experiments, we validate our theory and show that the learned policies can stabilize the system using only macroscopic observations, within a significantly longer time horizon than non-adaptive baseline controllers.
【3】The Impossibility Triangle of Long-Context Modeling
标题：长上下文建模的不可能三角
链接：https://arxiv.org/abs/2605.05066
备注：41 pages, 6 figures
摘要：We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent of sequence length (Efficiency), (ii) state size independent of sequence length (Compactness), and (iii) the ability to recall a number of historical facts proportional to sequence length (Recall). We formalize this trade-off within an Online Sequence Processor abstraction that unifies Transformers, state space models, linear recurrent networks, and their hybrids. Using the Data Processing Inequality and Fano's Inequality, we prove that any model satisfying Efficiency and Compactness can recall at most O(poly(d)/log V) key-value pairs from a sequence of arbitrary length, where d is the model dimension and V is the vocabulary size. We classify 52 architectures published before March 2026 into the triangle, showing that each achieves at most two of the three properties and that hybrid architectures trace continuous trajectories in the interior. Experiments on synthetic associative recall tasks with five representative architectures validate the theoretical bound: empirical recall capacity lies strictly below the information-theoretic limit, and no architecture escapes the triangle.
【4】Full-chip CMP modelling based on Fully Convolutional Network leveraging White Light Interferometry
标题：基于完全卷积网络的全芯片化学机械抛光建模，利用白色干涉术
链接：https://arxiv.org/abs/2605.05062
备注：Presented at the International Conference on Planarization Technology 2025 in Hong Kong
摘要：As time-to-market is crucial in the Integrated Circuit (IC) industry, speeding up layout manufacturability verifi-cation is essential. Chemical-Mechanical Polishing (CMP) plays a vital role in IC fabrication but is significantly influenced by Layout-Dependent Effects (LDE). An accurate and efficient CMP model enables design teams to correct surface unevenness before fabrication, reducing costs and accelerating the design phase. However, existing models often rely on Density Step Height (DSH) modeling, which is time-consuming for calibration and requires substantial hardware resources for fine-grained predictions. In this paper, we propose combining the advantages of two surface analysis techniques, White Light Interfer-ometry (WLI) and Atomic Force Microscopy (AFM), to train a deep learning model. This model aims to predict full-chip post-CMP nanotopography with nanometer-scale accuracy. Our deep learning model is based on a Convolutional Neural Network (CNN) and follows a two-step pipeline. The model is trained on each technique separately, resulting in a detailed full-chip CMP model.
【5】Piper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism
标题：Piper：通过资源建模和流水线混合并行主义进行高效大规模MoE训练
链接：https://arxiv.org/abs/2605.05049
摘要
：Frontier models increasingly adopt Mixture-of-Experts (MoE) architectures to achieve large-model performance at reduced cost. However, training MoE models on HPC platforms is hindered by large memory footprints, frequent large-scale communication across heterogeneous networks, and severe workload imbalance. To characterize these challenges, we develop a mathematical model that quantifies memory, compute, and communication requirements for MoE configurations under various parallelization schemes, verified through micro-benchmarking, code instrumentation, and hardware profiling. Our analysis identifies performance bottlenecks: all-to-all latency at scale from expert parallelism, insufficient compute-communication overlap, low GPU utilization from imbalanced skinny GEMMs, and the absence of platform-aware hybrid parallelization strategies. To address these, we introduce Piper, a framework that leverages resource modeling to identify efficient training strategies for MoE models on target HPC platforms, applying pipeline parallelism with optimized schedules. Piper achieves 2-3.5X higher MFU than state-of-the-art frameworks such as X-MoE, and a novel all-to-all algorithm delivers 1.2-9X bandwidth over vendor implementation.
【6】Learned Neighbor Trust for Collaborative Deployment in Model-Agnostic Decentralized Learning
标题：模型无关分散学习中协作部署的学习邻居信任
链接：https://arxiv.org/abs/2605.05009
摘要：Many decentralized distillation methods are designed around training-time coordination, yet deploy each node in isolation even when more capable neighbors remain available at inference time. This is an incomplete objective for settings such as IoT, where devices are heterogeneous, data is scarce and skewed, and a node's strongest neighbors may far exceed its own local capacity. We study how nodes should train so that their predictions compose well at deployment, and how each node should learn whom to trust. Under a server-free, model-agnostic protocol where nodes exchange only queries and soft predictions, we propose Learned Neighbor Trust (LNTrust) wherein each node learns a compact trust function over its neighborhood from local validation evidence. This trust function gates auxiliary distillation during training and defines a deployment ensemble at inference, so that collaboration learned during training transfers directly to deployment. Across datasets and topologies, LNTrust improves deployed accuracy over the strongest output-only baseline by large margins while using significantly less communication than previous methods.
【7】DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion
标题：DualTCN：一个用于2个时间域海洋CTEM倒置的物理约束时态卷积网络
链接：https://arxiv.org/abs/2605.04997
摘要：DualTCN is the first deep-learning framework for inverting time-domain marine controlled-source electromagnetic (MCSEM) transient data. Moving away from traditional subsurface discretization, the framework regresses four earth-model parameters -- $σ_1$, $σ_2$, $d_1$, $d_2$ -- and reconstructs conductivity-depth profiles using a differentiable soft-step decoder. The optimized architecture (379K parameters) features a Temporal Convolutional Network (TCN) encoder paired with a late-time branch and an auxiliary seafloor-depth head. This design achieves a 25.3\% loss reduction over baseline models, with high predictive accuracy ($R^2 = 0.898$ for $σ_2$) and an inversion speed of 3.5~ms per sample on an A100 GPU. The framework demonstrates high robustness to noise through curriculum-based amplitude augmentation, maintaining a mean $\bar{R}^2$ of 0.858 at $\pm2\%$ random amplitude error, compared to $0.363$ without augmentation. DualTCN generalizes effectively to three-layer extensions (seawater/resistive layer/basement), accurately resolving basement conductivity ($R^2 \approx 0.88$), though thin-layer resolution remains a physical limitation ($R^2 \approx 0.23$). In comparative benchmarks, DualTCN significantly outperforms traditional local optimization methods like Levenberg-Marquardt and L-BFGS-B, yielding a mean $\bar{R}^2 = 0.877$ versus 0.129-0.439 for multi-start baselines, while operating at up to 21,000$\times$ lower computational cost. Finally, the framework incorporates uncertainty quantification via Monte Carlo (MC) Dropout. While well-calibrated for $σ_1$ (PICP90 = 0.944), inherent signal limitations at short offsets (200m) lead to under-coverage for $d_2$ (PICP90 = 0.572), which can be mitigated through post-hoc temperature scaling or split conformal prediction.
【8】Adaptivity Under Realizability Constraints: Comparing In-Context and Agentic Learning
标题：可实现性约束下的适应性：比较上下文和抽象学习
链接：https://arxiv.org/abs/2605.04995
摘要：We compare in-context learning with fixed queries and agentic learning with adaptive queries for uniform approximation of task families. We consider two settings: an unrestricted regime, where querying and approximation are arbitrary functions, and a realizable regime, where we require these operations to be implemented by ReLU neural networks. In both settings, adaptivity never hinders approximation performance. However, this advantage can change when one passes from the unrestricted regime to the realizable regime. We identify four distinct approximation scenarios, each witnessed by an explicit task family: (a) no advantage of adaptivity; (b) an advantage in the unrestricted regime that persists under ReLU realizability; (c) an advantage that arises only under realizability; and (d) an advantage that disappears under realizability. This demonstrates that representational constraints interact profoundly with the effect of adaptivity.
【9】On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
标题：将政策视为强盗武器，进行树型MDPs在线学习
链接：https://arxiv.org/abs/2605.04979
备注：Accepted as a full paper in the Main Track of AAMAS 2026
摘要：A Tree Markov Decision Problem (T-MDP) is a finite-horizon MDP with a starting state $s_{1}$, in which every state is reachable from $s_{1}$ through exactly one state-action trajectory. T-MDPs arise naturally as abstractions of decision making in sequential games with perfect recall, against stationary opponents. We consider the problem of on-line learning in T-MDPs, both in the PAC and the regret-minimisation regimes. We show that well-known bandit algorithms -- \textsc{Lucb} and \textsc{Ucb} -- can be applied on T-MDPs by treating each policy as an arm. The apparent technical challenge in this approach is that the number of policies is exponential in the number of states. Our main innovation is in the design of confidence bounds based on data shared by the policies, so that the bandit algorithms can yet be implemented with polynomial memory and per-step computation. We obtain instance-dependent upper bounds on sample complexity and regret that sum a ``gap term'' from every terminal state, rather than every policy. Empirically, our algorithms consistently outperform available alternatives on a suite of hidden-information games.
【10】Why Geometric Continuity Emerges in Deep Neural Networks: Residual Connections and Rotational Symmetry Breaking
标题：为什么深度神经网络中出现几何连续性：残余连接和旋转对称性破缺
链接：https://arxiv.org/abs/2605.04971
备注：9 pages of main text, plus appendices. Under review at NeurIPS 2026
摘要
：Weight matrices in deep networks exhibit geometric continuity -- principal singular vectors of adjacent layers point in similar directions. While this property has been widely observed, its origin remains unexplained. Through experiments on toy MLPs and small transformers, we identify two mechanisms: residual connections create cross-layer gradient coherence that aligns weight updates across layers, and symmetry-breaking nonlinearities constrain all layers to a shared coordinate frame, preventing the rotation drift that would otherwise destabilize weight structure. Crucially, a nonlinear but rotation-preserving activation fails to retain continuity, isolating symmetry breaking -- not nonlinearity itself -- as the active ingredient. Activation and normalization play distinct roles: activation concentrates continuity in the leading singular direction, while normalization distributes it across multiple directions. In transformers, continuity is projection-specific: Q, K, Gate, and Up (which read from the residual stream) develop input-space ($\mathbf{v}_1$) continuity; O and Down (which write to it) develop output-space ($\mathbf{u}_1$) continuity; V alone, lacking an adjacent nonlinearity, develops only low continuity.
【11】Skill Neologisms: Towards Skill-based Continual Learning
标题：技能新词：迈向基于技能的持续学习
链接：https://arxiv.org/abs/2605.04970
摘要：Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to new skills in a scalable manner is an open-problem: fine-tuning and parameter-efficient variants risk catastrophic forgetting, while context-based approaches have limited expressiveness and are constrained by the model's effective context. We explore skill neologisms--i.e., soft tokens integrated in the model's vocabulary and optimized to improve capabilities over a specific skill--as a way to selectively extend model capabilities to new skills without weight updates. We first observe that off-the-shelf pre-trained LLMs already demonstrate tokens associated with procedural knowledge. We then show that skill neologisms can be learned to improve model capabilities on specific skills while being composable with out-of-distribution skills, and that independently trained skill neologisms can be composed zero-shot. These results suggest that skill neologisms may provide a scalable path towards skill-based continual learning.
【12】Order-based Rehearsal Learning
标题：基于命令的排练学习
链接：https://arxiv.org/abs/2605.04955
摘要：When a machine learning (ML) model forecasts an undesired event, one often seeks a decision to avoid it, known as the avoiding undesired future (AUF) problem. Many rehearsal learning methods have been proposed for AUF, but they rely on an underlying graph structure; learning such a graph from observational data is challenging and can incur substantial estimation error. In this work, we demonstrate that the order structure can be sufficient for AUF decision-making, and propose the first order-based rehearsal learning method. Although an order is less informative than a graph, it can be sufficient to identify the influence of decisions from observational data, suggesting that learning the entire graph is not always necessary. To learn the order, we develop an information-theoretic method that imposes no restrictions on the form of structural functions or the type of noise distributions. For AUF decision-making, we construct an order-based sampler to approximate the influence of decisions and, combined with a surrogate objective for maximizing the post-decision success probability, reduce the AUF task to a differentiable optimization problem. Experiments show that our order learning method outperforms existing methods, and that our AUF approach not only surpasses methods relying on learned graphs or learned orders, but also matches or even exceeds oracle baselines that are given the true graph.
【13】Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks
标题：训练时批量正规化重塑逐段仿射网络中的局部分区几何
链接：https://arxiv.org/abs/2605.04946
摘要：Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (CPA) networks through the geometry of switching hyperplanes and the induced affine-region partition. Conditioned on a mini-batch, we show that BN defines for each neuron a reference hyperplane through the batch centroid, and that breakpoint-switching hyperplanes are parallel translates whose offsets are expressed in batch-standardized coordinates and are independent of the raw bias. This yields an exact criterion for when a switching hyperplane intersects a local $\ell_\infty$ window and motivates a local region-density functional based on exact affine-region counts. Under explicit sufficient conditions, we show that BN increases expected local partition refinement in ReLU and more general piecewise-affine networks, and that this mechanism transfers locally through depth inside parent affine regions where the upstream representation map is an affine embedding. These results provide a function-level geometric account of training-time BN as a batch-conditional recentering mechanism near the data.
【14】Cross-Model Consistency of Feature Importance in Electrospinning: Separating Robust from Model-Dependent Features
标题：静电纺中特征重要性的跨模型一致性：将稳健性与模型相关特征分离
链接：https://arxiv.org/abs/2605.04905
摘要：Electrospinning is a highly sensitive fabrication process in which small variations in operating parameters can significantly influence fiber morphology and material performance. Machine learning (ML) methods are increasingly employed to model these process-structure relationships and to identify the relative importance of processing variables. However, most existing studies rely on a single ML model, implicitly assuming that the resulting feature importance is robust and reproducible. In this study, the consistency of feature importance across multiple ML model families was systematically evaluated using a curated dataset of 96 polyvinyl alcohol (PVA) electrospinning experiments. Twenty-one ML models representing linear, tree-based, kernel-based, neural network, and instance-based approaches were trained and compared. To provide a unified interpretability framework, SHAP (SHapley Additive exPlanations) values were used to calculate feature importance consistently across all models. A rank-based statistical analysis was then performed to quantify inter-model agreement and assess the robustness of parameter rankings. The results demonstrate that predictive performance and interpretive reliability are fundamentally distinct properties. Although several models achieved comparable predictive accuracy, substantial differences were observed in their feature importance rankings. Solution concentration emerged as the most robust and consistently influential parameter (variability = 0), whereas flow rate and applied voltage exhibited high ranking variability (variability > 0.9), indicating strong model dependence. These findings suggest that feature importance derived from a single ML model may be unreliable, particularly for small experimental datasets, and highlight the importance of cross-model validation for achieving trustworthy interpretation in ML-assisted electrospinning research.
【15】Replay-Based Continual Learning for Physics-Informed Neural Operators
标题：基于回放的基于物理知识的神经操作员的连续学习
链接：https://arxiv.org/abs/2605.04832
摘要
：Neural operators generally demonstrate strong predictive performance on in-distribution (ID) problems. However, a critical limitation of existing methods is their significant performance degradation when encountering out-of-distribution (OOD) data. To address this issue, this work introduces continual learning into physics-informed neural operators, with particular emphasis on neural operators built upon the Transolver architecture, and proposes a simple yet effective replay-based continual learning strategy. The proposed method is fully physics-informed and does not require labeled data, relying solely on input fields together with physical constraints for training. When new OOD data become available, a small number of past data are incorporated through a distillation-based constraint to preserve previously acquired knowledge and alleviate catastrophic forgetting. Meanwhile, a transfer learning LoRA is employed to enable rapid adaptation to the new data. The proposed framework is systematically validated on three representative physical problems, including the Darcy flow problem in fluid mechanics, a two-dimensional hyperelastic brain tumor problem in biomechanics, and a three-dimensional linear elastic Triply Periodic Minimal Surfaces problem in solid mechanics. The results demonstrate that the proposed method effectively mitigates catastrophic forgetting on previously learned data while maintaining fast adaptability to new data. Compared with conventional joint training strategies, the proposed method significantly improves training efficiency while reducing additional memory usage and computational cost.
【16】Concurrence of Symmetry Breaking and Nonlocality Phase Transitions in Diffusion Models
标题：扩散模型中对称性破缺与非定域相变的同时性
链接：https://arxiv.org/abs/2605.04830
备注：20 pages, 10 figures. comments are welcome
摘要：Diffusion models undergo a phase transition in a critical time window during generation dynamics, with two complementary diagnoses of criticality. The symmetry breaking picture views the critical window as when trajectories bifurcate into different semantic minima of the energy landscape, whereas the nonlocality picture views the critical window as when local denoising fails. We study whether two notions of such phase transitions are concurrent in modern diffusion transformers. By evaluating the dynamics and outcomes of the generation trajectory, we observe a near-simultaneous occurrence of the non-locality and symmetry breaking critical times. Our work is the first to unify the two notions of phase transitions in practice: it provides a concrete diagnostic for when and why diffusion models rely on conditioning and global denoising, enabling principled evaluation of model efficiency and guiding the design of architectures and sampling schemes that avoid unnecessary computation.
【17】Cognitive Twins: Investigating Personalized Thinking Model Building and Its Performance Enhancement with Human-in-the-Loop
标题：认知双胞胎：研究个性化思维模型构建及其通过人在环的性能增强
链接：https://arxiv.org/abs/2605.04761
备注：40 pages, 5 figures, 20 tables, 1 algorithm, 10 listings
摘要：This paper presents the Personalized Thinking Model (PTM), a hierarchical and interpretable learner representation designed for AI supported education. PTM organizes evidence from learner journals into a five-layer structure covering behavioral instances, behavioral patterns, cognitive routines, metacognitive tendencies, and self-system values. PTM is grounded in Marzano's New Taxonomy of Educational Objectives and tries to clone learner's thinking model and build cognitive twin. It was constructed using a pipeline that combines large language model inference (Gemini 2.5 Pro), sentence embeddings, dimensionality reduction, and consensus clustering. This paper evaluates PTM fidelity through three methods applied to 40 participants in a seven-week study. First, automatic evaluation using atomic information point matching yielded an overall F1 score of 74.57% before human-in-the-loop (HITL) refinement and 75.48% after refinement. Second, user evaluation using a Likert scale produced mean ratings of 4.26 and 4.30 on a five-point scale for pre and post-HITL conditions respectively. Third, semantic alignment verification showed that topic coherence increased from 0.436 at the behavioral layer to 0.626 at the core value layer, while lexical overlap with journal vocabulary decreased from 0.114 to 0.007 across those same layers. These results suggest that the PTM produces outputs with acceptable fidelity, was generally perceived by users as reflecting their thinking, and showed a pattern consistent with semantic abstraction across layers.
【18】AxMoE: Characterizing the Impact of Approximate Multipliers on Mixture-of-Experts DNN Architectures
标题：AxMoE：描述逼近乘数对混合专家DNN架构的影响
链接：https://arxiv.org/abs/2605.04754
备注：accepted at the IEEE Computer Society Annual Symposium on VLSI ISVLSI 2026
摘要：Deep neural network (DNN) inference at the edge demands simultaneous improvements in accuracy, computational efficiency, and energy consumption. Approximate computing and Mixture-of-Experts (MoE) architectures have each been studied as independent routes towards efficient inference, the former by replacing exact arithmetic with low-power approximate multipliers, the latter by routing inputs through specialized expert sub-networks to enable conditional computation. However, their interaction remains entirely unexplored. This paper presents AxMoE, the first study of the impact of approximate multiplication on MoE DNN architectures. We evaluate three MoE variants: Hard MoE, Soft MoE, and Cluster MoE against dense baselines across three CNN architectures (ResNet-20, VGG11_bn, VGG19_bn) on CIFAR-100 and a Vision Transformer (ViT-Small) on Tiny ImageNet-200 dataset, using eight 8-bit signed multipliers (including one exact baseline) from the EvoApproxLib library. Results show that, without retraining, the Dense baseline is the most resilient topology across all CNN architectures, whereas on ViT-Small, all topologies degrade at comparable rates regardless of routing strategy. After approximate-aware retraining, recovery varies substantially across architectures, topologies, and multipliers. ResNet-20 achieves full recovery across the entire multiplier range, whereas VGG architectures recover at moderate multipliers but fail irreversibly at aggressive ones for all topologies except Cluster MoE on VGG11_bn; on ViT-Small, Hard MoE outperforms Dense under aggressive approximation at equal normalized inference cost. These results pave the way for future approximate MoE hardware-software co-design strategies.
【19】Ensuring Reliability in Programming Knowledge Tracing: A Re-evaluation of Attention-augmented Models and Experimental Protocols
标题：确保程序设计知识追踪的可靠性：对注意增强模型和实验协议的重新评估
链接：https://arxiv.org/abs/2605.04727
备注：Accepted at the International Conference on Intelligent Tutoring Systems (ITS 2026). To appear in Springer LNCS
摘要
：Programming Knowledge Tracing (PKT) has recently advanced through hybrid approaches that integrate attention-based feature modeling for code representation with RNN-based sequential prediction. While these models report strong empirical performance, their reliability can be sensitive to subtle implementation and experimental design choices. This study revisits representative PKT models and shows that reported gains can be substantially influenced by model configuration and sequence construction practices. We identify issues in attention dimension settings that affect performance estimates, and demonstrate that improper ordering of student attempts, such as ignoring ServerTimestamp, can violate temporal causality and lead to overly optimistic results. To ensure consistent evaluation, hyperparameters are selected via grid search guided by a single designated fold and then fixed uniformly across all folds during cross-validation. We further analyze the role of assignment-wise characteristics and systematically explore the impact of maximum sequence length. Using this protocol, we re-evaluate PKT models on the CodeWorkout dataset. Our results show that, under controlled and consistent settings, the performance gap between attention-enhanced models and standard DKT is significantly reduced, and increased architectural complexity does not consistently translate into superior performance. Beyond individual model comparisons, this work provides practical guidance for reliable and comparable evaluation in programming knowledge tracing.
【20】Learning Time-Inhomogeneous Markov Dynamics in Financial Time Series via Neural Parameterization
标题：通过神经参数化学习金融时间序列中的时间非齐次马尔科夫动力学
链接：https://arxiv.org/abs/2605.04690
备注：10 pages, 10 figures and 1 table. Presented at The 2026 ASA Midwest Regional Conference in Statistics and Data Science and the 2026 Undergraduate Symposium at the University of Wisconsin - Madison
摘要：Modeling the dynamics of non-stationary stochastic systems requires balancing the representational power of deep learning with the mathematical transparency of classical models. While classical Markov transition operators provide explicit, theoretically grounded rules for system evolution, their empirical estimation collapses due to severe data sparsity when applied to high-resolution, high-noise environments. We explore this statistical barrier using financial time series as a canonical, real-world testbed. To overcome the degeneracy of empirical counting, we introduce a framework that utilizes neural networks strictly as parameterization engines to generate explicit, time-varying Markov transition matrices. By constraining the neural network to output its predictions as a formal stochastic operator, we maintain complete structural interpretability. We demonstrate that these learned operators successfully capture complex regime shifts: the state-conditioned model achieves mean row heterogeneity $\barρ = 0.0073$ while the state-free ablation collapses to exactly zero, and operator row entropy correlates with realized variance at $r = -0.62$ ($p \approx 10^{-251}$), revealing that high-volatility regimes homogenize transition dynamics rather than diversify them. Furthermore, rather than enforcing the Chapman-Kolmogorov equations as a rigid structural requirement, we repurpose them as a localized diagnostic tool to pinpoint specific temporal windows where first-order memory assumptions break down. Ultimately, this framework demonstrates how neural networks can be constrained to make rigorous, classical operator analysis viable for complex real-world time series.
【21】Counter-Dyna: Data-Efficient RL-Based HVAC Control using Counterfactual Building Models
标题：Counter-Dyna：使用反事实建筑模型的数据高效的基于RL的空调控制
链接：https://arxiv.org/abs/2605.04555
摘要：Model-based reinforcement learning (MBRL) offers a promising approach for data-efficient energy management in buildings, combining the strengths of predictive modeling and reinforcement learning. While previous MBRL methods applied to HVAC control have reduced training data requirements, they still require several months of interaction with the building to learn a satisfactory control policy. A key reason is that existing surrogate models attempt to predict the entire state-space, including weather and electricity prices that are unaffected by control actions, or completely ignore these variables. Addressing these issues, we propose Counter-Dyna, a method that enhances the data-efficiency of Dyna, an MBRL method. We create data-efficient counterfactual surrogate models (CSM) by leveraging invariances in the state-space. Using a CSM in Dyna speeds up RL training measured in environment interaction data compared to previous results. In comparison with previous state-of-the-art that used 6-12 months of environment interactions, our method needs only 5 weeks. We evaluate our method in a large simulation study using the literature standard BOPTEST framework and proximal policy algorithm (PPO) as the RL algorithm. Our results show cost-saving potentials of 5.3% to 17.0% in a hypothetical deployment scenario. Our work is a significant step towards making real-world deployment of RL algorithms in HVAC control practically viable.
【22】SpecPL: Disentangling Spectral Granularity for Prompt Learning
标题：SpecPL：解开光谱粒度以快速学习
链接：https://arxiv.org/abs/2605.04504
摘要：Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglecting the spectral granularity essential for fine-grained discrimination. To bridge this, we introduce Disentangling Spectral Granularity for Prompt Learning (SpecPL), which approaches prompt learning from a novel spectral perspective via Counterfactual Granule Supervision. Specifically, we leverage a frozen VAE to decompose visual signals into semantic low-frequency bands and granular high-frequency details. A frozen Visual Semantic Bank anchors text representations to universal low-frequency invariants, mitigating overfitting. Crucially, fine-grained discrimination is driven by counterfactual granule training: by permuting high-frequency signals, we compel the model to explicitly distinguish visual granularity from semantic invariance. Uniquely, SpecPL serves as a universal plug-and-play booster, revitalizing text-oriented baselines like CoOp and MaPLe via visual-side guidance. Experiments on 11 benchmarks demonstrate competitive state-of-the-art performance, achieving a new performance ceiling of 81.51\% harmonic-mean accuracy. These results validate that spectral disentanglement with counterfactual supervision effectively bridges the gap in the stability-generalization trade-off. Code is released at https://github.com/Mlrac1e/SpecPL-Prompt-Learning.
【23】Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
标题：走向普遍偏好一致：纳什均衡下的扩散模型
链接：https://arxiv.org/abs/2605.04494
备注：21 pages, 5 figures
摘要：Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally efficient alternative that avoids explicit reward modeling and has been widely adopted in diffusion alignment. However, existing preference-based methods for diffusion alignment still rely on reward-induced preference signals and typically assume that human preferences can be adequately modeled by the Bradley--Terry (BT) model, which may fail to capture the full complexity of human preferences. In this paper, we formulate diffusion alignment from a game-theoretic perspective. We propose Diffusion Nash Preference Optimization (Diff.-NPO), an intuitive general preference framework for diffusion alignment. Diff.-NPO encourages the current policy to play against itself to achieve self improvement and lead to a better alignment. Empirically, we demonstrate the effectiveness of Diff.-NPO on the text-to-image generation task via various metrics. Diff.-NPO consistently outperforms existing preference-based diffusion alignment methods.
【24】Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone
标题：部署相关的对齐不能仅从模型级评估中推断
链接：https://arxiv.org/abs/2605.04454
摘要
：Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under fixed inputs, such as truthfulness, instruction following, or pairwise preference, and these scores are often used to support claims about deployed alignment. This paper argues that deployment-relevant alignment cannot be inferred from model-level evaluation alone. Alignment claims should instead be indexed to the level at which evidence is collected: model-level, response-level, interaction-level, or deployment-level. Two studies support this position. First, a structured audit of eleven alignment benchmarks, extended to a sixteen-benchmark corpus, dual-coded against an eight-dimension rubric with Cohen's kappa = 0.87, finds that user-facing verification support is absent across every benchmark examined, while process steerability is nearly absent. The few interactional benchmarks identified, including tau-bench, CURATe, Rifts, and Common Ground, remain fragmented in coverage, and benchmark construction rather than data source determines what is measured. Second, a blinded cross-model stress test using 180 transcripts across three frontier models and four scaffolds finds that the same verification scaffold raises one model's verification support to ceiling while leaving another categorically unchanged. This shows that scaffold efficacy is model-dependent and that the gap identified by the audit cannot be closed at the model level alone. We propose a system-level evaluation agenda: alignment profiles instead of single scores, fixed-scaffolding protocols for comparable interactional evaluation, and reporting templates that make the inferential distance between evaluation evidence and deployment claims explicit.
【25】Counterfactual identifiability beyond global monotonicity: non-monotone triangular structural causal models
标题：超越全球单调性的反事实可识别性：非单调三角结构因果模型
链接：https://arxiv.org/abs/2605.04413
摘要：Structural causal models provide a unified semantics for interventions and counterfactuals, but most identifiability results rely on restrictive assumptions like global monotonicity, which are often violated in embodied interaction, where the same exogenous perturbation can induce opposite responses under different contact contexts. We ask what structure still suffices once global monotonicity is dropped. We introduce non-monotone triangular structural causal models (NM-TM-SCM), which retain triangular recursion but replace global monotonicity with mechanism-wise invertibility and context-independent inverse transport. We prove that these conditions are equivalent to exogenous isomorphism and imply complete counterfactual identifiability, and we give a counterexample showing that local invertibility alone is insufficient. We instantiate the theory in CausalInverter, with triangular invertible layers, orientation gates, and transport-stability regularization. On synthetic non-monotonic mechanisms, the structural bias yields systematic counterfactual gains as non-monotonicity increases. On MuJoCo Door, our model achieves perfect event-level counterfactual recovery, lowers continuous angle error relative to a Transformer baseline, and delivers substantially more stable recovery than Transformer and conditional-flow predictors. On MuJoCo Push, where non-monotonicity is weaker, the same low-data predictors remain competitive or better, consistent with a bias-variance boundary. These results identify a broader identifiable regime between globally monotone triangular models and unconstrained black-box world models.
【26】$p$-adic Manifold Learning and Benchmark Tasks from Impartial Games
标题：$p$-adic来自公正游戏的多维学习和基准任务
链接：https://arxiv.org/abs/2605.04374
摘要：We introduce $p$-adic manifold learning, propose an algorithm to solve it, and propose benchmark tasks from impartial games.
【27】Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
标题：通过测试时间后验调整缓解表格内上下文学习中的标签漂移
链接：https://arxiv.org/abs/2605.04363
备注：ICML 2026
摘要：TabPFN has recently gained attention as a foundation model for tabular datasets, achieving strong performance by leveraging in-context learning on synthetic data. However, we find that TabPFN is vulnerable to label shift, often overfitting to the majority class in the training dataset. To address this limitation, we propose DistPFN, the first test-time posterior adjustment method designed for tabular foundation models. DistPFN rescales predicted class probabilities by downweighting the influence of the training prior (i.e., the class distribution of the context) and emphasizing the contribution of the model's predicted posterior, without architectural modification or additional training. We further introduce DistPFN-T, which incorporates temperature scaling to adaptively control the adjustment strength based on the discrepancy between prior and posterior. We evaluate our methods on over 250 OpenML datasets, demonstrating substantial improvements for various TabPFN-based models in classification tasks under label shift, while maintaining strong performance in standard settings without label shift. Code is available at this repository: https://github.com/seunghan96/DistPFN.
【28】Covariance-Aware Goodness for Scalable Forward-Forward Learning
标题：可扩展的前向-前向学习的协方差感知优度
链接：https://arxiv.org/abs/2605.04346
摘要：The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly under-perform backpropagation on complex benchmarks such as ImageNet-100 and Tiny-ImageNet. We identify this gap as a structural bottleneck in goodness extraction: standard sum-of-squares formulation collapses feature volumes into channel-wise activation energies which omits critical second-order dependencies. To address this, we propose a framework centered on three key components. First, Bi-axis Covariance Goodness(BiCovG) explicitly augments the standard goodness function with structured second-order information along two axes: cross-channel projections that model inter-feature covariance, and nested multi-scale aggregation that encodes spatial correlation statistics. This provides a tractable approximation to covariance-aware goodness without the prohibitive O(C^2) complexity of explicit matrix estimation. Second, a lightweight Logistic Fusion module aggregates layer-wise predictions, amplifying the contribution of deeper representations. Third, the Feature Alignment Layer(FAL) introduces a zero-initialized correction at block boundaries to mitigate representation misalignment in deep locally trained networks. By introducing these three components, we effectively double the depth of viable Forward-Forward learning, extending robust layer utilization from shallow baselines to 16 layer architectures like VGG-16. The resulting BP-free model achieves 73.01% on ImageNet-100 and 50.30% on Tiny-ImageNet. As a practical extension, Hybrid Goodness Blocks control the scope of gradient propagation via configurable block sizes, further narrowing the ImageNet-100 gap to 3.6% and matching BP on Tiny-ImageNet, while still reducing peak memory by approximately 50% relative to BP.
【29】Structural Equivalence and Learning Dynamics in Delayed MARL
标题：延迟MARL中的结构等价和学习动力学
链接：https://arxiv.org/abs/2605.04345
摘要：We formally establish the equivalence between Observation Delay (OD) and Action Delay (AD) in cooperative partially observable multi-agent systems using observation-action histories. We show that both systems generate identical admissible joint-policy sets, and their induced state-action-observation trajectories are identical in distribution, leading to identical optimal solutions in Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). This formally generalizes existing infinite-horizon single-agent results to any-horizon partially observable cooperative multi-agent problems with decentralized policy execution, and allows any mixed-delay configuration to be reduced to a pure OD system. We further prove that in Transition-Independent MDPs (TI-MDPs), the observation-action history reduces to a tractable minimal local augmented state. However, we show through numerical experiments that although the optimal solution spaces are structurally isomorphic, the practical learning dynamics are fundamentally different. First, using the minimal local augmented state, the equivalence no longer holds when transitions are not independent. Second, operational constraints and causal credit-assignment errors in Temporal Difference (TD) algorithms induce different learning behaviors across regimes. Finally, leveraging this structural equivalence to bypass these learning challenges, we demonstrate successful multi-agent zero-shot policy transfer from OD to AD, paving the way for unified, efficient solution methods in complex delayed systems.
【30】On the Architectural Complexity of Neural Networks
标题：关于神经网络的架构复杂性
链接：https://arxiv.org/abs/2605.04325
备注：67 pages, 54 figures, 11 tables
摘要：We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.
【31】Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
标题：模型参数中无法检测到的后门：在高维度中隐藏稀疏的秘密
链接：https://arxiv.org/abs/2605.04209
摘要：We present Sparse Backdoor, a supply-chain attack that plants a \emph{provably undetectable} backdoor in pre-trained image classifiers, including convolutional networks and Vision Transformers. The attack injects a structured sparse perturbation along a randomly chosen direction into a small subset of columns at each fully connected layer, propagating a trigger signal to an adversary-chosen target class, and masks the perturbation with an independent isotropic Gaussian dither. The dither serves a single technical purpose: it induces a clean reference distribution anchored at the pre-trained weights, against which undetectability can be formalized. Under a mild margin condition on the pre-trained classifier, we show that the dithered reference is functionally equivalent to the original classifier. We prove that distinguishing the backdoor-injected model from this reference is at least as hard as Sparse PCA detection, which is computationally infeasible under standard hardness assumptions. The guarantee holds against any probabilistic polynomial-time distinguisher with white-box access to the parameters.
【32】Deep Wave Network for Modeling Multi-Scale Physical Dynamics
标题：用于多尺度物理动力学建模的深波网络
链接：https://arxiv.org/abs/2605.04198
摘要：Performance of deep learning models is strongly governed by architectural capacity, with width and depth as primary controls. However, in physical-science applications, models are often compared at a single fixed size or by separating accuracy and computational cost, which can be misleading since architectures exhibit different accuracy-cost scaling as width and depth vary. This issue is particularly relevant for U-Net-type encoder-decoder models, widely used for multi-scale gas, fluid, and plasma dynamics due to their ability to represent features across spatial scales. A U-Net constructs a multi-resolution representation via an encoder that progressively reduces spatial resolution, followed by a decoder that restores it for prediction. Skip connections link corresponding encoder and decoder features, preserving fine-scale information and improving optimization. In practice, U-Net width is routinely tuned, while depth is typically kept fixed (a set number of down/up-sampling stages with few convolutions per stage), limiting systematic exploration of depth for improving the accuracy-cost trade-off. We address this limitation by increasing effective depth through stacking multiple encoder-decoder "waves" in series, with skip connections both within and across waves to enable progressive cross-scale refinement. We call this architecture a Deep Wave Network (DW-Net). Training data, optimization, and schedules are kept identical across models. Instead of evaluating single configurations, we train multiple width variants of each architecture and compare accuracy vs. GPU time Pareto fronts. Across several 2D and 3D flow benchmarks, DW-Net models consistently improve the Pareto frontier over single-wave U-Nets, achieving higher accuracy at matched cost or similar accuracy at reduced cost, and reaching low-error regimes with up to 3x less training time under identical training settings.
【33】Constrained Extreme Gradient Boosting for Adapting Reduced-Order Models
标题：适应降阶模型的约束极端梯度提升
链接：https://arxiv.org/abs/2605.04130
备注：Preprint. Under review. 4 numerical examples
摘要
：High-fidelity simulations, such as computational fluid dynamics and finite element analysis, are essential for modeling complex engineering systems but are often prohibitively expensive for tasks including parametric studies, optimization, and real-time control. Projection-based reduced-order models (ROMs) alleviate this cost by projecting the governing dynamics onto low-dimensional subspaces. However, their performance can deteriorate under parameter variation, motivating the need for adaptive basis construction. In this work, we propose a constrained ensemble learning framework, termed Constrained Extreme Gradient Boosting (cXGBoost), for predicting Proper Orthogonal Decomposition (POD) bases as functions of system parameters. The approach leverages a geometric representation of subspaces on the Grassmann manifold, which are mapped to a Euclidean space to enable efficient regression using gradient boosting trees. A norm constraint is imposed during training to ensure the validity of the inverse mapping and preserve the geometric structure of the predicted subspaces. The proposed method is evaluated on four numerical examples, including fluid dynamics and wave propagation problems, demonstrating its ability to accurately predict parameter-dependent bases while maintaining robustness across nonlinear regimes. These results highlight the potential of combining geometric learning with constrained ensemble methods for scalable and reliable reduced-order modeling of high-dimensional parametric systems.
【34】Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities
标题：位置：煤矿里的随机鹦鹉。模型崩溃是对低资源社区的威胁
链接：https://arxiv.org/abs/2605.04127
备注：13 pages, 1 figure, International Conference on Machine Learning
摘要：Model collapse, the degradation in performance that arises when generative models are trained on the outputs of prior models, is an increasing concern as artificially generated content proliferates. Related critiques of large language models have highlighted their tendency to reproduce frequent patterns in training data, their reliance on vast datasets, and their substantial environmental cost. Together, these factors contribute to data degradation, the reinforcement of cultural biases, and inefficient resource use. In this position paper we aim to combine these views and argue that model collapse threatens current efforts to democratize AI. By reducing training efficiency and skewing data distributions away from the tails of their support, model collapse disproportionately impacts low-resource and marginalized communities. We examine both the environmental and cultural implications of this phenomenon, situate our position within recent position papers on model collapse, and conclude with a call to action. Finally, we outline initial directions for mitigating these effects.
【35】Learning reveals invisible structure in low-rank RNNs
标题：学习揭示了低秩RNN中的不可见结构
链接：https://arxiv.org/abs/2605.04115
备注：30 pages, 12 figures
摘要：Learning in neural systems arises from synaptic changes that reshape the representations underlying behavior. While low-rank recurrent neural networks (RNNs) have emerged as a powerful framework for linking connectivity to function, a theoretical understanding of their learning process remains elusive. Here, we extend the low-rank framework from activity to learning by deriving gradient-descent dynamics directly in a reduced overlap space. We formulate a closed-form, low-dimensional system of ODEs that governs learning in this space, exact for linear RNNs and asymptotically exact for nonlinear RNNs in the large-$N$ Gaussian limit. Central to our analysis is a distinction between two classes of overlaps: loss-visible overlaps, which fully determine network activity, output, and loss, and loss-invisible overlaps, which do not affect function but are required to describe learning. We illustrate the consequences of this decomposition through two phenomena. First, we show that learning can serve as a perturbation that exposes differences in connectivity between functionally equivalent networks. Second, we show that loss-invisible overlaps can act as memory variables that encode training history, and characterize the conditions under which this occurs. Finally, we present several testable predictions for biological learning experiments derived from our theory.
【36】HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Search
标题：赫尔库莱斯：硬件高效、稳健、持续学习的神经架构搜索
链接：https://arxiv.org/abs/2605.04103
备注：21 pages, 1 figure
摘要：Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-world deployment, the traditional focus on hardware-aware efficiency is no longer sufficient. We observe that modern NAS methods, especially those that target edge AI, are evolving to address a triple objective: Efficiency, Robustness, and Continual Learning. While efficiency ensures feasibility in resource-constrained environments, robustness guarantees reliability under environmental variabilities, and continual learning enables adaptation to sequential tasks without catastrophic forgetting. We propose a taxonomy of NAS approaches through this triple lens, distinguishing between methods targeting resource optimization, environmental resilience, and architectural plasticity. This unified perspective reveals that these axes, though often studied in isolation, are mutually reinforcing. Building on this taxonomy, we map the current landscape of these NAS methods into a new framework called Hardware-Efficient, Robust, and ContinUal LEarning Search (HERCULES). We define the desiderata, the twelve labours of HERCULES, addressing the non-trivial challenge of balancing an adequate search-space exploration with the immense computational costs of a multi-objective NAS, accounting for these crucial objectives of current AI systems. By identifying critical gaps in existing research, this survey outlines a roadmap toward integrated algorithmic, architectural, and hardware-software co-design for truly deployable, lifelong-learning AI systems.
【37】Enhancing the interpretability of spatially variable N2O model predictions with soft sensors during wastewater treatment
标题：利用软传感器增强废水处理期间空间变量N2 O模型预测的可解释性
链接：https://arxiv.org/abs/2605.04082
备注：1 Graphical abstract, 2 Tables, 7 Figures
摘要：Model-based solutions for nitrous oxide (N2O) emissions from wastewater treatment plants (WWTP) are informed by operational datasets designed to control nutrient levels in liquid waste, coupled with dedicated campaigns for N2O measurements. We analysed how machine learning (ML) models predict disturbances to WWT operation and spatially variable N2O emissions. A real dataset was investigated to validate the modelling framework from N2O emissions predicted by four ML models (R2 = 0.79 - 0.89). Monitoring campaigns for N2O were simulated with a plant-wide mechanistic model to include additional sensors, site-level N2O datasets, and wastewater disturbances (n = 16). ML models were highly accurate (0.97 +- 0.02, n = 80), but the feature importance depended on the model, the scenario and the N2O measurement scale (reactor vs. WWTP). We argue that N2O soft sensor model predictions are limited to the measuring location and the methodological uncertainty of the dataset, which affect the interpretability of the model. Lastly, the analysis of the mechanistic model structure exposed interactions between autotrophic and heterotrophic pathways over nitric oxide which can overestimate aerobic nitrite production and bias the N2O pathway contributions.
【38】Connecting online criminal behavior with machine learning: Using authorship attribution to analyze and link potential online traffickers
标题：将在线犯罪行为与机器学习联系起来：使用作者归因来分析和链接潜在的在线贩运者
链接：https://arxiv.org/abs/2605.04080
备注：Doctoral thesis
摘要
：This research investigated how online criminal activities can be better understood and connected using data-driven machine learning methods. Many illegal activities, such as human trafficking and illicit trade, have moved to online platforms where offenders hide behind anonymous accounts and frequently change identities. This makes it difficult for authorities to understand how large these networks are and how different online profiles may be linked. The research shows that people tend to maintain consistent patterns in how they write advertisements and present images online, even when they try to stay anonymous. By analysing these patterns across large collections of online advertisements, the research demonstrates how to link related accounts and identify repeated behaviour across illegal online markets. In addition, the research also addresses how such methods should be used responsibly. It proposes clear guidelines to ensure that privacy, fairness, and transparency are respected when these tools are applied. Overall, the research provides practical ways to support law enforcement investigations while emphasising careful and ethical use.
【39】Single-Position Intervention Fails: Distributed Output Templates Drive In-Context Learning
标题：单位置干预失败：分布式输出模板推动上下文学习
链接：https://arxiv.org/abs/2605.04061
备注：8 pages, 3 figures. Accepted to the 2026 Learning and Intelligent Optimization Conference and workshops on Foundation Models for Science: Real-World Impact and Science-First Design, Latent & Implicit Thinking - Going Beyond CoT Reasoning, Logical Reasoning of Large Language Models at ICLR 2026
摘要：Understanding how large language models encode task identity from few-shot demonstrations is a central open problem in mechanistic interpretability. Prior work uses linear probing to localize task representations, reporting high classification accuracy at specific layers. We reveal a striking dissociation: probing accuracy completely fails to predict causal importance. Single-position activation intervention achieves 0% task transfer across all 28 layers of Llama-3.2-3B-despite 100% probing accuracy at those same positions. This null result is itself a key finding, demonstrating that task encoding is fundamentally distributed. Multi-position intervention-replacing activations at all demonstration output tokens simultaneously-achieves up to 96% transfer (N=50, 95% CI: [87%, 99%]) at layer 8, pinpointing for the first time the causal locus of ICL task identity. We establish the generality of these findings across four models spanning three architecture families (LLaMA, Qwen, Gemma), discovering a universal intervention window at ~30% network depth. Causal tracing uncovers an asymmetric architecture: the query position is strictly necessary (53-100% disruption) while no individual demonstration position is necessary (0% disruption)-resolving a key ambiguity in prior accounts. Crucially, transfer depends on internal representation compatibility, not surface similarity (r=-0.05 vs r=0.31), ruling out trivial explanations. These results establish the distributed template hypothesis: ICL task identity is encoded as output format templates distributed across demonstration tokens, fundamentally reshaping our understanding of how in-context learning operates.
【40】Lookahead Drifting Model
标题：前瞻漂移模型
链接：https://arxiv.org/abs/2605.04060
【41】Endogenous Regime Switching Driven by Scalar-Irreducible Learning Dynamics
标题：量不可约学习动力学驱动的内生政权转换
链接：https://arxiv.org/abs/2605.04054
【42】Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
标题：通过代表定理学习再生核赫BERT空间中的重建嵌入
链接：https://arxiv.org/abs/2601.05811
【43】Proximal Projection for Doubly Sparse Regularized Models
标题：双稀疏正规化模型的近端投影
链接：https://arxiv.org/abs/2605.05093
【44】Multiscale Euclidean Network Trajectories: Second-Moment Geometry, Attribution, and Change Points
标题：多尺度欧几里得网络轨迹：二次矩几何、归因和变化点
链接：https://arxiv.org/abs/2605.04589
【45】Heterogeneous Ordinal Structure Learning with Bayesian Nonparametric Complexity Discovery
标题：具有Bayesian非参数复杂性发现的异类有序结构学习
链接：https://arxiv.org/abs/2605.04191
其他(48篇)
【1】Estimating the expected output of wide random MLPs more efficiently than sampling
标题：比采样更有效地估计宽随机MLP的预期输出
链接：https://arxiv.org/abs/2605.05179
备注：68 pages. Code is available at https://github.com/alignment-research-center/mlp_cumulant_propagation
【2】What Matters in Practical Learned Image Compression
标题：实际学习图像压缩中的重要性
链接：https://arxiv.org/abs/2605.05148
【3】Transformed Latent Variable Multi-Output Gaussian Processes
标题：变换的潜变量多输出高斯过程
链接：https://arxiv.org/abs/2605.05133
备注：ICML 2026
【4】How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
标题：无限宽度持续多久？长期线性回归中的信号传播
链接：https://arxiv.org/abs/2605.05113
【5】Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime
标题：推出通过率控制：引导二进制奖励RL走向最具信息性的制度
链接：https://arxiv.org/abs/2605.05112
备注：25 pages, 8 figures, 11 tables
【6】A Bayesian Approach for Task-Specific Next-Best-View Selection with Uncertain Geometry
标题：不确定几何条件下任务特定次优视图选择的贝叶斯方法
链接：https://arxiv.org/abs/2605.05095
备注：Code for this paper is available at https://github.com/jingsenzhu/BayesianNBV
【7】Kinematic Discriminants of Deceleration Behavior Modes in Car-Following: Evidence from NGSIM Trajectory Data
标题：跟车减速行为模式的运动学辨别：来自NGSIM轨迹数据的证据
链接：https://arxiv.org/abs/2605.05050
【8】Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
标题：自我诱导的结果潜力：没有验证员的代理人的回合级信用分配
链接：https://arxiv.org/abs/2605.04984
【9】Conceptors for Semantic Steering
标题：语义导向的概念
链接：https://arxiv.org/abs/2605.04980
【10】Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics
标题：自我注意力作为交通：对称光谱诊断的局限性
链接：https://arxiv.org/abs/2605.04893
备注：42 pages, 6 figures, 3 tables; 82-page online supplement (proofs, additional experiments, dataset statistics) as an ancillary file
【11】Hybrid Iterative Neural Low-Regularity Integrator for Nonlinear Dispersive Equations
标题：非线性频散方程的混合迭代神经低规则积分器
链接：https://arxiv.org/abs/2605.04853
【12】Bilinear Mamba-Koopman Neural MPC for Varying Dynamics
标题：适用于变化动态的双线性Mamba-Koopman神经MPC
链接：https://arxiv.org/abs/2605.04793
备注：18 pages, 5 figures. Preprint
【13】Using Common Random Numbers for Simulation-based Planning with Rollouts
标题：使用公共随机数进行带卷展的基于仿真的规划
链接：https://arxiv.org/abs/2605.04732
【14】Exact Dual Geometry of SOC-ICNN Value Functions
标题：SOC-ICNN值函数的精确二元几何
链接：https://arxiv.org/abs/2605.04722
【15】Budget-aware Auto Optimizer Configurator
标题：预算意识自动优化器触发器
链接：https://arxiv.org/abs/2605.04711
【16】ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
标题：ELLIS：用于长视野视觉MPC的整体校准潜在想象力
链接：https://arxiv.org/abs/2605.04709
【17】Differentiable Chemistry in PINNs for Solving Parameterized and Stiff Reaction Systems
标题：PINN中用于求解参数化和刚性反应系统的差异化学
链接：https://arxiv.org/abs/2605.04708
【18】Gray-Box Poisoning of Continuous Malware Ingestion Pipelines
标题：连续恶意软件摄入管道的灰箱中毒
链接：https://arxiv.org/abs/2605.04698
【19】ITBoost: Information-Theoretic Trust for Robust Boosting
标题：ITBoost：稳健提升的信息理论信任
链接：https://arxiv.org/abs/2605.04671
【20】Neural-Guided Domain Restriction to Accelerate Pseudospectra Computation for Structured Non-normal Banded Matrices
标题：神经引导区域限制加速结构非正规带状矩阵伪谱计算
链接：https://arxiv.org/abs/2605.04550
【21】UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
标题：UniVer：多步骤和多草稿推测解码的统一视角
链接：https://arxiv.org/abs/2605.04543
【22】From Video-to-PDE: Data-Driven Discovery of Nonlinear Dye Plume Dynamics
标题：从视频到PDE：非线性染料羽流动力学的数据驱动发现
链接：https://arxiv.org/abs/2605.04535
【23】Discovering Sparse Counterfactual Factors via Latent Adjustment for Survey-based Community Intervention
标题：通过基于调查的社区干预的潜在调整发现稀疏的反事实因素
链接：https://arxiv.org/abs/2605.04460
【24】Evaluation Cards for XAI Metrics
标题：XAI收件箱评估卡
链接：https://arxiv.org/abs/2605.04410
备注：7 pages. Accepted at the 5th XAI4CV Workshop, CVPR 2026 (non-archival)
【25】Contextual Memory-Enhanced Source Coding for Low-SNR Communications
标题：用于低SNR通信的上下文存储增强源编码
链接：https://arxiv.org/abs/2605.04400
【26】Extending Differential Temporal Difference Methods for Episodic Problems
标题：情景问题的差异时间差方法的扩展
链接：https://arxiv.org/abs/2605.04368
备注：RLC 2026
【27】Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping
标题：作为马尔科夫矩阵的记忆：通过令牌到词典映射的示例高效知识扩展
链接：https://arxiv.org/abs/2605.04308
备注：Accepted to ICML 2026
【28】Gradient Flow Structure and Quantitative Dynamics of Multi-Head Self-Attention
标题：多头自我注意力的梯度流结构和定量动力学
链接：https://arxiv.org/abs/2605.04279
备注：20 pages, 5 figures
【29】Explaining and Preventing Alignment Collapse in Iterative RLHF
标题：解释和防止迭代RL HF中的对齐崩溃
链接：https://arxiv.org/abs/2605.04266
备注：Code at: https://github.com/GauthierE/fpo
【30】Climate-based Pre-screening of Self-sustaining Regreening Opportunities in Drylands: A Case Study for Saudi Arabia
标题：基于气候的干旱地区自我维持的再绿化机会预筛选：沙特阿拉伯的案例研究
链接：https://arxiv.org/abs/2605.04206
【31】Enabling Real-Time Training of a Wildfire-to-Smoke Map with Multilinear Operators
标题：使用多线性运算符实现野火到烟雾地图的实时训练
链接：https://arxiv.org/abs/2605.04164
备注
：27 pages
【32】Simultaneous CNN Approximation on Manifolds with Applications to Boundary Value Problems
标题：流形上的联合CNN逼近及其在边值问题中的应用
链接：https://arxiv.org/abs/2605.04126
【33】AsymmetryZero: A Framework for Operationalizing Human Expert Preferences as Semantic Evals
标题：AsimmyZero：将人类专家偏好操作为语义Evals的框架
链接：https://arxiv.org/abs/2605.04083
【34】Time series causal discovery with variable lags
标题：具有可变滞后的时间序列因果发现
链接：https://arxiv.org/abs/2605.04081
【35】Confronting Label Indeterminacy in Automated Bail Decisions
标题：自动保释决策中面临标签不确定性
链接：https://arxiv.org/abs/2605.04073
备注：This manuscript has been accepted for presentation as a short paper at the 21st International Conference of AI & Law in Singapore, June 8 to 12 of 2026
【36】Toward Human-AI Complementarity Across Diverse Tasks
标题：实现多元化任务中的人机互补
链接：https://arxiv.org/abs/2605.04070
备注：10 pages main text, 37 pages total with appendices
【37】SemiConLens: Visual Analytics for 2D Semiconductor Discovery
标题：SemiConLens：用于2D半导体探索的视觉分析
链接：https://arxiv.org/abs/2605.04067
【38】Transformation Categorization Based on Group Decomposition Theory Using Parameter Division
标题：基于参数划分的群分解理论的变换分类
链接：https://arxiv.org/abs/2605.04056
【39】Constraint-Aware Execution Planning for Hybrid Space-Ground Compute Workloads
标题：混合空地计算工作负载的约束感知执行规划
链接：https://arxiv.org/abs/2605.04052
备注：11 pages, 6 figures, 2 algorithms, 4 tables
【40】Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
标题：线性联想记忆中的尖锐容量阈值：从赢家通吃到列表检索
链接：https://arxiv.org/abs/2605.05189
【41】Building informative materials datasets beyond targeted objectives
标题：构建超出目标的信息材料数据集
链接：https://arxiv.org/abs/2605.05104
【42】Jacobian-Velocity Bounds for Deployment Risk Under Covariate Drift
标题：协变量漂移下部署风险的Jacobi-Speed界限
链接：https://arxiv.org/abs/2605.04932
备注：8 pages, 4 figures, 4 tables
【43】Neural Discovery of Strichartz Extremizers
标题：埃哈茨均衡器的神经发现
链接：https://arxiv.org/abs/2605.04918
备注：38 pages, 26 figures
【44】PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
标题：PAIR-CI：不完整数据下因果发现的校准条件独立性测试
链接：https://arxiv.org/abs/2605.04838
【45】Generative Quantum-inspired Kolmogorov-Arnold Eigensolver
标题：生成量子启发的Kolmogorov-Arnold特征解算器
链接：https://arxiv.org/abs/2605.04604
【46】Causal discovery under mean independence and linearity
标题：平均独立性和线性下的因果发现
链接：https://arxiv.org/abs/2605.04381
备注：25 pages, 5 figures
【47】Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction
标题：用于祖先序列重建的树条件编辑流
链接：https://arxiv.org/abs/2605.04119
备注：9 pages of main text, 3 figures, 3 tables, and 1 algorithm. This version is a preliminary preprint
【48】Analogy between Boltzmann machines and Feynman path integrals
标题：Boltzmann机与Feynman路径积分的类比
链接：https://arxiv.org/abs/2301.06217
机器翻译由腾讯交互翻译提供，仅供参考
点击“阅读原文”获取带摘要的学术速递
Python社区是高质量的Python/Django开发社区
本文地址：http://www.python88.com/topic/195987
本文地址：http://www.python88.com/topic/195987