|
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264篇
大模型相关(31篇)
【1】AMEL: Accumulated Message Effects on LLM Judgments
标题：AMEL：累积信息对LLM判断的影响
链接：https://arxiv.org/abs/2605.22714
备注：19 pages, 14 figures, 6 tables. Single author. Code, data (75,898 deduplicated API responses), and analysis pipeline at this https URL
摘要：
【2】Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
标题：概念化嵌入：视觉语言模型的稀疏解纠缠
链接：https://arxiv.org/abs/2605.22679
摘要：
【3】Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery
标题：LLM引导程序发现的进化多任务优化
链接：https://arxiv.org/abs/2605.22613
摘要：
【4】Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions
标题：医疗保健LLM基准仅取决于其明确的假设
链接：https://arxiv.org/abs/2605.22612
备注：13 pages, 1 figure
摘要：
【5】GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving
标题：GraphFlow：一种基于图的高效LLM-Agent服务工作流管理
链接：https://arxiv.org/abs/2605.22566
备注：Accepted to ICML 2026
摘要：
【6】Relational Linear Properties in Language Models: An Empirical Investigation
标题：语言模型中的关系线性特性：实证研究
链接：https://arxiv.org/abs/2605.22532
摘要：
【7】Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
标题：将统计工作流汇编为LLM权重：以两个数量级的成本实现接近前沿的质量
链接：https://arxiv.org/abs/2605.22502
备注：19 pages
摘要：
【8】One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs
标题：一个LR不适合所有人：LLM的重尾引导分层学习率
链接：https://arxiv.org/abs/2605.22297
摘要：Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice of applying a uniform learning rate across all layers overlooks the structural heterogeneity of Transformers, potentially limiting their effectiveness as the backbone of Large Language Models (LLMs). In this paper, we introduce Layerwise Learning Rate (LLR), an adaptive scheme that assigns distinct learning rates to individual Transformer layers. Our method is grounded in Heavy-Tailed Self-Regularization (HT-SR) theory, which characterizes the empirical spectral density (ESD) of weight correlation matrices to quantify heavy-tailedness. Layers with weaker heavy-tailedness are assigned larger learning rates to accelerate their training, while layers with stronger heavy-tailedness receive smaller learning rates. By tailoring learning rates in this manner, LLR promotes balanced training across layers, leading to faster convergence and improved generalization. Extensive experiments across architectures (from LLaMA to GPT-nano), optimizers (AdamW and Muon), and parameter scales (60M-1B) demonstrate that LLR achieves up to 1.5x training speedup and outperforms baselines, notably raising average zero-shot accuracy from 47.09% to 49.02%. A key advantage of LLR is its low tuning overhead: it transfers nearly optimal LR settings directly from the uniform baseline. Code is available at https://github.com/hed-ucas/Layer-wise-Learning-Rate.
【9】Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
标题：根据能力定制教学：LLM推理的方向适应性自蒸馏
链接：https://arxiv.org/abs/2605.22263
备注：Under Review
摘要：On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level supervision on its own rollouts. However, recent studies show that OPSD degrades complex reasoning by suppressing predictive uncertainty, which supports exploration and hypothesis revision. Our token-level analysis shows that this failure arises from applying a uniform direction of teacher supervision across tokens with different uncertainty levels: conformity to the privileged self-teacher suppresses exploration at high entropy, while deviation from the teacher degrades step accuracy at low entropy. Accordingly, we propose \textbf{Direction-Adaptive Self-Distillation} (\textbf{DASD}), which reframes privileged self-distillation from uniform teacher imitation into entropy-routed directional supervision: high-entropy tokens are pushed away from the privileged teacher to preserve exploration, while low-entropy tokens are pulled toward the teacher to stabilize step-level execution. Across six mathematical reasoning benchmarks, DASD achieves the best macro Avg@16 over strong RLVR and self-distillation baselines. Pass@$k$, reasoning-health, and generalization analyses show that these average gains come from preserving exploration without sacrificing step-level execution.
【10】Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
标题：技能编织：通过模块化技能包高效改进LLM
链接：https://arxiv.org/abs/2605.22205
备注：Accepted by ACL2026
摘要：Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities with strict memory and inference constraints. In this work, we introduce SkillWeave, a modular improvement framework that enables LLMs to specialize under fixed memory budgets. SkillWeave partitions full capabilities of a general-purpose model into skillpacks -- lightweight, domain-specific delta modules -- that reorganize and refine the model's internal knowledge. For efficient deployment, SkillWeave integrates SkillZip to compress skillpacks into compact and inference-ready format, enabling strong multi-domain performance with low-latency execution. On multi-task and agentic benchmarks, a 9B SkillWeave model outperforms several baselines and even surpasses a 32B monolithic LLM, while achieving up to 4x speedup.
【11】Reinforced Graph of Thoughts: RL-Driven Adaptive Prompting for LLMs
标题：强化思维图：LLC驱动的自适应预算
链接：https://arxiv.org/abs/2605.22195
备注：26 pages (including appendix), 16 figures
摘要：Graph of Thoughts (GoT), a generalized form of recent prompting paradigms for large language models (LLMs), has been shown to be useful for elaborate problem solving. By executing a graph of operations, thoughts of the LLM are structured as an arbitrary graph, forming the actual graph of thoughts. Originally, the graph of operations is defined manually, which requires in-depth knowledge about the solution of the problem to solve. Such a static graph of operations is rigid and therefore lacks adaptability. We propose Reinforced Graph of Thoughts (RGoT), an automated approach to the GoT prompting paradigm that leverages reinforcement learning (RL) to adaptively generate a graph of operations from a human-defined set. Results indicate that, under certain constraints, it is possible to construct graphs of operations adaptively to the task's complexity in an automated way.
【12】Enhancing Multimodal Large Language Models for Safety-Critical Driving Video Analysis
标题：增强用于安全关键驾驶视频分析的多模式大型语言模型
链接：https://arxiv.org/abs/2605.22185
备注：Accepted at the 2026 IEEE International Conference on Intelligent Transportation Systems (ITSC 2026)
摘要：Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, their application to safety-critical driving scenarios remains limited by an inability to accurately perceive and reason about rare high-stakes dynamic events, such as collisions or near-collisions. To address this, we introduce a pipeline that enhances MLLM perception by fusing downsampled video frames with synchronized high-frequency telematics data (IMU and GPS) and semantic insights from specialized computer vision models. Our pipeline generates high-quality pseudo-labels, including descriptive captions and question-answer pairs, specifically designed to train MLLMs to identify and describe Safety-Critical Events (SCEs) in real-world driving footage. We show the effectiveness of our approach fine-tuning the open-source QwenVL-2.5 model via DoRA adapters: our experiments demonstrate significant improvements in identifying and explaining safety-critical events, with fewer than 50M trainable parameters and limited computational budget.
【13】One-Way Policy Optimization for Self-Evolving LLMs
标题：自进化LLM的单向策略优化
链接：https://arxiv.org/abs/2605.22156
摘要：
【14】From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
标题：从推理链到可验证子问题：课程强化学习实现LLM推理的学分分配
链接：https://arxiv.org/abs/2605.22074
摘要：
【15】LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation
标题：LABO：通过广泛的探索和选择性实验实现LLM加速Bayesian优化
链接：https://arxiv.org/abs/2605.22054
备注：Accepted to ICML 2026
摘要：The high cost and data scarcity in scientific exploration have motivated the use of large language models (LLMs) as knowledge-driven components in Bayesian optimization (BO). However, existing approaches typically embed LLMs directly into the sampling or surrogate modeling pipeline, without fully leveraging their significantly lower evaluation cost compared to real-world experiments. To address this limitation, we propose LLM-Accelerated Bayesian Optimization (LABO), a framework that combines LLM predictions with experimental observations within a single BO loop. LABO employs a gating criterion to dynamically balance the reliance on LLM predictions versus actual experiments. By leveraging inexpensive LLM evaluations to broadly explore the search space and reserving costly real experiments only for regions with high uncertainty, LABO achieves more sample-efficient optimization. We provide a theoretical analysis with a cumulative regret bound that formalizes this efficiency gain. Empirical results across diverse scientific tasks demonstrate that LABO consistently outperforms existing methods under identical experimental budgets. Our results suggest that LABO offers a practical and theoretically grounded approach for integrating LLMs into scientific discovery workflows.
【16】Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
标题：查看您的LLM秘密词典！五行代码揭示了您的LLM学到了什么（包括它不应该学到的东西）
链接：https://arxiv.org/abs/2605.22005
摘要
：We show that singular value decomposition of the lm_head} weight matrix of a transformer-based large language model -- requiring only five lines of PyTorch and no model inference -- reveals interpretable semantic subspaces directly from the model weights. Each left singular vector identifies the vocabulary tokens most readily selected when the hidden state aligns with the corresponding singular direction; inspecting these clusters exposes the model's training data composition and curation philosophy. Analysing GPT-OSS-120B, Gemma-2-2B, and Qwen2.5-1.5B, we find that singular value spectra and vocabulary cluster structures differ systematically across models: GPT exhibits a graduated hierarchy of functionally differentiated subspaces; Gemma is dominated by pre-nineteenth-century English orthography, forming a stepwise clustering structure that may contribute to high output controllability; and Qwen exhibits broad multilingual coverage alongside subspaces whose vocabulary the authors have determined to be ethically inappropriate for direct publication. Base-instruct comparison reveals that ethically concerning subspaces originate in pretraining and are not removed by post-training alignment. We introduce the Vocabulary Cluster Score (VCS) to quantify subspace coherence, and the Weighted Projection Score (WPS) as a static glitch token detector; applying WPS to GPT-OSS-120B recovers shokubutsu-hyakka-tsu (ID 137606), a well-known glitch token widely reported in the CJK language community, without any model inference. We propose a taxonomy of root causes for problematic vocabulary content and call for lm_head} SVD analysis to be adopted as a standard pre-release safety auditing step. Our findings further suggest directions toward SVD-guided tokenizer optimisation and more controllable LLM design.
【17】Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
标题：Ex-GraphRAG：图形增强LLM的可解释证据路由
链接：https://arxiv.org/abs/2605.21994
摘要：GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via message-passing GNNs. Because these encoders entangle node contributions through iterated neighborhood aggregation, there is no closed-form way to determine how much each retrieved entity influenced the encoder's output, and therefore no way to faithfully audit what structural evidence actually reached the model. We introduce Ex-GraphRAG, which replaces the GNN encoder with a Multivariate Graph Neural Additive Network (M-GNAN), an extension of additive graph models to high-dimensional embedding spaces that yields an exact decomposition of the encoder's output across individual nodes and feature groups, without post-hoc approximation. On STaRK-Prime, this auditable encoder matches black-box performance. Using it to audit evidence routing, we uncover a semantic-structural mismatch: the nodes that dominate the encoder's output are structurally disconnected in the retrieved subgraph, held together by low-attribution intermediaries whose removal degrades multi-hop QA by up to 28%. This mismatch, invisible to any opaque encoder, reveals that semantic importance and structural connectivity are governed by disjoint sets of nodes, with direct implications for retrieval pruning, context construction, and failure diagnosis in graph-augmented LLMs.
【18】Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs
标题：通过可验证的预测动作进行推理：金融LLM的一致性基础RL
链接：https://arxiv.org/abs/2605.21975
摘要：Financial markets are characterized by extreme non-stationarity, low signal-to-noise ratios, and strong dependence on external information such as news, company fundamentals, and macroeconomic signals. Yet, existing approaches either abstract time-series into text or decouple forecasting from language-based reasoning, leading to a fundamental mismatch between qualitative reasoning and quantitative outcomes. To address this, we introduce StockR1, a time-series-enhanced LLM that unifies stock forecasting and financial reasoning through a verifiable forecast action. Based on a tool-call design, the model first emits a forecast action, which is a structured and interpretable representation of its qualitative market outlook. It then invokes a time-series decoder conditioned on this action to generate distributional future trajectories, leading to more informed question answering and financial reasoning. We optimize the full pipeline with reinforcement learning, where rewards jointly reflect answer validity, forecast accuracy, and consistency between generated actions and observed time-series dynamics. In addition, rewards are reweighted by a sample-level uncertainty scalar, encouraging the model to accommodate varying uncertainty in market dynamics. We evaluate StockR1 on financial question answering and stock forecasting over a large-scale 10-year benchmark. Our method consistently outperforms time-series baselines and general-purpose LLMs, improving reasoning accuracy by 17.7% (4B) and 25.9% (8B). These findings demonstrate that structuring the forecast actions establishes a powerful synergy between language reasoning and temporal prediction, enabling LLMs to reason through verifiable, interpretable, and numerically grounded decisions.
【19】The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation
标题：推理错觉：通过零CoT截断暴露LLC中的规避数据污染
链接：https://arxiv.org/abs/2605.21856
摘要：Large language models (LLMs) have demonstrated impressive reasoning abilities across a wide range of tasks, but data contamination undermines the objective evaluation of these capabilities. This problem is further exacerbated by malicious model publishers who use evasive, or indirect, contamination strategies, such as paraphrasing benchmark data to evade existing detection methods and artificially boost leaderboard performance. Current approaches struggle to reliably detect such stealthy contamination. In this work, we uncover a critical phenomenon: a model's generated reasoning steps actively mask its underlying memorization. Inspired by this, we propose the Zero-CoT Probe (ZCP), a novel black-box detection method that deliberately truncates the entire Chain-of-Thought (CoT) process to expose latent shortcut mappings. To further isolate memorization from the model's intrinsic problem-solving capabilities, ZCP compares the model's zero-CoT performance on the original benchmark against an isomorphically perturbed reference dataset. Furthermore, we introduce Contamination Confidence, a metric that quantifies both the likelihood and severity of contamination, moving beyond simple binary classifications. Extensive experiments on both previously identified contaminated models and specially fine-tuned contaminated models demonstrate that ZCP robustly detects both direct and evasive data contamination. The code for ZCP is accessible at https://github.com/Yifan-Lan/zero-cot-probe.
【20】OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
标题：OPPO：LLM推理中令牌级信用分配的Bayesian值回归
链接：https://arxiv.org/abs/2605.21851
摘要：Reinforcement learning with verifiable rewards has become the standard recipe for improving LLM reasoning, but the dominant algorithm GRPO assigns a single trajectory-level advantage to every token, diluting the signal at pivotal reasoning steps and injecting noise at uninformative ones. Critic-free alternatives derived from on-policy distillation supply per-token signals through oracle-conditioned likelihood ratios, yet apply each signal in isolation from the trajectory-level evidence accumulated up to that position. We propose Oracle-Prompted Policy Optimization (OPPO), which rests on a single observation: the oracle signal used by prior distillation-style methods for local discrimination is also the natural Bayesian update of the model's belief about eventual success. Accumulating the signal along a trajectory yields, in closed form and at the cost of one extra forward pass, a running estimate of the success probability at every position, together with a token-level advantage that requires no learned value network and no additional rollouts. A first-order analysis factorizes the advantage into the per-token discrimination signal used by distillation methods modulated by a state weight that concentrates credit on genuinely pivotal tokens, with a directional variance-reduction guarantee. The framework admits two estimators differing only in which model scores the evidence: a \textit{self-oracle} that reuses the student and recovers the on-policy distillation reward as a strict special case, and a \textit{teacher-oracle} that delegates scoring to a stronger frozen model. On two base LLMs across seven mathematics, science, and code reasoning benchmarks, OPPO improves over GRPO, DAPO, and SDPO by up to $+6.0$ points on AMC'23 and $+5.2$ points on AIME'24, with gains that widen monotonically with response length.
【21】On-Policy Consistency Training Improves LLM Safety with Minimal Capability Degradation
标题：策略一致性训练以最小的能力退化提高LLM安全性
链接：https://arxiv.org/abs/2605.21834
摘要：Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Consistency training is a promising new alignment paradigm to mitigate such failures by training invariants into the model using contrastive input pairs. Existing consistency training procedures generate the supervision signal once, offline, and use supervised fine-tuning (SFT) to update the model. Unfortunately, the resulting models tend to merely memorize the surface forms of the training distribution and thus generalize poorly and regress in their capabilities. We introduce On-Policy Consistency Training (OPCT), a new consistency training approach where the objective is computed over the model's own responses to prompts, supervised by itself conditioned on corresponding contrastive prompts. We evaluate OPCT on three safety axes: sycophancy, jailbreaking, and safety awareness. Across three model families, OPCT outperforms its SFT counterpart on all safety desiderata. It nearly halves the sycophancy rate relative to baseline (8.1% vs. 15.4%, compared to 11.2% for SFT). Under an adaptive per-target attacker, OPCT holds jailbreak defense success near 99% on held-out jailbreak behaviors, whereas SFT achieves 87% on average. On safety awareness, OPCT outperforms SFT in two out of three models, and matches it on the other. OPCT also largely avoids the capability regressions that SFT induces, such as a 28-point drop on MATH-500. Our results suggest that consistency training is best implemented as OPCT rather than as SFT, especially when generalization beyond the training distribution is desired.
【22】HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection
标题：HIDBench：基于主机的入侵检测的大型语言模型基准测试
链接：https://arxiv.org/abs/2605.21773
摘要：Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work, we present a new benchmark to assess LLMs' capabilities in supporting host-based intrusion detection systems (HIDS). This task requires fine-grained reasoning over large-scale, noisy, and highly imbalanced system logs, where complex interactions between benign and malicious activities make reliable detection challenging. Our benchmark unifies three public system log datasets, DARPA-E3, DARPA-E5, and NodLink, and introduces a data construction pipeline that transforms raw host telemetry into LLM-compatible inputs, enabling systematic evaluation under realistic intrusion detection settings. Our evaluation of frontier LLMs reveals substantial performance gaps across datasets. While many models achieve high precision (often above 0.8) on simpler datasets, their performance degrades significantly as system logs become noisier and more complex, with MCC frequently dropping below 0.5 and false positive rates increasing sharply. We further analyze model behavior and identify distinct regimes, including conservative detectors with low false positive rates and over-sensitive models that generate excessive alerts. Overall, our results highlight that while LLMs show strong potential for HIDS, their effectiveness is highly sensitive to data complexity, and robust system design is essential for reliable deployment.
【23】Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
标题：Memory-R2：长期记忆增强LLM代理的公平信用分配
链接：https://arxiv.org/abs/2605.21768
摘要：Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, updating, and reusing information across sessions. However, training such agents with reinforcement learning in multi-session environments is challenging because memory turns the agent's past actions into part of its future environment. Once different rollouts write, update, or delete different memories, they no longer share the same intermediate memory state, making trajectory-level comparisons fundamentally unfair. This violates a key assumption behind group-relative methods such as GRPO, where rollouts are compared as if they were sampled from the same effective environment. Consequently, trajectory-level rewards provide noisy or biased credit signals for long-horizon memory operations. To address this challenge, we introduce Memory-R2, a training framework for long-horizon memory-augmented LLM agents. Its core algorithm, LoGo-GRPO, combines local and global group-relative optimization. The global objective preserves end-to-end learning from long-horizon trajectory-level rewards, while local rerollouts compare different memory-operation outcomes from the same intermediate memory state, yielding fairer group comparisons and more precise supervision for memory construction. Beyond credit assignment, Memory-R2 jointly optimizes memory formation and memory evolution with a shared-parameter co-learning design, where a fact extractor and a memory manager are instantiated from the same LLM backbone through role-specific prompts. To stabilize multi-step RL over long memory horizons, we adopt a progressive curriculum that increases the training horizon from 8 to 16 to 32 sessions. Together, these components provide an effective training paradigm for memory-augmented LLM agents in long-horizon multi-session settings.
【24】Value-Gradient Hypothesis of RL for LLMs
标题：LLM RL的价值梯度假设
链接：https://arxiv.org/abs/2605.21654
摘要：Reinforcement learning substantially improves pretrained language models, but it remains understudied why critic-free methods such as PPO and GRPO work as well as they do, and when they should provide the largest gains. We develop a value-gradient perspective of critic-free RL for LLM post-training. First, under a differentiable rollout and additive-noise parameterization, we show that the actor update is value-gradient-like in expectation: the backward pass propagates costates whose conditional expectation equals the value gradient. Second, for discrete transformer policies, we show that autodifferentiation through attention produces empirical costates that approximate this value signal, with an error controlled by the sampling gap and policy entropy. These results motivate a decomposition of RL impact into value gradient signal and reachable reward headroom, yielding a criterion for when RL should be most effective along a pretraining trajectory.
【25】Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education
标题：探索使用LLM自动评估程序设计教育中学生自我理解的有效性
链接：https://arxiv.org/abs/2605.21614
摘要
：Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with self-explanations, which ask students to explain rather than passively study each problem-solving step. The main challenge of this approach is assessing the correctness of the student's explanations. In the prevailing approach, student explanations are judged by their semantic similarity to an instructor's or domain expert's explanation. Given recent advances in LLM-based automated scoring, it remains unclear whether semantic similarity methods are still the most effective technique to automatically score textual student responses like essays or code explanations. Comparing these methods also requires quality datasets that offer distinctive features such as balanced class distributions and domain-specific labeled data for automated scoring tasks. In this paper, we present a rigorous comparison between LLMs and semantic similarity used for automated scoring, framed as a binary classification task.
【26】AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems
标题：AutoMCU：基于LLM的多智能体系统的可靠性优先MCU神经网络定制
链接：https://arxiv.org/abs/2605.21560
摘要：Deploying neural networks on microcontroller units (MCUs) is critical for edge intelligence but remains challenging due to tight memory, storage, and computation constraints. Existing approaches, such as model compression and hardware-aware neural architecture search (HW-NAS), often depend on proxy metrics, incur high search cost, and do not fully bridge the gap between architecture design and verified deployment. This paper presents AutoMCU, a feasibility-first large language model (LLM)-based multi-agent system for automated neural network customization under MCU constraints. Given natural-language task requirements and hardware specifications, AutoMCU iteratively generates structured architecture candidates, filters infeasible designs through vendor toolchain feedback before training, evaluates feasible models under a controlled protocol, and verifies deployability through backend-grounded deployment analysis. AutoMCU includes two key mechanisms: 1) hardware-in-the-loop architecture generation for early elimination of undeployable candidates under RAM and Flash constraints, and 2) state-isolated multi-agent scheduling for stable coordination of proposal, training, evaluation, and deployment stages. Experiments on CIFAR-10 and CIFAR-100 under strict MCU constraints show that AutoMCU achieves competitive accuracy while reducing customization time to about 1--2 hours, compared with hundreds of GPU hours for representative MCU-oriented HW-NAS baselines. Comparisons with ColabNAS and the LLM-based NAS method GENIUS on NAS-Bench-201 further demonstrate the effectiveness and stability of AutoMCU. Real-device deployments on multiple STM32 microcontrollers validate its practical applicability to MCU-scale edge intelligence.
【27】From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment
标题：从参数到数据：用于高效LLM对齐的任务参数引导微调管道
链接：https://arxiv.org/abs/2605.21558
备注：Accepted@ICML26, 28 pages, 11 figures, 26 tables
摘要：Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selection and parameter-efficient fine-tuning as isolated processes, our empirical analysis suggests they may be intrinsically coupled. We posit the Strong Map Hypothesis: a sparse subset of attention heads plays a dominant role in task-specific adaptation, acting as keys that unlock specific data patterns. Building on this observation, we propose From Parameters to Data (P2D), a unified framework that leverages these task-sensitive attention heads as a dual compass for both sample mining and structural pruning. To rigorously quantify the total pipeline cost, we introduce the Alignment Efficiency Ratio (AER) metric for both selection latency and training time. Mechanistically, P2D identifies critical heads via a lightweight proxy and uses them as a functional filter to curate high-affinity data, establishing a synergistic pipeline. Empirically, by updating merely 10% of attention heads on 10% of the data, P2D achieves an 8.3 pp performance gain over strong baselines and delivers a 7.0x end-to-end time speedup. These results validate that precise parameter-data synchronization eliminates redundancy, offering a new paradigm for efficient alignment.
【28】Provable Joint Decontamination for Benchmarking Multiple Large Language Models
标题：可证明的联合净化，用于对多个大型语言模型进行基准测试
链接：https://arxiv.org/abs/2605.21543
摘要：Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation examples appear in the training data of one or more audited models, reported performance can be inflated and cross-model comparisons become unreliable. A broad line of training-data detection work designs scores to quantify how strongly a model memorizes a given data point, but these score-based methods lack theoretical guarantees. Recent conformal approaches provide provable false-identification control for a single model; however, applying them separately to each model can produce model-specific benchmarks, undermining fair comparison across models. In this work, we formalize multi-model benchmark decontamination as a joint selection problem and propose Joint Envelope Conformal Selection (JECS), a conformal procedure that enables global contamination rate (GCR) control under stated assumptions. Specifically, JECS computes per-model conformal p-values, aggregates them by the per-item maximum, and reconstructs a conservative envelope of the max-p null distribution from right-tail observations above a data-driven threshold. By applying the adaptive Benjamini-Hochberg (BH) procedure to the envelope-rescaled values, we select a benchmark with provable GCR control. Extensive experiments across various models and benchmarks demonstrate that JECS achieves higher power than the max-p baseline while consistently maintaining the target GCR control.
【29】DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
标题：DualOptimm+：弥合共享和去耦合的优化器状态，以在大型语言模型中实现更好的机器去学习
链接：https://arxiv.org/abs/2605.21539
备注：Accepted by ICML 2026
摘要：We propose DualOptim+, a novel optimization framework for improving machine unlearning in large language models. It introduces a base state to capture common representations shared by forgetting and retaining objectives and delta states to preserve objective-specific residuals. This architecture allows the optimizer to adaptively bridge shared and decoupled states based on the directional conflict between forgetting and retaining gradients. We further introduce DualOptim+ 8bit, a quantized variant that reduces memory overhead without compromising performance. Extensive experiments across fictitious and real-world unlearning, safety alignment, and multi-task learning tasks demonstrate that DualOptim+ consistently achieves a superior trade-off between different objectives. Codes are available at https://github.com/CityU-MLO/DualOptimPlus.
【30】Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation
标题：通过比较理念评估预测研究成功的语言教学模型
链接：https://arxiv.org/abs/2605.21491
备注：ACL 2026 Findings
摘要
：As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether LMs can learn to forecast the empirical success of research ideas before any experiments are run. We study comparative empirical forecasting: given a benchmark-specific research goal and two candidate ideas, predict which will achieve better benchmark performance. We construct a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode. While off-the-shelf 8B-parameter models struggle (30% acc.), SFT dramatically boosts performance to 77.1%, outperforming GPT-5 (61.1%). By framing evaluation as a reasoning task via Reinforcement Learning with Verifiable Rewards (RLVR), we train models to discover latent reasoning paths, achieving 71.35% acc. with interpretable justifications. Through additional ablations and out-of-distribution tests, we show robustness to surface-level heuristics and transfer to both a cross-domain time-split test set and an independently constructed test set. Our results demonstrate that compute-efficient small language models can serve as effective, objective verifiers, offering a scalable path for autonomous scientific discovery.
【31】Spectra as Language: Large Language Models for Scalable Stellar Parameter and Abundance Inference
标题：光谱作为语言：可扩展恒星参数和绝对推理的大型语言模型
链接：https://arxiv.org/abs/2605.22162
摘要：Stellar spectra encode key information on the physical properties and chemical compositions of stars. Accurate stellar parameter determination is essential for addressing major questions such as galaxy and stellar evolution. Large-scale spectroscopic surveys have accumulated unprecedented spectral data. Traditional feature extraction or model-fitting approaches struggle with high-dimensional, massive datasets, limited generalization, and computational inefficiency. Recent advances in large language models demonstrate strong generalization and feature-learning in tasks like natural language processing, DNA/RNA sequence analysis, and protein/chemical parsing. Stellar spectra are continuous sequential signals, enabling the transfer of language models to stellar spectroscopy. Here, we propose a two-stage large language model framework for stellar parameter inference, achieving accurate estimation of effective temperature, surface gravity, metallicity, and abundances of ~20 chemical elements. Scaling-law analyses show systematic performance improvements with increasing data, providing a scalable framework for forthcoming large-scale surveys.
Graph相关(图学习|图神经网络|图优化等)(10篇)
【1】Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
标题：深度集成真的能捕捉图神经网络中的不确定性吗？
链接：https://arxiv.org/abs/2605.22593
摘要：
【2】Implicit Regularization of Mini-Batch Training in Graph Neural Networks
标题：图神经网络中小批量训练的隐式正规化
链接：https://arxiv.org/abs/2605.22480
摘要：
【3】Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers
标题：迷失在符号化中：Transformers图符号化的基本权衡
链接：https://arxiv.org/abs/2605.22471
摘要：
【4】Evaluation of Pipelines for Data Integration into Knowledge Graphs
标题：数据集成到知识图的管道评估
链接：https://arxiv.org/abs/2605.22304
摘要：Integrating new data into knowledge graphs (KG) typically involves different tasks that are executed within workflows or pipelines There are many possible pipelines for a specific integration problem but there is not yet a general approach to evaluate the overall quality and performance of such pipelines to be able to determine the best choices. We therefore propose a new benchmark KGI-Bench to evaluate integration pipelines that ingest different kinds of input data into an existing KG. We evaluate pipelines by analyzing their output, i.e., the updated KG, with the three complementary quality metrics coverage, correctness and consistency. We also provide benchmark datasets (seed KG, overlapping input data of three formats, reference KG as a ground truth) for the movie domain. To demonstrate the applicability and usefulness of the proposed benchmark, we comparatively evaluate 12 pipelines and analyze their behavior across different input data formats and design choices.
【5】Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
标题：部分可观察性下知识图的短期到长期记忆迁移
链接：https://arxiv.org/abs/2605.22142
摘要：
【6】CausalGuard: Conformal Inference under Graph Uncertainty
标题：卡索卫士：图不确定性下的保形推理
链接：https://arxiv.org/abs/2605.21928
摘要：Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause under-coverage, while graph-agnostic conformal wrappers may regain nominal coverage only through large padding. We introduce CausalGuard, a structure-weighted conformal framework that calibrates after aggregating graph-conditional doubly robust pseudo-outcomes. Candidate DAGs are proposed from an LLM-derived edge prior, pruned by conditional-independence tests, and reweighted by Bayesian Information Criterion. A composite nonconformity score then calibrates the posterior-weighted pseudo-outcome. CausalGuard provides distribution-free finite-sample marginal coverage for this aggregated pseudo-outcome; under causal identification, overlap, conditional-mean nuisance stability, and concentration on target-aligned valid adjustment strategies, its conditional mean converges to the true Conditional Average Treatment Effect. Across five benchmarks, CausalGuard attains mean coverage above the nominal 90% level for the directly evaluable target and reduces width when graph-agnostic conformal baselines require large padding. Stress tests show that CausalGuard suppresses invalid collider adjustment and remains stable under misspecified priors when the retained candidate set is data-supported.
【7】Neural Acceleration for Graph Partitioning
标题：图形划分的神经加速
链接：https://arxiv.org/abs/2605.21519
摘要
：Graph Partitioning is a critical problem in numerous scientific and engineering domains including social network analysis, VLSI design, and many more. Spectral methods are known to produce quality partitions while minimizing edge cuts for a wide range of problems. However, the computational cost associated with the calculation of the Fiedler vector, an eigenvector associated with the second smallest eigenvalue of the graph Laplacian, remains a significant bottleneck due to memory issues and computational costs. In this paper, we present an accelerated approach to spectral bisection partitioning by replacing the traditional eigenvalue calculation with a simple artificial neural network model to approximate the Fiedler vector. We demonstrate that our approach achieves partitioning quality comparable to spectral bisection while significantly reducing the computational overhead, making it more scalable and efficient for large-scale problems
【8】Community-Aware Vertex Ordering for Reference-Based Graph Compression: A Cross-Encoder Empirical Study
标题：基于参考的图形压缩的社区意识的点排序：交叉编码器实证研究
链接：https://arxiv.org/abs/2605.21510
备注：26 pages, 7 figures, 9 tables. Full reproducibility package at https://github.com/jimbotonic/Adjacently.jl. Preprint; comments welcome
摘要：Reference-based graph compression encodes each vertex's neighbor list relative to a recent vertex, exploiting locality to compress large directed graphs. The dominant tool, WebGraph's BVGraph, fixes a single encoding pipeline and relies on a separately chosen vertex ordering -- typically URL-lexicographic or Layered Label Propagation (LLP). The interaction between ordering and encoder is rarely measured. We propose a two-stage Leiden+LLP vertex ordering -- global LLP to seed labels, Leiden community detection, then per-cluster LLP on each induced subgraph -- and study how it interacts with reference-based compression. On graphs with poor initial vertex order, reordering saves 0.3 to 5.4 bits per edge on every dataset and encoder we measured. The size of that gain is largely insensitive to the encoder: on four of five weakly ordered datasets, four independently parameterised encoders agree on the Leiden+LLP-vs-plain-LLP gain within roughly +/- 0.04 bpe. On URL-ordered web crawls, where the distributed ordering already encodes locality, adaptive encoders still benefit from reordering, but encoders tuned to URL-induced residual structure (BV-HC, CG at K>1) are mildly hurt by it. To quantify how much encoder choice matters once ordering is fixed, we contribute three reference-based encoders -- BG, CS, and CG -- that perform per-vertex cost-optimal selection from up to 28 candidate decompositions. Each is run under its own best-tested ordering. The best of the three improves over BVGraph high-compression by 2-9% on every dataset tested, with the encoder-level gain consistently smaller than the ordering-level gain on weakly ordered datasets. The encoder framework also yields a self-delimiting bitstream that supports low-overhead random access.
【9】A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
标题：A2 QT GN：用于动态链接预测的自适应幅度量子集成时间图网络
链接：https://arxiv.org/abs/2605.21916
备注：9 pages, 3 figures
摘要：Dynamic link prediction is important for modeling evolving interactions in complex systems, including social, communication, financial, and transportation networks. Classical temporal graph models capture sequential dependencies, but they may struggle to represent concurrent and rapidly changing node-edge interactions in large dynamic graphs. We propose A2QTGN (Adaptive Amplitude Quantum-Integrated Temporal Graph Network), a hybrid quantum-classical framework that combines adaptive amplitude encoding with a Temporal Graph Network backbone. The proposed mechanism represents node interaction features as quantum states and selectively refreshes amplitude embeddings based on temporal activity, preserving stable node states while emphasizing meaningful structural changes. This design reduces unnecessary quantum re-encoding and improves temporal representation for link prediction. Experiments on five Temporal Graph Benchmark datasets show that A2QTGN achieves strong predictive and ranking performance across diverse dynamic graphs. Ablation studies confirm the importance of both the quantum embedding module and the adaptive update strategy, while hardware-aware inference using a noisy backend and limited real-device execution supports the feasibility of near-term quantum-assisted temporal graph learning.
【10】Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks
标题：图神经网络解释揭示了生物网络中与疾病相关的枢纽的布局特征
链接：https://arxiv.org/abs/2605.21502
备注：25 pages (excluding supplement), 7 figures, 7 supplementary tables
摘要：Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering meaningful molecular mechanisms remains unclear. Here, we systematically evaluate four widely used approaches: Saliency Attribution (SA), Integrated Gradients (IG), GNNExplainer, and Layer-wise Relevance Propagation (LRP) for identifying disease-relevant structure in breast cancer RNA-seq data projected onto a protein-protein interaction network. Using synthetic benchmarks with known ground-truth motifs, we show that explanation methods recover distinct signal organizations: SA performs best for sparse single-node drivers, whereas IG and LRP preferentially recover distributed pathway-like and cascade-like signals. In TCGA BRCA data, we identify a consistent topological signature of disease-associated hubs in which attribution peaks in the immediate 1-hop neighborhood and decays across successive network shells, a pattern most pronounced for IG and LRP and associated with strong enrichment of known cancer hubs. We further observe a trade-off between local hub enrichment and global gene ranking performance, with IG optimizing local enrichment and SA achieving superior global discrimination. Motivated by these complementary behaviors, we introduce a framework combining a shell-based hub score with consensus ranking across explainers. Consensus scores improve prioritization of canonical cancer genes (TP53, BRCA1, ESR1, MYC), reduce dependence on node degree, and, especially when tuned, outperform individual methods. Pathway enrichment further reveals improved recovery of biologically coherent cancer programs, including ERBB2, RTK, MAPK, immune, and cytokine signaling. Together, these results demonstrate that topology-aware integration of graph explanations can improve biological interpretability and biologically relevant molecular recovery.
Transformer(8篇)
【1】Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
标题：代表未计算：Transformer中候选心律失常中间体的因果检验
链接：https://arxiv.org/abs/2605.22488
备注：16 pages, 4 figures
摘要：
【2】Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference
标题：混合Mamba-Transformer推理的非对称虚拟内存翻页
链接：https://arxiv.org/abs/2605.22416
备注：11 pages, 8 figures, 6 tables. Code and reproducibility artifacts at https://github.com/codepawl/cachepawl
摘要
：Hybrid language models like Jamba mix attention layers with State Space Models (SSMs), creating two memory cache types with opposite profiles: Key-Value (KV) caches grow linearly with sequence length, while SSM states stay fixed per layer. Current inference engines handle this poorly. Unified pools pad SSM states to attention page sizes, wasting up to 7.3x capacity. Static dual pools cannot adapt when prompt distributions shift between requests. We present Asymmetric Virtual Memory Paging (AVMP). The allocator separates the two cache types into physically distinct pools behind a unified virtual address space, and migrates capacity between pools when one runs out. Migration triggers only on allocation failure, keeping behavior deterministic. We evaluate AVMP across 270 synthetic cells plus 60 cells of ShareGPT trace replay on an RTX 3060 12GB. Out-of-Memory events drop 7.6% and request throughput improves 1.83x to 13.3x across synthetic workloads and 2.36x on ShareGPT. All gains hold under paired-bootstrap 95% confidence intervals. A phase-time breakdown reveals two distinct mechanisms: shorter OOM recovery on capacity-pressured workloads, and faster allocation calls on KV-heavy workloads. Implementation is pure Python; Triton integration is future work.
【3】How Many Different Outputs Can a Transformer Generate?
标题：一个Transformer可以产生多少种不同的输出？
链接：https://arxiv.org/abs/2605.22223
备注：ICML 2026 Spotlight
摘要：We study how we can leverage only a handful of characteristics of a transformer's architecture to closely predict the number of different sequences it can output, both qualitatively and quantitatively. We provide an upper bound depending on the length of the prompt, which we show empirically to be tight up to a factor less than 10, across architectures and model sizes. Our analysis also provides a theoretical explanation for previously observed empirical failures of transformers on simple sequence tasks, such as copying and cramming. Formally, we prove that (i) the maximal length of accessible sequences (those that the transformer can output for some prompt) grows linearly with the prompt length, (ii) beyond a critical threshold, the proportion of accessible sequences decays exponentially with sequence length, and (iii) the linear coefficient relating prompt length to accessible sequence length admits a theoretical upper bound. Notably, these results hold even with unbounded context and computation time.
【4】Can Transformers Learn to Verify During Backtracking Search?
标题：Transformer可以在回溯搜索期间学习验证吗？
链接：https://arxiv.org/abs/2605.22221
摘要：Backtracking search underlies classical constraint solvers, planners, and theorem provers. Recent transformer-based reasoning systems explore search trees over their own intermediate steps. A common training recipe fits an autoregressive next-token loss on offline solver traces. The model's input at each step is a cumulative trace of all prior decisions. The optimal continue-or-backtrack predictor depends only on the current search state, since two trajectories reaching the same state admit the same viable continuations. We show that decoder-only transformers trained on cumulative traces fail this requirement in two ways: the trace can scatter state features across many positions (scattered retrieval), and the predictor can condition on the trajectory rather than the state (history entanglement). We address scattered retrieval with localization, a trace-level fix that rewrites each decision block to expose state features locally. We address history entanglement with Selective State Attention (SSA), a fixed attention mask that enforces state-based decisions structurally without modifying training data, objective, or parameters. We focus on reactive verification, after propagation has exposed a contradiction. We test SSA on 3-SAT, graph coloring, Blocks World, and backtracking parsing. On same-state pairs that differ only in prior history, SSA emits identical decisions while a cumulative-trained causal baseline does not. Our contribution is a diagnostic of transformer behavior on serialized trajectory data, paired with a structural fix. Pretrained language models that search over their own reasoning steps may face the same failure. Our analysis opens up inference-time context clearing as a candidate way to apply the same isolation without retraining.
【5】From TF-IDF to Transformers: A Comparative and Ensemble Approach to Sentiment Classification
标题：从TF-IDF到Transformer：情感分类的比较和整体方法
链接：https://arxiv.org/abs/2605.22003
备注：6 pages, 9 figures. This is the author's accepted manuscript, presented at the International Conference on Intelligent Computing, Networks and Security (IC-ICNS 2026), March 26-28, Bhubaneswar, India. Proceedings publication pending
摘要：Sentiment analysis, also referred to as opinion mining, primarily tries to extract opinion from any text-based data. In the context of movie reviews and critics, sentimental analysis can be a helpful tool to predict whether a movie review is generally positive or negative. It can be difficult for the ML models to understand the context or metaphysical sentiment accurately, as ML models rely largely on statistical word representations. The objective of this paper is to examine and categorise movie reviews into positive and negative sentiments. Diverse machine learning models are considered in doing so, and Natural Language Processing (NLP) methodologies are employed for data preprocessing and model assessment. The IMDb dataset is used. Specifically, Naive Bayes, Logistic Regression, Support Vector Machines (SVM), LightGBM, LSTM, and transformer-based models such as RoBERTa and DistilBERT were evaluated. After a lot of testing with accuracy, precision, recall, F1-score, and ROC-AUC, RoBERTa performed better than all the other models, with an accuracy of 93.02%. A soft voting ensemble that combined all the models also improved classification performance, showing that model ensembling works well for sentiment analysis.
【6】Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention
标题：能量门控注意力：光谱显着性作为Transformer注意力的感应偏差
链接：https://arxiv.org/abs/2605.21842
备注：12 pages, 4 figures
摘要：Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intrinsic informational content. In turbulent fluid dynamics, coherent structures -- the energetically dominant, spatially organized patterns that persist amid background chaos -- carry a disproportionate fraction of total energy and govern all transport. We propose that tokens play an analogous role in transformer attention: informationally dense positions (morphological boundaries, syntactic heads, discourse markers) concentrate spectral energy and should attract proportionally more attention than background tokens (function words, repeated patterns, low-information filler). We propose Energy-Gated Attention (EGA): a simple modification that gates value aggregation by the spectral energy of key token embeddings, computed by a single learned linear projection that discovers the dominant spectral mode of the embedding field. On TinyShakespeare, EGA achieves +0.103 validation loss improvement with only 12,480 additional parameters (<0.26% overhead) and no measurable computational cost. The result is consistent on Penn Treebank (+0.101), demonstrating dataset independence. A systematic ablation across three wavelet families (fixed Morlet, Daubechies db2/db4, and a parametric Morlet) establishes that fixed structured bases are suboptimal -- the optimal energy direction is data-adaptive and non-sinusoidal -- while identifying learned wavelet packets as a promising open direction. The learned energy threshold converges to tau ~= 0.35 independently of initialization, corresponding to the fraction (~36%) of tokens carrying above-average spectral energy in English text, a stable linguistic property consistent with the fraction of content words in running English text.
【7】$\textit{BlockFormer}$ : Transformer-based inference from interaction maps
标题：$ extit{BlockFormer}$：从交互地图中基于转换器的推断
链接：https://arxiv.org/abs/2605.21617
摘要：Inference from interaction maps, such as centromere identification from genome-wide chromosome conformation capture techniques -- notably Hi-C -- can be formulated as a generic inverse problem: infer a set of parameters given a map summarizing pairwise interactions between entities through blocks of variable numbers and sizes. In this work, we introduce a data-driven approach that leverages shared structure between these maps, such as global alignment between localized patterns, while handling the variability in number and size of entities arising in real-world data. Our approach relies on a transformer architecture capable of handling such variability and a custom simulator to generate abundant, yet computationally cheap synthetic data for training. Applied to the problem of centromere localization, the method accurately recovers their genomic positions across a wide range of species of various genome sizes.
【8】Temporal Contrastive Transformer for Financial Crime Detection: Self-Supervised Sequence Embeddings via Predictive Contrastive Coding
标题：金融犯罪检测的时间对比Transformer：通过预测对比编码嵌入自我监督序列
链接：https://arxiv.org/abs/2605.21490
备注：10 pages, 4 figures, one table
摘要：We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive objective to produce embeddings that encode behavioral patterns over time, with the goal of supporting downstream fraud detection tasks. We evaluate TCT in a realistic setting by using the learned embeddings as input features to a gradient boosting classifier. Experimental results show that embeddings alone achieve meaningful predictive performance (AUC 0.8644), indicating that the model captures non-trivial temporal structure. However, when combined with domain-engineered features, no measurable improvement is observed over the baseline (AUC 0.9205 vs. 0.9245), suggesting that the learned representations largely overlap with existing feature abstractions. These findings position TCT as a promising representation learning approach that captures relevant behavioral signal, while highlighting the challenges of achieving additive value over strong domain features. The results reflect an intermediate stage in the development of temporal representation learning for financial crime detection and motivate further research on model architecture, training objectives, and integration strategies. At this early stage, achieving performance comparable to a strong feature-engineered baseline is itself a meaningful outcome, indicating that learned representations approximate domain-specific features without manual engineering. While not yet production-ready, these results point to a promising direction for reducing reliance on feature engineering in financial crime detection.
GAN|对抗|攻击|生成相关(17篇)
【1】SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation
标题：SeqLoRA：用于连续多概念生成的二层垂直自适应
链接：https://arxiv.org/abs/2605.22743
摘要：
【2】The Distillation Game: Adaptive Attacks & Efficient Defenses
标题：蒸馏游戏：自适应攻击和有效防御
链接：https://arxiv.org/abs/2605.22737
摘要：
【3】ChronoVAE-HOPE: Beyond Attention -- A Next-Generation VAE Foundation Model for Specialized Time Series Classification
标题：ChronoVAE-HOPE：超越关注--用于专业时间序列分类的下一代VAE基础模型
链接：https://arxiv.org/abs/2605.22684
摘要：
【4】From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder
标题：从基线到后续：英国生物库中使用因果分层变分自动编码器的反事实脊柱DXA图像合成
链接：https://arxiv.org/abs/2605.22649
备注：7 pages, 4 figures, 3 tables. Accepted at the 48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2026)
摘要：
【5】The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
标题：多任务放射学报告生成中的双重困境：梯度动力学分析与解决方案
链接：https://arxiv.org/abs/2605.22635
备注：Accepted by ICML 2026
摘要：
【6】UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection
标题：UAD+：用于未知网络攻击检测的可解释混合框架
链接：https://arxiv.org/abs/2605.22621
摘要：
【7】When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
标题：当更强触发适得其反：后门攻击的多维理论
链接：https://arxiv.org/abs/2605.22481
摘要：
【8】Boundary-targeted Membership Inference Attacks on Safety Classifiers
标题：针对安全分类器的边界目标成员推断攻击
链接：https://arxiv.org/abs/2605.22373
摘要
：Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive datasets including discussions of self-harm and mental health, raising important, yet poorly understood, privacy concerns. Membership inference attacks (MIAs) allow adversaries to infer membership of examples used to train models. In this work, we hypothesize that identifying the examples on which the classifier is least confident are informative for an adversary to infer membership. This reflects a localized failure of generalization, where the model relies on memorization to resolve ambiguity in the training set. To investigate this, we introduce a new boundary-targeted selection strategy that identifies low confidence examples that amplify the signal of an examples membership within a training set. Our experimental results show that an adversary can recover 19\% of the conversations a safety classifier flagged as indicating user distress, at a 5\% false-positive rate, on a classifier fine-tuned for detecting a user who may require emotional support. This is $3.5$ times more than attacking using state-of-the-art MIA methods alone. Finally, we characterize the boundary laying examples and show that content-based filtering is ineffective for protection, and existing noise strategies can effectively mitigate susceptibility of these examples.
【9】VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation
标题：VeriScale：用于可验证代码生成的对抗性测试套件扩展
链接：https://arxiv.org/abs/2605.22368
摘要：As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to construct diverse and challenging test cases, and test-suite reduction to distill them into compact yet discriminative suites. While VeriScale is general, we instantiate it on Verina to construct VerinaPlus, which expands the original test suites by over 83$\times$, and VerinaLite, a lightweight 14$\times$ variant. Our experiments across eight state-of-the-art LLMs demonstrate that VerinaPlus exposes substantial model weaknesses hidden by the original benchmark, evidenced by sharp score drops on both SpecGen and CodeGen tasks, whereas VerinaLite maintains this discriminative power at a fraction of the evaluation cost. The enhanced benchmarks and source code are publicly available at https://github.com/XiaoyangLiu-sjtu/VeriScale.
【10】TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation
标题：TransitLM：无地图交通路线生成的大规模数据集和基准
链接：https://arxiv.org/abs/2605.22355
摘要：Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports training models to bypass this dependency. We present TransitLM, a large-scale dataset of over 13 million transit route planning records from four Chinese cities covering 120,845 stations and 13,666 lines, released as a continual pre-training corpus and benchmark data for three evaluation tasks with complementary metrics. Experiments show that an LLM trained on TransitLM produces structurally valid routes at high accuracy and implicitly grounds arbitrary GPS coordinates to appropriate stations without any explicit mapping. These results demonstrate that transit route planning can be learned entirely from data, enabling end-to-end, map-free route generation directly from origin-destination information. The dataset and benchmark are available at https://huggingface.co/datasets/GD-ML/TransitLM, with evaluation code at https://github.com/HotTricker/TransitLM.
【11】Toward Understanding Adversarial Distillation: Why Robust Teachers Fail
标题：走向理解对抗蒸馏：为什么强大的教师失败
链接：https://arxiv.org/abs/2605.21999
备注：Accepted to ICML 2026. Code is available at https://github.com/HongsinLee/why-robust-teachers-fail
摘要：Adversarial Distillation aims to enhance student robustness by guiding the student with a robust teacher's soft labels within the min-max adversarial training framework, yet its success is notoriously inconsistent: a more robust teacher often fails to improve, or even harms, the student's robust generalization. In this paper, we identify a key mechanism of this teacher dependency: the misalignment between the teacher's supervisory confidence and the student's representational limitations on a consistent subset of training data -- the Robustly Unlearnable Set. We present a theoretical framework analyzing the feature learning dynamics of a two-layer neural network, demonstrating that this mismatch creates a dichotomy in distillation outcomes. We prove that when a teacher provides confident supervision on unlearnable samples, it compels the student to memorize spurious noise patterns that eventually overpower the learned robust signal, thereby driving robust overfitting. Conversely, a teacher that exhibits high uncertainty on these samples effectively suppresses noise memorization, allowing the student to rely solely on the learnable signal for robust generalization. We empirically validate our theory across both synthetic simulations and real-image classification datasets, confirming that robust overfitting is driven by the teacher's interaction with unlearnable samples. Finally, we demonstrate that a teacher's predictive entropy on unlearnable samples serves as a strong indicator of student robustness, validating our theoretical framework and offering a principled guideline for robust teacher selection.
【12】SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization
标题：SCI防御：防御生成引擎优化的操纵攻击
链接：https://arxiv.org/abs/2605.21948
备注：20 pages, NeurIPS 2026 submission
摘要：LLM-based ranking systems are vulnerable to Generative Engine Optimization (GEO) attacks, where adversaries inject semantic signals into product descriptions to artificially boost rankings. We propose SCI-Defense, a three-component defense framework combining Perplexity detection (PPL), Semantic Integrity Scoring (SIS), and Inter-Candidate Detection (ICD). SIS evaluates four manipulation dimensions: Authority Attribution (AA), Narrative Purposiveness (NP), Comparative Claims (CA), and Temporal Claims (TC). Evaluated on 600 Amazon product descriptions across 6 categories, SCI-Defense achieves Precision=1.000 and FPR=0.000, with Recall of 1.000, 0.952, and 0.830 against String, Reasoning, and Review attacks respectively. On 600 MS MARCO web passages, String attacks are blocked with perfect recall while Review attacks yield near-zero recall, as web passages lack the persuasion-oriented signals that SIS targets in product descriptions. We demonstrate that existing defenses -- PPL-only filters, SafetyClf content classifiers, and paraphrasing -- achieve zero recall against semantic manipulation attacks. We further demonstrate new attacks such as Specification Amplification and Use-Case Saturation can expose semantic relevance manipulation as a structural defense blind spot that suggests directions for future research.
【13】CCLab: Adversarial Testing of Learning- and Non-Learning-Based Congestion Controllers
标题：CCCab：基于学习和非学习的拥堵控制器的对抗测试
链接：https://arxiv.org/abs/2605.21915
备注：13 pages for main paper, 16 pages in total
摘要
：Congestion controllers (CCs) are critical to network performance, and yet their robustness under adverse conditions remains insufficiently understood. While recent learning-based CCs have demonstrated strong performance in controlled environments, it is unclear how they compare to traditional CCs when controllers' input signals are corrupted or when environmental conditions become systematically challenging. In this paper, we introduce CCLab, an adversarial testing framework for systematically evaluating the robustness of both learning-based and non-learning-based CCs. CCLab includes a reinforcement learning (RL)-based adversarial agent that operates in a closed loop with the congestion control policy, generating bounded perturbations either on input signals (feature-level) or on external network conditions (environment-level), while preserving realism through explicit constraints. Using this framework, we compare learning-based CCs with non-learning-based CCs under both feature-level and environment-level adversarial conditions. While both types of CCs suffer from performance degradation under adversarial testing, we find that learning-based CCs, in general, are more robust than traditional human-designed algorithms. Finally, we show that our adversarial traces can be used to train more robust CCs that outperform existing learning-based CCs under both challenging and normal conditions.
【14】Engineering Hybrid Physics-Informed Neural Networks for Next-Generation Electricity Systems: A State-of-the-Art Review
标题：下一代电力系统的混合物理信息神经网络工程：最先进的评论
链接：https://arxiv.org/abs/2605.21903
备注：59 pages, 6 Figures
摘要：The integration of machine learning with domain-specific physics is transforming the design, monitoring, and control of electricity systems, where data scarcity, limited interpretability, and the need to enforce physical laws constrain purely data-driven models. Physics-informed machine learning (PIML) addresses these limitations by embedding governing equations directly into the learning process, yielding accurate, efficient, and scalable solutions for Industry 4.0 applications. This article reviews hybrid PIML architectures for electricity systems, including physics-informed neural networks (PINNs), Deep Operator Networks (DeepONets), Fourier Neural Operators, Extreme Learning Machine-enhanced PINNs, graph-based PINNs (PIGNNs), and domain-decomposition PINNs. Each approach is examined through case studies spanning field analysis, fault detection, digital twins, surrogate modeling, and control optimization. The review shows that embedding Maxwell's equations and other first-principles constraints substantially improves predictive accuracy under sparse and noisy data, reduces simulation time by orders of magnitude relative to finite element methods, and enhances generalization across operating regimes. Hybrid frameworks consistently outperform purely data-driven baselines on parameter sensitivity, dynamic behavior, and robustness, while supporting real-time digital-twin calibration and uncertainty quantification. Persistent challenges include training instability for stiff multi-scale problems, computational cost of high-fidelity models, and the absence of standardized benchmarks. The findings demonstrate that PIML enables a paradigm shift from black-box data-driven methods to transparent, physics-informed strategies, positioning the field for sustained innovation in resilient and intelligent electricity systems.
【15】Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
标题：通过差异隐私的二元视角证明针对后门攻击的鲁棒性
链接：https://arxiv.org/abs/2605.21780
摘要：Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor attacks, where training and test data are jointly perturbed, remains challenging because training- and test-time randomized mechanisms must be analyzed within a single robustness certificate. We address this by connecting randomized smoothing to the dual view of differential privacy through privacy profiles, which provide a numerical procedure for composing heterogeneous mechanisms. The resulting framework enables tight, modular, end-to-end certification of complex, composed mechanisms while leveraging existing analyses of differentially private mechanisms. We instantiate the framework for DP-SGD and Deep Partition Aggregation with inference-time smoothing, deriving joint robustness guarantees against both training-time and inference-time attacks. Experiments on MNIST and CIFAR-10 demonstrate the effectiveness of our framework. Overall, we provide a principled and general framework for using composite mechanisms to certify robustness under complex threat models that better capture the capabilities of real-world adversaries.
【16】UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation
标题：UniVl：统一的视觉语言嵌入，用于空间背景图像生成
链接：https://arxiv.org/abs/2605.21611
摘要：We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of supplying a reference image and a global text prompt through two separate encoders, one for vision and one for language, UniVL is trained to bind semantics to spatial locations directly from a single unified visual input, where the textual instruction is rendered onto the spatial mask. This removes the need for a standalone text encoder at inference time. The resulting model supports contextual image generation by following user-specified instructions about what should appear where, while substantially reducing computation. To address this task, we propose a framework in which the UniVL encoder, adapted from an optical-character-recognition-pretrained backbone, reads the unified condition optically and produces a UniVL embedding, fVIL, that fuses visual and semantic intent with spatial locations in a single token sequence. A two-stage pipeline first aligns UniVL with the VAE embedding space and then conditions a pretrained diffusion backbone entirely on UniVL embeddings, eliminating the standalone text encoder, such as T5. Although this reframing uses a deliberately minimal text interface, it yields strong empirical gains. On UniVL-ImgGen, a benchmark of 477K mask-annotated images that we construct for training and evaluation, UniVL improves image quality over text-prompted baselines, reducing FID from 14 to 11 and increasing PSNR from 16 to 20. It also eliminates the text encoder entirely, reducing inference TFLOPs by up to 52% and runtime by up to 44%. Additional ablation studies validate the contributions of the proposed components, paving the way for efficient, spatially grounded image generation with a unified conditioning paradigm.
【17】Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
标题：针对闭源MLLM的可转移攻击的频域正规化对抗对齐
链接：https://arxiv.org/abs/2605.21541
摘要
：Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models, such that perturbations align with transferable semantic cues rather than surrogate-specific behaviors. However, existing methods suffer from spatial-domain feature redundancy and surrogate-specific gradient signals, thereby hindering cross-model transferability. In this paper, we propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective. For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus. For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a \textit{model-agnostic} low-pass regularizer that modulates the surrogate gradient using only the geometric frequency coordinate, \textit{i.e.}, no surrogate-derived statistic is involved, so that FGR is model-agnostic by construction, removing surrogate-specific high-frequency artifacts while preserving transferable low-frequency directions. Together, the two components form a unified frequency-domain treatment of transferability. Extensive experiments on $15$ flagship MLLMs across $7$ vendors show that FRA-Attack achieves superior cross-model transferability, particularly with state-of-the-art performance on GPT-5.4, Claude-Opus-4.6 and Gemini-3-flash.
半/弱/无/有监督|不确定性|主动学习(9篇)
【1】Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
标题：证据深度学习的插件损失：包括Softmax分类器的不确定性估计简化框架
链接：https://arxiv.org/abs/2605.22746
摘要：
【2】Ternary Decision Trees with Locally-Adaptive Uncertainty Zones
标题：具有局部自适应不确定区的三元决策树
链接：https://arxiv.org/abs/2605.22740
备注：15 pages, 4 figures, 5 appendix sections. Submitted to Data Mining and Knowledge Discovery (DAMI)
摘要：
【3】A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting
标题：风电预测中认识性和先验性不确定性的后预测方差分解
链接：https://arxiv.org/abs/2605.22390
摘要：Accurate wind power forecasting requires reliable uncertainty quantification, yet most existing methods report a single predictive uncertainty that conflates epistemic and aleatoric sources. This paper applies the law of total variance to the joint setting of heteroscedastic neural network regression and Bayesian posterior approximation, deriving an explicit decomposition of total uncertainty (TU) into aleatoric (AU) and epistemic (EU) components. The resulting estimators are compatible with standard posterior-approximation methods and with $β$-NLL training to regulate the mean--variance learning trade-off. A wind power--specific evaluation framework is proposed to validate disentanglement without access to ground-truth uncertainty labels, comprising three modules: controlled synthetic experiments to verify responses to heteroscedastic noise and distribution shift; data-property--driven validation on a real-world wind turbine SCADA dataset; and dataset-size scaling experiments to examine the predicted asymptotic behavior of EU. Across synthetic and real-world experiments, the decomposed AU and EU components respond in theoretically consistent directions to noise structure, distributional shift, and training-scale variation, supporting the theoretical consistency and operational utility of the proposed decomposition and evaluation protocol.
【4】Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization
标题：为什么语义熵失败：几何感知和校准政策优化的不确定性
链接：https://arxiv.org/abs/2605.21801
摘要：Post-training has become central to improving reasoning and alignment in large language models, where critic-free models enable scalable learning from model-generated outputs but lack principled mechanisms to distinguish informative from noisy signals. Recent approaches leverage response-level measures as uncertainty signals to regulate group-based optimization methods such as GRPO. Yet their empirical success remains unstable and unclear in how they influence optimization dynamics. In this paper, we provide, to our knowledge, the first principled formulation that interprets uncertainty signals as mechanisms for characterizing and regulating gradient variance and learning signal quality. Based on both empirical and theoretical analysis, we identify two critical gaps of current entropy-based estimators: The anisotropic gap and The calibration gap. Motivated by this analysis, we propose Geometric-aware Calibrated Policy Optimization (GCPO), a novel framework integrating geometry-aware measures to capture semantic disagreement with reward-based calibration to align uncertainty with learning signal strength. Experiments on multiple benchmarks show that our approach more faithfully tracks gradient variability and consistently improves post-training performance. Our results highlight the importance of designing uncertainty signals that are aligned with optimization dynamics, offering a principled perspective for robust post-training.
【5】MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
标题：MMD-Balls作为Credal集：测试时间适应中认识不确定性的PAC-Bayesian框架
链接：https://arxiv.org/abs/2605.21783
备注：15 pages, 0 figures. Accepted at the 2nd Workshop on Epistemic Intelligence in Machine Learning (EIML@ICML 2026)
摘要：Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to prediction reliability. We develop a PAC-Bayesian framework yielding generalization bounds explicitly parameterized by the maximum mean discrepancy (MMD) between source and target distributions. Our principal contribution is interpreting MMD-balls around the source distribution as credal sets in Walley's imprecise probability theory, yielding natural epistemic uncertainty quantification. We establish: (i) a PAC-Bayesian bound with an MMD-dependent shift penalty under an RKHS-Lipschitz loss assumption; (ii) a finite-sample version via MMD concentration; (iii) a uniform worst-case risk bound over all distributions in the credal set, with a lower-upper risk decomposition; and (iv) geodesic preservation bounds explaining why kernel-guided adaptation protects local feature geometry. The credal set interpretation separates epistemic from aleatoric uncertainty and provides a principled decision criterion for when adaptation is warranted.
【6】Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study
标题：CPD风险预测中的校准、不确定性沟通和部署准备：框架评估研究
链接：https://arxiv.org/abs/2605.21566
备注：27 pages, 6 figures, 4 tables. Supplementary materials (S1-S4) included as ancillary file
摘要
：Machine learning models for chronic kidney disease (CKD) risk prediction often post strong discrimination scores on internal test sets. Calibration and uncertainty quantification get far less attention, leaving clinicians without reliable information about whether the probability outputs are accurate. We trained five classifiers on the UCI CKD dataset (400 patients, 62.5% CKD prevalence): logistic regression, random forest, XGBoost, SVM with Platt scaling, and Gaussian naive Bayes. We evaluated each across calibration quality, conformal prediction coverage, and an eight-criterion deployment readiness framework. A distributional stress-test applied the best-calibrated variant of each model to the open-access MIMIC-IV demo cohort (97 patients, 23.7% CKD) to assess behaviour under prevalence shift and feature missingness. We measured calibration before and after Platt scaling and isotonic regression using Expected Calibration Error and Brier Score, and quantified uncertainty through split conformal prediction targeting 90% marginal coverage. All five models reached AUROC 1.00 on the UCI test set. Isotonic recalibration reduced internal ECE to 0.000-0.022. On MIMIC-IV, AUROC fell to 0.48-0.58, ECE rose to 0.68-0.76, and conformal coverage dropped from 0.80-0.98 to 0.21-0.25 against a 90% target. No model scored above 4 out of 16 on the deployment readiness checklist. Near-perfect internal performance did not transfer. Calibration stability and conformal coverage should be evaluated on external data before any clinical prediction model moves toward deployment.
【7】Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition
标题：利用自我调整的课程学习增强多模式对话情感识别中的模式平衡
链接：https://arxiv.org/abs/2605.21565
备注：Accepted at Neural Computing and Applications (Springer), 2026
摘要：Multimodal Emotion Recognition in Conversations (MERC) is a crucial task for understanding human interactions, where multimodal approaches integrating language, facial expressions, and vocal tone have achieved significant progress. However, modality misalignment and imbalanced learning remain major challenges, limiting the effective utilization of multimodal information. To address this issue, we propose a plug-and-play framework based on Self-Paced Curriculum Learning (SPCL) for MERC. We introduce a dual-level Difficulty Measurer that captures both utterance-level and conversation-level challenges. The utterance-level score models fine-grained modality-specific difficulty, while the conversation-level score captures broader dialogue structures, including emotional dependencies and modality coherence. Based on these scores, the Learning Scheduler dynamically guides training from easier to more difficult instances. By integrating SPCL into existing MERC architectures, our method alleviates modality imbalance and improves model robustness. Extensive experiments on the IEMOCAP and MELD datasets demonstrate consistent improvements across different architectures and modality settings. On IEMOCAP, SPCL improves weighted F1-score by approximately +1.2% to +6.6% over baseline models, while on MELD, gains reach up to +10.4%. These results highlight the effectiveness and generalizability of SPCL as a lightweight plug-and-play module for multimodal emotion recognition.
【8】Objective-Induced Bias and Search Dynamics in Multiobjective Unsupervised Feature Selection
标题：多目标无监督特征选择中的搜索诱导偏差和搜索动力学
链接：https://arxiv.org/abs/2605.21561
摘要：Unsupervised feature selection is commonly formulated as a multiobjective optimisation problem that jointly optimises subset quality and subset size. Yet the behaviour of this formulation depends critically on the choice of evaluation objective, the direction of subset-size regularisation, and the initialisation strategy. We study these factors in a controlled setting using a synthetic dataset with known informative, redundant, and irrelevant feature types. Six formulations are compared by combining three evaluation objectives: accuracy, silhouette score, and PCA reconstruction loss with subset-size minimisation or maximisation. The results show that formulation strongly affects both search dynamics and the quality of the resulting Pareto front. Silhouette-based formulations exhibit a strong bias toward trivial low-cardinality solutions and remain weak proxies for predictive performance. In contrast, the proposed PCA loss objective produces compact subsets with test accuracy comparable to subsets obtained by directly optimising supervised accuracy. Overall, the study shows that objective design is central to effective multiobjective unsupervised feature selection.
【9】Self-Supervised ConvLSTM for Fermi Large Area Telescope Transient Detection
标题：用于费米大面积望远镜瞬态探测的自监督ConvLSTM
链接：https://arxiv.org/abs/2605.22112
备注：17 pages, 5 figures. Accepted for publication in Astronomy and Computing. Author-accepted manuscript version
摘要：We present a framework for detecting transient gamma-ray phenomena in a controlled environment by combining end-to-end simulations of the Fermi-LAT sky with self-supervised spatio-temporal deep learning. We generate a ten-year synthetic Universe with gtobssim and process the simulated events into daily all-sky maps of counts and exposure, obtaining a time-ordered sequence that mirrors the structure of Fermi-LAT observations. To model the nominal evolution of the sky, we employ a Convolutional Long Short-Term Memory (ConvLSTM) network that operates directly on map sequences, preserving spatial locality while learning temporal dependencies. The model is trained to reconstruct expected emission, and departures from the learned baseline are quantified through pixel-wise mean-squared residual maps. We then define statistically motivated anomaly criteria by estimating per-pixel thresholds from the residual distribution on the training set, and we enforce spatial coherence via local filtering to suppress isolated fluctuations. The ConvLSTM is then deployed as trained predictor on Fermi-LAT daily maps, where the sky can depart from the nominal behavior because of genuine astrophysical variability and instrumental non-stationarities. The resulting pipeline flags localized, time-dependent excesses consistent with high-variable sources or transient events (e.g., flares or GRBs) and provides a benchmark for evaluating anomaly-detection strategies on long-duration, Fermi-LAT-like datasets.
迁移|Zero/Few/One-Shot|自适应(10篇)
【1】CogAdapt: Transferring Clinical ECG Foundation Models to Wearable Cognitive Load Assessment via Lead Adaptation
标题：CogAdapt：通过铅自适应将临床心电图基础模型转移到可穿戴认知负荷评估
链接：https://arxiv.org/abs/2605.22774
备注：7 pages, 7 figures. Submitted to IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2026)
摘要：
【2】MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
标题：MoSA：运动约束压力自适应，通过学习剩余各向异性来缓解连续体动力学中的真实与模拟差距
链接：https://arxiv.org/abs/2605.22597
摘要：
【3】ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation
标题：隐含地形V2：子波引导的空间自适应神经地形表示
链接：https://arxiv.org/abs/2605.22556
备注：14 pages, 8 figures
摘要：
【4】Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations
标题：有噪观测下学习核化支持者的自适应测量分配
链接：https://arxiv.org/abs/2605.22275
备注：20 pages, 9 figures
摘要
：Kernel methods are typically formulated under the assumption of exact, noise-free access to the Gram matrix. However, in emerging settings such as quantum machine learning, each kernel entry must be inferred from noisy observations, and its accuracy depends on how a limited measurement budget is allocated. Despite this, existing approaches overwhelmingly rely on uniform allocation, which equalizes estimator variance but ignores the highly non-uniform dependence of kernelized classifiers on the Gram matrix. In this work, we introduce an adaptive measurement-allocation strategy for learning kernelized Support Vector Machines (SVMs) from noisy Bernoulli observations. Our approach combines two complementary principles: (i) geometric sensitivity, capturing how perturbations of individual kernel entries affect the classifier margin, and (ii) active-set instability, quantifying the probability of discrete changes in support-vector membership induced by measurement noise. These signals define a task-aware allocation scheme that concentrates measurements on the most decision-critical regions of the kernel matrix. We provide a theoretical analysis showing that the benefit of adaptive allocation is governed by the heterogeneity of the induced kernel importance structure, leading to distinct regimes in which adaptive or uniform strategies are preferable. Empirical evaluations on synthetic datasets demonstrate that adaptive allocation significantly improves support-vector recovery, margin estimation, and decision-function accuracy under fixed measurement budgets. A dual-coefficient stability criterion further enables early stopping, achieving near-optimal performance while using only a fraction of the measurement cost. Additional experiments on quantum kernels derived from real-world data reveal a regime-dependent behavior aligned with known phenomena such as kernel concentration. Together...
【5】CoRMA: Contrastive RMA for Contact-Rich Meta-Adaptation
标题：CoLMA：针对丰富接触元适应的对比LMA
链接：https://arxiv.org/abs/2605.22082
摘要：
【6】An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
标题：一种改进的自适应ID优化器，具有增强的深度学习收敛性和稳定性
链接：https://arxiv.org/abs/2605.21968
备注：11 Pages, Double Column, 6 Tables, 5 Figures
摘要：Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent. However, it suffers from two key drawbacks. First, it has noisy and varying gradients, and second, it has an overshoot phenomenon. To address noisy gradients, Adam was proposed, which remains the most widely used adaptive optimizer. To address the overshoot phenomenon, a control-theory-based PID optimizer was proposed. To tackle both the limitations within a single framework, several variants of Adaptive PID (AdaPID) have recently been proposed. Although AdaPID performs well, it still inherits two critical drawbacks from Adam, namely convergence and stability issues. In this work, we address both these limitations. To fix the convergence issue, we uniquely integrate the idea of using a non-increasing effective learning rate into AdaPID (originally proposed in AMSGrad, an extension of Adam). To fix the stability issue, we innovatively integrate a gradient difference based modulation factor into AdaPID (originally proposed in DiffGrad, another extension of Adam). Combining both these ideas in AdaPID, results in our novel IAdaPID-ADG optimizer. We evaluate our proposed optimizer on multiple datasets, including benchmark datasets (MNIST and CIFAR10) and real-world datasets (IARC and AnnoCerv). The IAdaPID-ADG substantially outperforms all competing optimizers. Additionally, we perform an ablation study on the MNIST dataset to demonstrate the contribution of each added component.
【7】Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
标题：分布转移下基于忠实词典的解释性的几何自适应解释器
链接：https://arxiv.org/abs/2605.21849
摘要：Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers such as sparse autoencoders and transcoders are a primary tool, but their faithfulness under out-of-distribution (OOD) shift has received little systematic attention. We show that distribution shift rotates the subspace that the model actively uses, misaligning the explainer's dictionary trained on in-distribution (ID) activations. We formalize this misalignment as the faithfulness gap, a geometric distance between the ID dictionary and the OOD-active subspace, and show that it controls OOD faithfulness degradation. To reduce this gap, we propose the Geometry-Adaptive Explainer (GAE), which realigns the explainer's dictionary with the OOD-active subspace while preserving the original feature structure. This requires only unlabeled OOD activations and no gradient updates. We prove that GAE improves over the unadapted ID explainer, with excess loss bounded quadratically by the second-moment shift. Empirically, GAE even matches or surpasses all training-based baselines in causal faithfulness across multiple models and OOD settings.
【8】Zero-shot adaptation to order book dynamics
标题：Zero-Shot改编以订购图书动态
链接：https://arxiv.org/abs/2605.21707
摘要：We describe an adaptive market-making architecture that preserves the analytical structure of the Avellaneda--Stoikov framework while introducing a successor measure-style adaptation mechanism. In our paper we keep Avellaneda--Stoikov fast Hamilton--Jacobi--Bellman structure and make it adaptive to changing market regimes and trading objectives. The central idea is to separate market dynamics from the trading objective. The market state determines a low-dimensional set of Avellaneda--Stoikov parameters, while recent realized rewards determine a low-dimensional objective vector. The HJB forward map then converts this objective into optimal bid and ask quotes through a scalarization of future reward features.
【9】Scalable On-Policy Reinforcement Learning via Adaptive Batch Scaling
标题：基于自适应批量缩放的可扩展策略强化学习
链接：https://arxiv.org/abs/2605.21557
摘要
：Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increasing batch sizes typically yields diminishing returns or performance degradation due to the inherent non-stationarity of the data distribution. We challenge this view by observing that non-stationarity is not a fixed property of RL, but evolves throughout training: early stages exhibit rapid behavioral shifts that demand small batches for plasticity, whereas late stages approach a quasi-stationary regime where large batches enable precise convergence. Motivated by this observation, we propose Adaptive Batch Scaling (ABS), that dynamically adjusts the effective batch size according to the stability of the learning policy. Central to ABS is Behavioral Divergence, a novel metric that quantifies policy non-stationarity by measuring action-level shifts between consecutive updates, which we use to scale batch size inversely to policy volatility. Integrated with the Parallelised Q-Network (PQN) algorithm and evaluated on the ALE benchmark, ABS seamlessly reconciles early-stage plasticity with late-stage stable convergence. Strikingly, contrary to conventional wisdom, our results reveal that the combination of larger networks and larger batch sizes achieves the best performance - a scaling behavior previously thought to be unattainable in RL, now unlocked through adaptive batch control.
【10】Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks
标题：自适应RBF-KAN：Kolmogorov-Arnold网络中动态形状参数的比较评估
链接：https://arxiv.org/abs/2605.21534
摘要：Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline bases. Although effective, spline-based implementations can be computationally expensive. A modified version of KANs, called FastKAN, improves efficiency by replacing splines with Gaussian radial basis functions (RBFs), but it relies on a fixed kernel and shape parameter. In this work, we extend the RBF-based KAN framework by introducing a broader family of radial basis kernels and by initializing the kernel shape parameter using leave-one-out cross-validation (LOOCV). To the best of our knowledge, this is the first study that integrates LOOCV-based kernel scale estimation with deep KAN training. We also introduce Matérn and Wendland kernels into the KAN framework for the first time, enabling more flexible basis representations beyond the Gaussian kernel used in FastKAN. The LOOCV estimate provides a data-driven initialization of the kernel scale, which is subsequently refined during network training. The proposed adaptive RBF-KAN is evaluated on several two-dimensional benchmark functions. The results highlight the importance of kernel selection and adaptive shape parameters, with different kernels showing advantages for smooth functions, discontinuities, and oscillatory patterns. Overall, combining LOOCV-based initialization with adaptive kernel learning provides a practical strategy for improving RBF-based KAN models.
强化学习(11篇)
【1】Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
标题：通过多智能体强化学习实现超人安全敏捷竞赛
链接：https://arxiv.org/abs/2605.22748
备注：12 pages (+4 supplementary). Website: this https URL
摘要：
【2】Abstraction for Offline Goal-Conditioned Reinforcement Learning
标题：离线目标条件强化学习的抽象
链接：https://arxiv.org/abs/2605.22711
摘要：
【3】Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
标题：不要忘记评论家：基于价值观的多循环连续强化学习的数据排练
链接：https://arxiv.org/abs/2605.22454
摘要：Data rehearsal has emerged as a leading approach for mitigating catastrophic forgetting in Continual Reinforcement Learning (CRL). However, existing work remains confined to policy gradient frameworks, regularizing only actors due to the performance degradation incurred by critic regularization. This actor-centric approach overlooks the potential of data rehearsal for value function approximation. Moreover, existing evaluations in CRL rarely consider multi-cyclic environments where task sequences repeat, a critical real-world scenario that exacerbates forgetting and plasticity. We investigate data rehearsal for Deep Q-Networks using Q-value regularization in multi-cyclic settings and propose Qreg+NWLU which introduces two simple modifications: (1) continuous data rehearsal that dynamically collects and updates stored Q-values throughout training, and (2) "No-Wait" regularization that applies immediately rather than after the first task. Together, these modifications yield improvements in learning efficiency, forgetting mitigation, and knowledge transfer over Qreg and conventional CRL methods within value function approximation settings.
【4】DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA
标题：DeferMem：通过强化学习进行长期记忆QA的查询时证据提取
链接：https://arxiv.org/abs/2605.22411
备注：31 pages, 3 figures
摘要：Large language model (LLM) agents still struggle with long-term memory question answering, where answer-supporting evidence is often scattered across long conversational histories and buried in substantial irrelevant content. Existing memory systems typically process memory before future queries are known, then retrieve the resulting units based on similarity rather than their utility for answering the query. This workflow leaves downstream answerers to denoise retrieved candidates and reconstruct query-specific evidence. We present DeferMem, a long-term memory framework that decouples this problem into high-recall candidate retrieval and query-conditioned evidence distillation. DeferMem uses a lightweight segment-link structure to organize raw history and retrieve broad candidates at query time. It then applies a memory distiller trained with DistillPO, our reinforcement learning algorithm for distilling the high-recall but highly noisy candidates into a set of faithful, self-contained, and query-conditioned evidence. DistillPO formulates post-retrieval evidence distillation as a structured action comprising message selection and evidence rewriting. It optimizes this action with a decomposed-and-gated reward pipeline and structure-aligned advantage assignment, gating reward components from validity to quality checks while exposing task-level correctness feedback early and assigning each reward to its responsible output span. On LoCoMo and LongMemEval-S, DeferMem surpasses strong baselines in QA accuracy and memory-system efficiency, achieving the highest QA accuracy with the fastest runtime and zero commercial-API token cost for memory operations.
【5】Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning
标题：跨域离线强化学习的目标对齐Bellman备份
链接：https://arxiv.org/abs/2605.22376
摘要
：Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain by leveraging data collected from a source domain. Existing works typically assess the transferability of source-domain data by measuring its similarity to target-domain transitions, and implicitly perform transition-level selection. Transitions that are considered similar are assigned higher weights or rewards, while dissimilar ones are down-weighted. However, transition-level similarity does not necessarily imply consistency in long-term returns. Even visually or dynamically similar transitions may lead to significantly different outcomes in the target domain, which can mislead policy learning and degrade performance. To address this issue, we revisit the fundamental objective of policy learning. Since policy optimization ultimately relies on Bellman targets to evaluate the quality of decisions, we propose to assess the transferability of source-domain transitions based on their alignment with target-domain Bellman targets, rather than superficial transition similarity. Based on this insight, we propose a method termed Target-Aligned Bellman Backup (TABB), which selectively leverages source-domain data by measuring their contribution to accurate Bellman target estimation in the target domain. We evaluate TABB across a broad range of cross-domain offline RL settings with highly limited target-domain data. Experimental results show that TABB consistently achieves strong performance.
【6】Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
标题：切比雪夫政策和山地车问题：低维控制任务的强化学习
链接：https://arxiv.org/abs/2605.22305
备注：ICML 2026 Spotlight Paper
摘要：We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years. This enables us to reveal two surprising insights: The optimal control is quite simple, yet modern RL agents display a large gap to optimality. Motivated by the analysis of the optimal control, we introduce Chebyshev policies as a universal (i.e. dense) class of RL policies from first principles. They can be trained as drop-in replacements of neural nets, reducing the regret by a factor of 4.18, while requiring 277 times fewer parameters, fostering sample efficiency, explainability and realtime capability. Chebyshev policies are evaluated on further RL tasks, including a real-world nonlinear motion control testbed. They consistently improve performance over neural nets with PPO, ARS and REINFORCE. Our results demonstrate how Chebyshev policies offer a compelling and lightweight alternative or addition to neural nets for low-dimensional control tasks.
【7】Kernel-Based Safe Exploration in Deep Reinforcement Learning
标题：深度强化学习中基于核的安全探索
链接：https://arxiv.org/abs/2605.22207
备注：Accepted at L4DC Conference (22 Jan 2026)
摘要：Safety has been a major concern when deploying deep reinforcement learning algorithms in the real world. A promising direction that ensures that the learned policy does not visit unsafe regions is to learn a \emph{barrier function} along with the policy. A barrier is a function from states to reals that assigns low values to the initial states, high values to the unsafe states, and decreases in expectation on each transition; such a function can be used to bound the probability of reaching unsafe states. Previous attempts learned a barrier function directly from exploration data, but this required either large amounts of data or restrictions on the system dynamics. In this paper, we show how kernel embeddings can be used to learn barrier functions during deep reinforcement learning for stochastic systems with unknown dynamics. Our algorithm, \emph{kernel-based safe exploration (KBSE)}, learns an optimal policy and a barrier simultaneously during exploration. The barriers are computed iteratively, represented as conditional mean embeddings, and provide better probabilistic safety guarantees with more exploration. The exploration algorithm uses the learned barrier functions to identify safety violations. In the case of violation, it intervenes to modify the unsafe action to a safe action, thereby ensuring that the exploration is restricted to actions that bound the probability of reaching unsafe states. We evaluate KBSE on several complex continuous control benchmarks. Experimental results establish our new algorithm to be suitable for synthesizing control policies that are probabilistically safe without degradation in reward accumulation.
【8】Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
标题：Maestro：强化学习来规范分层模型技能集成
链接：https://arxiv.org/abs/2605.22177
摘要：The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on monolithic LLMs and fixed logic to interface with these skills. This gives rise to a critical bottleneck: different LLMs offer distinct advantages across diverse domains, yet current frameworks fail to exploit the complementary strengths of models and skills, thereby limiting their performance on downstream tasks. In this paper, we present Maestro (Multimodal Agent for Expert-Skill Targeted Reinforced Orchestration), a Reinforcement Learning (RL)-driven orchestration framework that reframes heterogeneous multimodal tasks as a sequential decision-making process over a hierarchical model-skill registry. Rather than consolidating all knowledge into a single model, Maestro trains a lightweight policy to dynamically compose ensembles of frozen expert models and a two-tier skill library, deciding at each step whether to invoke an external expert, which model-skill pair to select, and when to terminate. The policy is optimized via outcome-based RL, requiring no step-level supervision. We evaluate Maestro across ten representative multimodal benchmarks spanning mathematical reasoning, chart understanding, high-resolution perception, and domain-specific analysis. With only a 4B orchestrator, Maestro achieves an average accuracy of 70.1%, surpassing both GPT-5 (69.3%) and Gemini-2.5-Pro (68.7%). Crucially, the learned coordination policy generalizes to unseen models and skills without retraining: augmenting the registry with out-of-domain experts yields a 59.5% average on four challenging benchmarks, outperforming all closed-source baselines. Maestro further maintains high computational efficiency with low latency. The source code is available at https://github.com/jinyangwu/Maestro.
【9】On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
标题：基于优化的模糊等效项的折扣强化学习的样本复杂性
链接：https://arxiv.org/abs/2605.21763
备注：Accepted to RLC 2026. arXiv admin note: substantial text overlap with arXiv:2506.00286
摘要：We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures called the optimized certainty equivalent (OCE), which includes important risk measures such as entropic risk, CVaR, and mean-variance. Our focus is on the sample complexities of learning the optimal state-action value function (value learning) and an optimal policy (policy learning) under recursive OCE. We provide an exact characterization of utility functions $u$ for which the corresponding OCE defines an objective that is PAC-learnable. We analyze a simple model-based approach and derive PAC sample complexity bounds. We establish that whenever $u$ does not have full domain $\text{dom}(u)\neq \mathbb{R}$, the corresponding problem is not PAC-learnable. Finally, we establish corresponding lower bounds for both value and policy learning, demonstrating tightness in the size $SA$ of state-action space, and for a more restricted class of utilities, we derive lower bounds that makes the dependence on the effective horizon $\frac{1}{1-γ}$ explicit. Specifically, for $\text{CVaR}_τ$ we show that the correct dependence on $τ$ is $\frac{1}{τ^2}$, thus improving by a factor of $\frac{1}τ$ over state-of-the-art although our bound has a suboptimal dependence on $\frac{1}{1-γ}$.
【10】HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine
标题：HealthCraft：急诊医学的强化学习安全环境
链接：https://arxiv.org/abs/2605.21496
备注：16 pages, 5 figures, 6 tables. Code, task suite, and Docker bundle: https://github.com/GOATnote-Inc/healthcraft
摘要
：Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmarks miss the failure modes that matter in emergency medicine: trajectory-level safety collapse, tool misuse, and capitulation under sustained clinical pressure. We present HealthCraft, the first public reinforcement-learning environment that rewards trajectory-level safety under realistic emergency-medicine conditions, adapted from Corecraft. It is built on a FHIR R4 world state with 14 entity types and 3,987 seed entities, exposes 24 MCP tools, and defines a dual-layer rubric that zeroes reward whenever any safety-critical criterion is violated. We release 195 tasks across six categories, graded against 2,255 binary criteria (515 safety-critical); a post-hoc 10-task negative-class slate extends this to 205 tasks and 2,337 criteria. V8 results on two frontier models show Claude Opus 4.6 at Pass@1 24.8% [21.5-28.4] and GPT-5.4 at 12.6% [10.2-15.6], with safety-failure rates of 27.5% and 34.0%. On multi-step workflows - the closest proxy to real emergency care - performance collapses to near zero (Claude 1.0%, GPT-5.4 0.0%) despite partial competence on individual steps. Six infrastructure bugs fixed between pilots v2 and v8 re-ordered which model "looks stronger," evidence that infrastructure fidelity is part of the measurement. A deterministic LLM-judge overlay bounds evaluator noise, and a 60-run negative-class smoke pilot shows the reward signal is not drop-in training-safe: restraint criteria pass at 0.929 prevalence, a gameability an eval harness can tolerate but a training reward cannot. We scaffold coupling to a Megatron+SGLang+GRPO loop per Corecraft Section 5.2 and leave training-reward ablations as future work. Environment, tasks, rubrics, and harness are released under Apache 2.0.
【11】Reinforcement learning for ion shuttling on trapped-ion quantum computers
标题：捕获离子量子计算机上离子穿梭的强化学习
链接：https://arxiv.org/abs/2605.22463
备注：15 pages + 9 pages supplementary material, 6 figures
摘要：Scalable trapped-ion quantum computing is commonly realized with modular chips that feature distinct zones with specific functionalities, such as storage, state preparation, and gate execution. To execute a quantum circuit, the ions must be transported between these zones. This process is called ion shuttling. To achieve reliable computation results, the shuttling process must be optimized. However, as the number of ions increases, this becomes a high-dimensional optimization problem where optimal solutions cannot be computed efficiently. We demonstrate, to the best of our knowledge, the first use of reinforcement learning (RL) for the optimization of ion shuttling. RL is well-suited for such scenarios, as it enables learning a strategy through direct interaction with the problem. We show that our RL approach outperforms current state-of-the-art heuristic techniques, yielding a reduction in shuttling operations of up to 36.3 %. Furthermore, we show that our method is easily applicable to various chip architectures. Our approach offers a versatile method to study shuttling efficiency during chip design and, therefore, a highly relevant tool for future, more complex architectures.
符号|符号学习(3篇)
【1】Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
标题：赢者通吃瓶颈在多任务学习中强制解除纠缠的符号表示
链接：https://arxiv.org/abs/2605.22472
摘要：
【2】Symbolic Density Estimation for Discrete Distributions
标题：离散分布的符号密度估计
链接：https://arxiv.org/abs/2605.21813
备注：28 pages, 5 figures, 22 tables
摘要：Discrete probability laws underpin statistical modeling, yet the catalog of interpretable distributions has expanded only gradually through centuries of case-by-case mathematical derivations. We introduce symbolic density estimation (SDE), an unsupervised framework that automatically recovers closed-form probability mass functions by composing elementary analytic operations within a structured search space. Our method integrates domain-specific structural priors with evolutionary search and a validity-aware inference stage, and it extends to richer distribution families such as zero inflation and finite mixtures. To support systematic evaluation and future research, we contribute a benchmark dataset spanning a broad collection of commonly used discrete distributions. The proposed algorithm recovers all benchmark families with accurate parameter estimates. A real data application shows that it identifies concise and interpretable mixture models that improve goodness-of-fit over standard models.
【3】Predicting Performance of Symbolic and Prompt Programs with Examples
标题：通过示例预测符号程序和提示程序的性能
链接：https://arxiv.org/abs/2605.21515
摘要：LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given a program, either symbolic (e.g. Python) or a prompt executed on an LLM, and a few in-domain examples, predict its performance on unseen tasks from the same domain. We use a simple coin-flip model, treating each pass/fail program execution as a Bernoulli random variable, whose success probability is the programs unknown performance. In this model, performance depends entirely on: 1) the observed execution outcomes on test cases, and 2) a prior over performances. We compile empirical performance priors from a corpus of diverse programs and tasks, and find that performance for symbolic programs (e.g., Python) are all or nothing, while prompt programs have a diffuse prior with many nearly-correct programs. This difference explains why a few passing tests can certify symbolic programs but not prompt programs. Building on this insight, we develop RAP (Retrieved Approximate Prior), which retrieves similar tasks and prompt programs from an existing corpus to construct a proxy prior, which is then used to predict performance. We show RAP achieves solid performances.
医学相关(7篇)
【1】Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs
标题：儿科ICU抗菌药物管理的机器学习架构基准
链接：https://arxiv.org/abs/2605.22611
备注：16 pages, 6 figures, code: this https URL
摘要：
【2】BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
标题：BioFormer：通过生物医学时间序列中的光谱结构对齐重新思考跨学科概括
链接：https://arxiv.org/abs/2605.22468
摘要：
【3】EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes
标题：跟踪：强大的抑郁症跟踪从辅导成绩单跨会话制度
链接：https://arxiv.org/abs/2605.22286
摘要
：Text-based counseling is an important interface for AI mental-health support, where transcripts may be used to monitor depression severity and flag sessions requiring timely human review. However, robust PHQ-8 prediction across session regimes remains challenging: fine-tuning-based methods can exploit richer supervision but may generalize poorly under data scarcity, while prompt-based LLM methods are data-efficient but usually treat each transcript holistically and provide limited support for longitudinal context. We study robust depression tracking from counseling transcripts across single-session and multi-session regimes. We introduce LongCounsel, a multi-session counseling dataset with session-level PHQ-8 supervision for evaluating repeated-session tracking under partial symptom disclosure and cross-session continuity. We further propose EmoTrack, a PHQ-8 prediction framework that combines LLM-extracted clinical signals with frozen turn-level semantic embeddings and trains symptom-specific predictors over the resulting transcript representation. When prior sessions are available, EmoTrack can further incorporate them through compact cross-session memory. Experiments on LongCounsel and DAIC-WOZ show that EmoTrack achieves a clear gain on the real single-session benchmark, including a 13.5% relative MAE reduction over the strongest DAIC-WOZ baseline, and remains competitive with the strongest longitudinal baseline on LongCounsel.
【4】Can Breath Biomarkers Causally Influence Blood Glucose? Investigating VOC-Mediated Modulation in Diabetes
标题：呼吸生物标志物会对血糖产生因果影响吗？研究VOC介导的糖尿病调节
链接：https://arxiv.org/abs/2605.22075
摘要：
【5】ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data
标题：ChronoMedical World：从纵向护理数据学习患者轨迹的医学世界模型
链接：https://arxiv.org/abs/2605.21963
备注：14 pages, 2 figures, 6 tables
摘要：Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-disease care, yet existing electronic health record (EHR) models are predominantly discriminative, and general-purpose large language models drift under repeated interventions. We propose the \textbf{ChronoMedicalWorld Model (CMWM)}, an action-conditioned latent world-model framework for learning patient trajectories from longitudinal care data. CMWM couples a joint-embedding state encoder with a wide action encoder that admits both structured intervention indicators and free-text communication embeddings, and trains a recurrent latent transition module under a six-term objective: next-observation supervision, next-latent prediction, SIGReg latent regularisation, and three physiology-aware shape priors (slope, continuity, large-jump penalty). A closed-loop rollout-prefix protocol matches training to deployment, so the model is optimised against the same multi-step error it exhibits at inference. As a concrete case study, we instantiate CMWM for annual estimated glomerular filtration rate (eGFR) trajectory forecasting in chronic kidney disease (CKD). On a 2{,}232-patient nephrology cohort, the CKD instantiation achieves a dynamic-50\% history rollout test mean absolute error (MAE) of 7.384 and root-mean-square error (RMSE) of 10.256, against 7.964 and 11.069 for a tuned GPT-5.5 structured-prompting baseline ($-7.28\%$ MAE, $-7.35\%$ RMSE), with the gain dominated by the dialogue portion of patient--health-coach communication. The framework is not CKD-specific: its architecture, loss design, and training protocol apply to any chronic condition that can be cast as periodic clinical state interleaved with structured and conversational interventions.
【6】Machine learning prediction of obstructive coronary artery disease using opportunistic coronary calcium and epicardial fat assessments from CT calcium scoring scans
标题：使用CT钙评分扫描的机会性冠状动脉钙和心外膜脂肪评估来机器学习预测阻塞性冠状动脉疾病
链接：https://arxiv.org/abs/2605.21762
备注：16 pages, 4 figures, 3 tables
摘要：Non-contrast computed tomography calcium scoring (CTCS) is a cost-effective imaging modality widely used to detect coronary artery calcifications. This study aimed to develop an advanced machine learning framework that utilizes quantitative analyses of coronary calcium and epicardial fat from CTCS images to predict obstructive coronary artery disease (CAD). The study population consisted of 1,324 patients from the SCOT-HEART clinical trial who underwent both CTCS and coronary CT angiography. We extracted and analyzed a broad range of features, including 24 clinical variables, 189 calcium-omics, and 211 epicardial fat-omics features from the CTCS images. Feature selection was conducted using the CatBoost algorithm combined with SHapley Additive exPlanation (SHAP) values. Predictive modeling utilized the CatBoost gradient boosting method, focusing on the most informative features. From an initial set of 424 candidate features, 14 were identified as most predictive through the CatBoost-SHAP method. The top two predictive features originated from fat-omics, with the remaining 12 features derived from calcium-omics. The optimized model achieved robust predictive capabilities, demonstrating a sensitivity of 83.1+/-4.6%, specificity of 93.8+/-1.7%, accuracy of 85.3+/-2.0%, and an F1 score of 73.9+/-3.3%. Inclusion of calcium-omics and fat-omics data significantly improved predictive performance. Notably, the model also showed reliable predictive accuracy in patients with diverse coronary calcium scores, including cases with obstructive CAD despite a zero-calcium score. This innovative approach holds promise for improving clinical decision-making and potentially reducing dependence on contrast-enhanced or invasive diagnostic procedures, particularly within low-to intermediate-risk patient groups.
【7】Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis
标题：多模态机器学习用于人群和受试者特异性lncRNA-2型糖尿病关联分析
链接：https://arxiv.org/abs/2605.20747
摘要：Long non-coding RNAs (lncRNAs) are emerging regulatory molecules implicated in chronic disease pathogenesis, including Type 2 Diabetes Mellitus (T2D). We investigated ten literature reported lncRNAs associated with T2D: MALAT1, MEG3, MIAT, ANRIL, GAS5, KCNQ1OT1, H19, BCYRN1, XIST, and HOTAIR across two independent population-based RNA-seq cohorts. Single-omics approaches provide an incomplete view of disease biology, therefore, an integrative multi-feature framework was developed, extracting expression, secondary-structure, and sequence features for each lncRNA. Eight machine learning (ML) classifiers were evaluated under stratified k-fold, leave-one-out cross-validation (LOOCV), and repeated hold-out schemes to ensure robust performance estimation. SHAP analysis was applied for subject-level association interpretation. In one cohort, GAS5 and XIST expression features, along with GAS5, MEG3, and ANRIL sequence features, were found to be associated with T2D, while MALAT1 expression and KCNQ1OT1, ANRIL, and MEG3 sequence features were found to be associated in the second cohort. MEG3 was identified by SHAP as the dominant lncRNA in both cohorts. ML results were consistent with established statistical methods while additionally providing population- and subject-level disease association profiles linked to specific molecular feature types. The proposed framework advances mechanistic understanding of T2D and supports lncRNA-based precision medicine.
蒸馏|知识提取(3篇)
【1】Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
标题：后训练是关于状态，而不是代币：SFT、RL和政策上蒸馏的状态分布视图
链接：https://arxiv.org/abs/2605.22731
摘要：
【2】X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
标题：X-Token：投影引导的跨Tokenizer知识提炼
链接：https://arxiv.org/abs/2605.21699
摘要：Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is preferred as a drop-in replacement requiring no auxiliary components. Logit-based methods either use only the correct-token probability, missing the full 'dark knowledge' in the teacher's distribution, or operate on the full output distribution, relying on strict token partitioning and/or unprincipled heuristic ranking. We identify two key shortcomings of full-distribution, logit-based methods: (i) an uncommon-token failure, where critical tokens fall into the unmatched subset (e.g., Llama's 1100 multi-digit numerals under digit-splitting Qwen supervision) and are suppressed during training, reducing GSM8k from 12.89 to 2.56 compared to same-tokenizer KD from a weaker teacher; and (ii) over-conservative matching, where strict 1-to-1 matching excludes near-equivalent tokens across surface forms. These failures require distinct remedies: eliminating the partition when critical tokens are misaligned, and refining it when alignment is reliable. We propose X-Token, an approach with two complementary loss formulations targeting these issues. P-KL removes partitioning and aligns the student's distribution with the teacher's via a sparse projection matrix W (initialized from tokenizer-level string rules) to address the uncommon-token failure. H-KL retains the hybrid form while relaxing matching to align each student token with its top-ranked teacher mapping under W. Both objectives share W and extend naturally to multiple teachers. Empirically, on Llama-3.2-1B, X-Token outperforms the current state of the art GOLD by +3.82 average points with a Qwen3-4B teacher and by +0.5 with a Phi-4-Mini teacher. Further, a two-teacher setup (Phi-4-mini + Llama-3B) improves over single-teacher distillation by +1.3 points.
【3】When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
标题：教师代币什么时候可靠？位置加权按策略自蒸馏推理
链接：https://arxiv.org/abs/2605.21606
备注：Pre-print. Code is available at https://github.com/SaFo-Lab/PW-OPSD
摘要：On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly treating the privileged teacher target as equally reliable at every student-visited prefix. Existing entropy-based OPD methods relax this uniformity by modulating token-level supervision with teacher entropy, but high teacher entropy in reasoning has an ambiguous reliability meaning: it can reflect either non-viable uncertainty or benign solution diversity. To identify this phenomenon, we introduce a branch-viability diagnostic. Specifically, we record next-token alternatives from the privileged-answer teacher prompt, force each alternative after the student prompt plus its on-policy spine prefix, and test whether the resulting student-template continuation recovers the correct answer. On Qwen3-4B, we find that an oriented within-sequence position score is the strongest tested predictor of teacher-token reliability, reaching an area-under-ROC-curve (AUROC) of 0.83; local uncertainty scores are at most 0.57. Motivated by this trajectory-level structure, we propose Position-Weighted On-Policy Self-Distillation (PW-OPSD), which applies an increasing position weight while keeping the same student rollout, privileged teacher pass, and clipped forward-KL target as OPSD. In our comprehensive evaluations with different random seeds, the diagnostic-derived PW-OPSD improves AIME 2024 and AIME 2025 Avg@12 by +1.0 and +1.1 points, and a generalization evaluation on two larger-scale models from different families, DeepSeek-R1-Distill-Llama-8B and Olmo-3-7B-Think, also demonstrates consistent aggregate Avg@12 improvements. These results show that teacher-token reliability in reasoning distillation is trajectory-structured and can be utilized without additional teacher computation.
推荐(1篇)
【1】PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation
标题：PEARL：通过对比学习进行工业规模直播推荐的无偏百分位数估计
链接：https://arxiv.org/abs/2605.21752
摘要：Recommender systems trained on user interaction data are susceptible to behavioral intensity imbalance--a systematic distortion arising from heterogeneous engagement patterns across users. This imbalance skews feedback signals such that observed interactions no longer faithfully reflect true preferences, causing models to disproportionately amplify signals from highly active users while underrepresenting others, which ultimately degrades recommendation quality and robustness at scale. To address this issue, we propose a nonparametric contrastive percentile approximation framework, PEARL, that models relative preference signals instead of absolute engagement magnitudes. Building upon relative advantage debiasing, PEARL leverages real contrastive interaction samples to approximate percentile relationships directly, without relying on auxiliary distribution estimation models. We provide theoretical justification demonstrating that such pairwise comparisons yield unbiased estimates of percentile-based preference signals. For broader applicability, we introduce a prediction-based bootstrapping mechanism for percentile smoothing to handle sparse and discrete feedback, alongside a generalized value-weighted formulation and a co-training strategy to enhance both modeling flexibility and representation learning. Extensive offline experiments demonstrate that PEARL effectively mitigates behavioral bias and consistently improves recommendation performance across multiple ranking targets. Deployed in a production livestream platform with a combined user base of billions, online A/B testing confirms substantial real-world gains: +2.10% Watch Duration, +0.80% Consumption Amount, +1.49% Interaction Rate, and -6.91% Report Rate.
聚类(2篇)
【1】EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning
标题：EnCAgg：增强的聚类聚合，用于对抗动态模型中毒的鲁棒联邦学习
链接：https://arxiv.org/abs/2605.22506
摘要：
【2】Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering
标题：基于最小描述长度的粒球树正则化谱聚类算法
链接：https://arxiv.org/abs/2605.22410
备注：28 pages, 5 figures, 6 tables
摘要
：Spectral clustering largely depends on the affinity graph, yet constructing a graph that preserves reliable local connectivity while adapting to heterogeneous data structures remains challenging. Existing granular-ball-based spectral clustering methods usually reduce graph complexity by using coarse-grained representatives. However, the learned local regions are often treated as graph nodes or anchors, and their structural information is not sufficiently used to regularize the original sample-level graph. To address this issue, this paper proposes a Minimum Description Length based Granular-Ball Tree-Regularized Spectral Clustering method, termed MDL-GBTRSC. The proposed method constructs a granular-ball tree through local MDL model selection, with reciprocal neighborhood continuity used to discourage splits that break reliable local connections. The stable leaf balls obtained from the tree provide coding-scale information for regularizing the sample-level affinity graph. In addition, a shared-neighbor bridge code is introduced to adjust weak local bridge relations without requiring an additional user-specified threshold. In this way, MDL-GBTRSC connects interpretable local representation learning with affinity graph construction in a unified spectral clustering framework. Experiments on real and synthetic datasets show that MDL-GBTRSC achieves the best average ARI and NMI under the adopted fixed-configuration protocol compared with classical spectral clustering baselines and representative granular-ball, micro-cluster, and anchor-based methods.
超分辨率|去噪|去模糊|去雾(1篇)
【1】Automatic Contextual Audio Denoising
标题：自动上下文音频去噪
链接：https://arxiv.org/abs/2605.22262
摘要：Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, traffic noise is informative in urban surveillance but noise for a phone call at the same location. Most current audio denoising systems apply fixed target-noise definitions, often removing useful components in one context while failing to suppress irrelevant components. To address this, we introduce the concept automatic contextual audio denoising (ACAD) which defines target and noise based on the inferred context. In this work, we restrict context to be associated with an acoustic scene class. We label sound events outside the event distribution of a scene class (noise) as out-of-context (OC) and events typical for that scene as in-context (IC). We implement a deep learning method that automatically infers the context of the audio signal and removes OC components, and benchmark it against variants: without context inference, with oracle context, and with separately provided uninformative context. On paired clean/noisy data across diverse contexts, where OC components in one context may be IC in another, our proposed method outperforms other approaches across standard objective metrics, indicating that the model can infer context and context-dependent processing can enhance denoising.
点云|SLAM|雷达|激光|深度RGBD相关(1篇)
【1】PointLLM-R: Enhancing 3D Point Cloud Reasoning via Chain-of-Thought
标题：PointLLM-R：通过思想链增强3D点云推理
链接：https://arxiv.org/abs/2605.22013
摘要：Understanding 3D point clouds through language remains a fundamental challenge in computer graphics and visual computing, due to the irregular structure of point cloud data and the lack of explicit reasoning in existing 3D multimodal models. While Chain-of-Thought (CoT) reasoning has shown strong effectiveness in LLMs and image-based MLLMs, its extension to 3D understanding remains largely underexplored. In this paper, we propose a data-centric framework for constructing large-scale CoT supervision tailored to 3D point cloud understanding. Our framework consists of a two-stage pipeline that first refines point-text instruction data via vision-language-model-based quality evaluation and reference-guided refinement, and then synthesizes high-quality reasoning paths through Human-in-the-Loop Prompt Optimization (HiLPO). Using this approach, we build PoCoTI, a CoT-enhanced point-text instruction-following dataset containing 55K samples with explicit reasoning paths. Fine-tuning PointLLM on PoCoTI yields PointLLM-R, a reasoning-capable 3D multimodal language model. Extensive experiments on generative 3D classification and captioning demonstrate that PointLLM-R achieves state-of-the-art performance and generalizes robustly to real-world scanned point clouds and multi-turn dialogue scenarios.
联邦学习|隐私保护|加密(2篇)
【1】Detecting Atypical Clients in Federated Learning via Representation-Level Divergence
标题：通过表示级分歧检测联邦学习中的非典型客户端
链接：https://arxiv.org/abs/2605.22266
摘要：Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable updates and degraded global performance. Moreover, in practical deployments, client updates may deviate from the expected behavior not only due to benign not i.i.d. distributions, but also due to distributional shifts or anomalous inputs, raising concerns about the reliability of the aggregation process. In this work, we propose a lightweight geometric signal to quantify the functional deviation of a client with respect to the global model. Instead of comparing model parameters or gradients, our approach measures how the local training of each client alters the activation-induced partition of the input space, evaluated on a shared probe set. This yields a permutation-invariant, interpretable metric of client--global divergence that captures differences in how data is processed by the model. We show that this signal effectively identifies clients that induce atypical functional changes, distinguishing stable yet heterogeneous clients from those whose updates significantly diverge from the global regime. As a result, the proposed metric provides a simple tool for monitoring client behavior and enabling risk-aware aggregation strategies in federated learning systems.
【2】Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction
标题：基于嵌入式的联邦学习和工作组治理用于缺铁预测
链接：https://arxiv.org/abs/2605.21563
摘要：Recent reviews find that the vast majority of published healthcare federated learning (FL) studies never reach real-world deployment. We developed an embedding-based FL pipeline for iron deficiency prediction from routine full blood count (FBC) data and deployed it across real institutional environments at Amsterdam University Medical Centre (AUMC) and NHS Blood and Transplant (NHSBT), two clinical environments that differ markedly in iron deficiency prevalence, ferritin distribution, and subject populations. A frozen domain-specific haematology foundation model, DeepCBC, performs site-local representation extraction, restricting federated training to a compact downstream classifier and substantially reducing recurrent communication relative to full-encoder federation. The two clinical datasets are structurally not independent and identically distributed (non-IID), with heterogeneity arising from distinct population differences rather than sampling artefacts. Runtime governance is enforced by FLA$^3$, a healthcare-oriented FL platform providing study-scoped execution, policy-based authorisation, and signed audit logging. Standard sample-size-weighted aggregation (FedAvg) reduced the area under the receiver operating characteristic curve (ROC-AUC) at both sites relative to local-only training, as the global update was biased towards the larger AUMC distribution. FedMAP, a personalised aggregation method, raised ROC-AUC from 0.9470 to 0.9594 at AUMC and from 0.8558 to 0.8671 at NHSBT relative to local-only training, achieving the highest macro ROC-AUC of 0.9133 and the best macro balanced accuracy overall. These results support personalised aggregation in clinical federations where client sample size and task relevance diverge substantially.
推理|分析|理解|解释(17篇)
【1】SDPM: Survival Diffusion Probabilistic Model for Continuous-Time Survival Analysis
标题：连续时间生存分析的生存扩散概率模型
链接：https://arxiv.org/abs/2605.22776
摘要：
【2】SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation
标题：SegCompass：探索与稀疏自动编码器的可解释对齐以增强推理分割
链接：https://arxiv.org/abs/2605.22658
备注：Accepted by CVPR 2026. 15 pages, 9 figures, 6 tables
摘要：
【3】Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
标题：理解组块行为克隆中的多峰失败
链接：https://arxiv.org/abs/2605.22493
摘要：
【4】Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence
标题：跨领域基准揭示了协调的人工智能代理何时从部分证据中改进科学推理
链接：https://arxiv.org/abs/2605.22300
摘要：Scientific evidence often spans instruments, databases, and disciplines, so no single source records the full phenomenon. This makes it difficult to determine when coordinated AI agents add value over simpler scientific workflows. We evaluate this question with a cross-domain benchmark spanning four scientific tasks: mapping molecular structure into musical representations, detecting historical paradigm shifts in science, identifying vector-borne disease emergence, and vetting transiting-exoplanet candidates. Each case uses a frozen evaluation panel, predefined scoring protocols, explicit baselines, ablations or null controls, and stated limitations. The results define three operating regimes. When different disciplines each capture only part of the phenomenon, cross-channel composites improve over single-channel baselines: climate-vector emergence reaches AUROC 0.944 and exoplanet vetting reaches AUROC 0.955. However, the exoplanet workflow is effectively tied with a strong combined-summary baseline, showing that decomposition does not always improve top-line performance. When one signal dominates, as in paradigm-shift detection, coordination mainly improves interpretation and traceability. For molecular sonification, the gain is representational rather than predictive. ScienceClaw x Infinite provides the auditable artifact and provenance layer for this evaluation. The benchmark therefore assigns value to coordination only when the corresponding performance, provenance, or representation claim is supported by explicit comparators.
【5】Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies
标题：用于多维预测研究的数据驱动设计的可解释人工智能
链接：https://arxiv.org/abs/2605.22243
备注：41 pages, 7 figures
摘要：Predictive modelling is important for health data analysis and data-driven clinical decision-making. However, predictive studies are challenging to design optimally by hand when tens or even hundreds of features require selection, transformation, or interaction modelling. While complex machine learning models offer high performance, their "black-box" nature limits the clinical trust, transparency, and interpretability required for decision-making. We developed and evaluated an Exploratory AI Recommender that provides data-driven recommendations to improve predictive performance of existing interpretable statistical models. The developed framework uses flexible AI modelling to capture complex data patterns and explainable AI techniques to translate the patterns into three recommendation types: feature exclusion, non-linear terms, and feature interactions. We evaluated the framework by comparing predictive performance of a baseline (i.e., no interactions or non-linear terms) Cox Proportional Hazards (CPH) model against an augmented CPH incorporating recommendations suggested by our method. The primary analysis predicts the time to the first occurrence of a fall or related injury in 245,614 patients. Our method recommended excluding 23 features, including non-linear terms for two features, and including 221 suggested feature interactions. The C-index improved from 0.805 (95% CI 0.798-0.812) to 0.815 (95% CI 0.809-0.822), and so did calibration (intercept: -0.006 to 0.003; slope: 1.063 to 0.950). All recommendations were supported by existing literature. The method also proved effective on two additional public datasets, demonstrating wider applicability. The proposed Exploratory AI Recommender demonstrates the potential of explainable AI and data-driven study design to improve the process of developing, and the performance of high-dimensional transparent predictive models.
【6】Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference
标题：决策感知二次ReLU替代，用于HE友好推理
链接：https://arxiv.org/abs/2605.22237
备注：13 pages, 2 figures
摘要：Fully homomorphic encryption (FHE) supports only additions and multiplications, so FHE-only neural-network inference typically replaces ReLU with polynomials fitted over empirical activation intervals. Such interval fitting often requires higher-degree polynomials to control activation error, incurring homomorphic evaluation costs, while classification is determined by the final logit decision. We revisit ReLU replacement from a decision-aware perspective: given a trained single-hidden-layer ReLU MLP and a specified calibration set, can an HE-friendly low-degree polynomial replace ReLU without retraining while preserving calibration-set decisions? We focus on quadratic replacement, the lowest-degree choice that retains a genuine per-unit nonlinearity. For calibration sets positive-margin separable in the lifted space, we formulate quadratic replacement as a linear separation problem, yielding necessary and sufficient conditions for calibration-lossless replacement and a constructive algorithm for the coefficients. When the positive-margin condition fails -- typically due to a few misclassified calibration samples -- we extend the same geometric framework via reduced convex hulls and Lagrangian-dual soft-margin relaxations, which bound the influence of any single sample, converting the problem into smaller convex quadratic programs that yield approximately feasible coefficients with high empirical agreement on calibration-set decisions. In particular, at the maximal weight cap $μ=1$, the reduced-convex-hull relaxation reduces to the convex-hull separation of the strictly separable case; the relaxation thus continuously extends the exact theory. Under CKKS, the quadratic replacement matches plaintext top-1 accuracy on multiple benchmarks, running 3.7--4.1$\times$ faster than Remez-7 in the activation module and 1.18--1.68$\times$ faster end-to-end.
【7】Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
标题：通过自我调节模拟规划进行高效统计推理
链接：https://arxiv.org/abs/2605.22138
备注：Code and model artifacts are available at this https URL
摘要：
【8】Three Costs of Amortizing Gaussian Process Inference with Neural Processes
标题：用神经过程摊销高斯过程推理的三个代价
链接：https://arxiv.org/abs/2605.21798
备注：To appear at ProbNum 2026
摘要：Neural processes amortize Gaussian process inference, replacing the exact $O(n^3)$ posterior with a learned $O(n)$ map from context sets to predictive distributions. For a class of latent neural processes, we bound the Kullback--Leibler (KL) divergence between the GP and LNP predictives, decomposing it into three interpretable sources, namely label contamination as the neural process uses label values to estimate a quantity that is label-independent in the exact GP, an information bottleneck because the finite-dimensional representation cannot resolve the full context geometry, and amortization error from a single encoder network shared across all contexts. The bottleneck truncation term decays in the representation dimension $d$ as $O(e^{-cd^{2/d_x}})$ for squared-exponential kernels on $\mathbb{R}^{d_x}$ where $c > 0$ is a kernel-dependent constant and as $O(d^{-2ν/d_x})$ for Matérn-$ν$ kernels, directly linking architecture sizing to kernel smoothness and input dimension. The label contamination term is $O(1)$ in general, with only the observation-noise component decaying as $O(1/n)$, identifying a persistent cost of routing uncertainty estimation through a label-dependent representation. These results characterize the costs of amortization within the analyzed class and yield architectural recommendations to predict variance from context locations alone in the GP-amortization regime, and replace mean aggregation with second-order pooling to close the dominant amortization gap.
【9】Quantitative coronary calcification analysis for prediction of myocardial ischemia using non-contrast CT calcium scoring
标题：使用非增强CT钙评分进行定量冠状动脉钙分析预测心肌缺血
链接：https://arxiv.org/abs/2605.21745
备注：15 pages, 4 figures, 3 tables
摘要：Non-contrast computed tomography calcium scoring (CTCS) is widely recognized as an effective tool for cardiovascular risk stratification. This study aimed to develop a novel machine learning framework for predicting myocardial ischemia from routine non-contrast CTCS scans using quantitative coronary calcium assessment. This study analyzed 1,375 patients who underwent both non-contrast CTCS and regadenoson stress cardiac positron emission tomography myocardial perfusion imaging within one year at University Hospitals Cleveland Medical Center. A total of 74 variables, including clinical variables, Agatston score, and calcium-omics features, were evaluated. Relevant features were identified using XGBoost with Shapley Additive exPlanations (SHAP). Predictive models were trained and evaluated using 5-fold cross-validation. Among 987 patients, 89 (9%) were positive for myocardial ischemia. The final model incorporated the Agatston score, eight calcium-omics features, and age. The proposed model achieved a precision of 98.9+/-3.0%, sensitivity of 79.2+/-8.4, and F1 score of 87.7+/-5.3%. The addition of calcium-omics features significantly improved predictive performance compared with models using clinical variables alone or clinical variables with the Agatston score (p<0.05). Interestingly, the number of calcified arteries, despite being the lowest-ranked feature based on SHAP analysis, showed the strongest association with myocardial ischemia in logistic regression analysis (odds ratio: 3.63, 95% confidence interval: 2.80-4.77, p<0.00001). We developed a machine learning approach for predicting myocardial ischemia using routinely acquired non-contrast CTCS scans. Calcium-omics features provided incremental predictive value beyond conventional risk factors and Agatston scoring and may support more accessible cardiovascular risk stratification.
【10】Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations
标题：相似零件：本地和全球原型修复的知情方法
链接：https://arxiv.org/abs/2605.21646
备注：Accepted for publication in International Journal of Applied Mathematics and Computer Science (IJAMCS)
摘要：Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but often lack feature-level granularity. We introduce a framework that integrates feature importance at two levels to address this gap. First, for local explanations, we propose \textit{alike parts}: a method that uses feature importance scores to highlight the most relevant, shared feature subsets between a classified instance and its nearest prototype, guiding user attention. Second, we augment the global prototype selection objective function with a feature importance term to actively promote diversity in the feature attributions of the selected prototypes. Experiments on six benchmark datasets show that this augmented selection process maintains or, in some cases, increases the prediction fidelity of the surrogate model, suggesting that feature diversity does not compromise model fidelity.
【11】ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
标题：Contact：通过显式接口推理进行接触优先抗体CDR设计
链接：https://arxiv.org/abs/2605.21600
摘要：Computational antibody CDR design methods condition on antigen structure to generate binding loops, yet existing architectures conflate two fundamentally distinct sub-problems: identifying which CDR positions will contact the antigen, and selecting amino acids at those positions. This conflation forces models to learn contact reasoning implicitly through uniform message passing, diluting antigen signal across all positions equally. We introduce ConTact, a contact-then-act architecture that explicitly decomposes CDR design into three cascaded stages: learning surface complementarity fingerprints, predicting CDR-antigen contacts, and injecting contact-gated antigen features into the sequence head. A distance-biased cross-attention module encodes geometric priors favoring spatial neighbors, while a contact-weighted cross-entropy loss concentrates gradient signal on binding-critical positions. On CHIMERA-Bench dataset, ConTact achieves the best structural quality (7% RMSD improvement over the next-best baseline), best epitope awareness (10% F1 score over GNN baselines), and competitive sequence recovery (AAR 0.38) among several CDR-H3 design baselines.
【12】Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model
标题：扩散Fitzhugh-Nagumo模型中的平衡传播和Hamilton推论
链接：https://arxiv.org/abs/2605.21568
摘要
：In this work, we extend the Equilibrium Propagation framework to skew-gradient systems and show an equivalence between deep Energy-Based Models and Hamiltonian neural networks. We focus on networks of diffusively coupled Fitzhugh-Nagumo neurons as a prototypical example. We show that since stationary solutions of the Fitzhugh-Nagumo model are described by self-adjoint operators, the methods of equilibrium propagation for performing credit assignment can be applied. Furthermore, for Fitzhugh-Nagumo networks with the topology of a deep residual network, we show that the steady state solutions admit a (spatial) Hamiltonian, and thus the methods of Hamiltonian Echo Backpropagation can be applied. We end by deriving an explicit layer-wise Hamiltonian recurrence relation governing inference for stationary solutions of both deep Fitzhugh-Nagumo networks and deep Energy-Based Models.
【13】Harnesses for Inference-Time Alignment over Execution Trajectories
标题：执行轨迹上的推理时间对齐利用
链接：https://arxiv.org/abs/2605.21516
摘要：Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are not uniformly better: increasing decomposition or guidance can sometimes improve execution, but can also reduce final task success. We study harness design through the lens of inference-time trajectory alignment. This perspective separates harness into two mechanisms: task decomposition, which structures a task into sub-goals, and guided execution, which reshapes local action distributions during execution. This decomposition allows us to quantify how workflow granularity, retry budgets, and guidance-induced action reweighting shape the performance limits of harness design. It further reveals concrete failure modes, including over-decomposition, over-pruning, and hallucinated execution. We validate these predictions through controlled synthetic experiments and real terminal agent benchmarks. Inspired by the theory, we further show that effective harnesses can be partial: specifying only the initial steps and leaving the remaining execution to agent can achieve higher pass rate than fully structured workflows.
【14】PhylaFlow: Hybrid Flow Matching in Billera-Holmes-Vogtmann Tree Space for Phylogenetic Inference
标题：PhylaFlow：Billera-Holmes-Vogtmann树空间中的混合流匹配，用于系统发生推理
链接：https://arxiv.org/abs/2605.21859
备注：9 pages, 3 figures
摘要：Phylogenetic trees are hybrid objects: branch lengths vary continuously, while topologies change discretely through edge contractions and expansions. Billera-Holmes-Vogtmann (BHV) tree space provides a canonical geometry for this structure, representing each resolved topology as a Euclidean orthant and topological changes as motion across shared lower-dimensional boundaries. We introduce PhylaFlow, a hybrid flow-matching model that learns posterior-basin transport in BHV tree space. PhylaFlow is trained on BHV geodesic paths from random starting trees to short-run posterior samples, coupling continuous branch-length motion within orthants with learned boundary events and discrete topology transitions. We evaluate the learned geometry operationally: if the flow reaches posterior-relevant regions, finite-budget Bayesian refinement initialized from, or guided by, its terminal trees should recover posterior-supported topologies more efficiently. Across DS1-DS8 phylogenetic posterior benchmarks, PhylaFlow substantially reduces initial Tree-KL relative to classical initializers. After finite-budget MrBayes refinement, direct PhylaFlow improves early and intermediate topology-recovery trajectories on most datasets, while split-guided PhylaFlow-MCMC obtains the strongest hard-case results. The best PhylaFlow variant outperforms short-warmup on seven of eight datasets and PhyloGFN on five of eight under the same refinement budget. In a joint sequence-conditioned experiment, sequence embeddings steer posterior split recovery, although exact posterior topology recovery remains preliminary. These results show that hybrid flow matching can learn actionable transport in BHV tree space and provide a geometry-aware proposal mechanism for Bayesian phylogenetic inference.
【15】Truncated Neural Likelihood Estimation for Simulation-Based Inference in State-Space Models
标题：状态空间模型中基于模拟推理的截断神经似然估计
链接：https://arxiv.org/abs/2605.21805
摘要：State-space models (SSMs) are powerful probabilistic tools for modeling time-varying systems with latent dynamics. Inference in SSMs involves the estimation of latent states and parameters. In this work, we focus on parameter inference, which for SSMs is in general a very challenging problem due to the intractability of the likelihood. Recently, neural estimation methods, such as sequential neural likelihood (SNL), have shown promising results in Bayesian inference problems. In this paper, we show that SNL, when applied to the SSM setting, suffers important limitations, such as requiring a large amount of simulated samples to achieve a moderate performance, scaling poorly with sequence length, while not being amortized. We then introduce a novel inference algorithm called truncated-SNL (T-SNL), which addresses the limitations of SNL. Our algorithm is more accurate, more stable and robust during training, more scalable to longer temporal sequences, and can be amortized when new observations become available. Our experiments show that T-SNL is sample-efficient, robust, and flexible algorithm which outperforms other approaches.
【16】Mapping Tomato Cropping Systems in California Using AlphaEarth Geospatial Embeddings and Deep Learning Analysis
标题：使用AlphaEarth地理空间嵌入和深度学习分析绘制加州番茄种植系统
链接：https://arxiv.org/abs/2605.21804
备注：5 pages, 3 figures, 1 table. Preprint submitted to ASABE 2026 AIM
摘要：Field-scale crop maps support supply-chain forecasting and policy, yet statewide crop identification still often depends on retrospective surveys or remote-sensing workflows built around hand-engineered spectral features. Those pipelines can be accurate, but they require repeated preprocessing and often lose robustness across years. This study evaluated whether Google DeepMind's AlphaEarth geospatial embeddings can serve as an analysis-ready alternative for mapping processing tomato systems in California. LandIQ 2018 crop polygons were used to assemble a balanced reference dataset of 4,742 tomato and 4,742 non-tomato fields. For each polygon, 64-band AlphaEarth embedding chips were extracted and aligned with binary masks, then divided into spatially independent training (n = 6,638), validation (n = 1,422), and test (n = 1,424) sets. A U-Net segmentation model was trained on AWS SageMaker using a composite masked binary cross-entropy and soft Dice loss. To complement hard predictions, Monte Carlo dropout was retained at inference and repeated 100 times per chip to estimate predictive mean and variance. On the independent test set, the model achieved 99.19% pixel accuracy, 98.69% precision, 99.40% recall, 99.04% F1 score, 98.11% intersection over union, and 99.02% chip accuracy. Uncertainty maps were consistently highest near field edges and low within field interiors. The results show that AlphaEarth embeddings retain crop-relevant spatial and temporal structure and can support accurate, field-scale tomato mapping without manual feature engineering.
【17】Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery
标题：蛋白质思维：利用思维树和嵌入空间流匹配的可解释推理，以发现蛋白质-蛋白质相互作用
链接：https://arxiv.org/abs/2605.21522
摘要
：Protein-protein interactions (PPIs) govern nearly all cellular processes, yet computational methods for identifying binding partners typically produce ranked predictions without mechanistic justification. This creates a fundamental barrier to adoption because biologists cannot assess whether predictions reflect genuine biochemical insight or spurious correlations. We present \textbf{Protein Thoughts}, a framework that reformulates PPI discovery as an interpretable search problem with explicit reasoning. The system decomposes binding evidence into four biologically meaningful signals: sequence similarity reflecting evolutionary relationships, structural complementarity capturing geometric fit, interface balance, and chemical compatibility encoding residue-level interactions. Rather than collapsing these signals into an opaque score, we preserve their individual contributions through a transparent value function that enables both ranking and auditing. To navigate large candidate spaces efficiently, we introduce hypothesis-guided entropy-regularized Tree-of-Thoughts search. A fine-tuned language model generates search directives from embedding-derived features, classifying candidates as high-priority, exploratory, or skippable. These directives condition a Boltzmann policy that balances exploitation with entropy-driven exploration, while hypothesis-aware pruning prevents premature abandonment of promising candidates. For candidates exhibiting score disagreement, hypothesis-conditioned embedding-space flow matching transports protein embeddings toward the binder manifold. On the SHS148k benchmark, Protein Thoughts achieves mean best-binder rank of 11.2 versus 47.7 for an entropic tree search baseline, a 76% improvement, and for binding prediction the trained value function achieves $91.08 \pm 0.19$ Micro-F1, outperforming existing PPI methods on the same dataset.
检测相关(9篇)
【1】FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
标题：FAME：用于消息级日志异常检测的故障感知专家混合
链接：https://arxiv.org/abs/2605.22779
备注：12 pages, 5 figures
摘要：
【2】Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
标题：伐木工：通过树木中的重型攻击检测建立更好的差异私有随机森林
链接：https://arxiv.org/abs/2605.22756
摘要：
【3】Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
标题：使用机器学习和元启发式特征优化在支持物联网的智能电网中进行网络物理异常检测
链接：https://arxiv.org/abs/2605.22749
摘要：
【4】More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts
标题：更多的背景，更大的模型，或道德知识？政治语篇中Schwartz价值检测的系统研究
链接：https://arxiv.org/abs/2605.22641
备注：Code: this https URL, best model: this https URL, 18 pages, 3 figures
摘要：
【5】The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
标题：噪音中的信号：通过因子分解潜在空间中的适合度测试进行OOD检测
链接：https://arxiv.org/abs/2605.22496
摘要：
【6】Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light
标题：使离散连续：用于细粒度评估弱光下人员检测性能的合成原始增强
链接：https://arxiv.org/abs/2605.22455
备注：Accepted non-archival paper at the CVPR 2026 AUTOPILOT Workshop (Autonomous Understanding Through Open-world Perception and Integrated Language Models for On-road Tasks)
摘要：Real-world deployment of AI vision models is both fueled and limited by the data available for training and testing. Real datasets are sparse and uneven: long-tailed or unbalanced distributions hinder generalization, and the low number of samples in low density regions makes it hard to run evaluations. Synthetic data can fill these gaps, providing us with a way to sample the input space more continuously and improve data coverage for benchmarks. Focusing on the autonomous driving safety-critical case of pedestrian detection in the dark, we show how synthetic low-light samples can be used to better characterize the performance of a state-of-the-art object detection model as a function of the scene illumination. We use a synthetic RAW image augmentation technique to generate low-light samples that match the noise model of the camera sensor. Performance metrics on real and synthetic low-light data are similar, indicating that the AI model finds it hard to distinguish between them.
【7】Multi-Stage Training for Abusive Comment Detection in Indic Languages
标题：基于多阶段训练的印度语辱骂性评论检测
链接：https://arxiv.org/abs/2605.22380
备注：4 pages, EAM2021 selected
摘要：In recent years social media has become an increasingly popular tool for communication. People use it to share their ideas, exchange information, and discuss thoughts. Given its prevalence and widespread reach, social media must remain a safe space for people. Content generated on social media can be abusive and it has become increasingly important to detect such content. In this paper, we use a language-based preprocessing and an ensemble of several models and analyze their performance of abusive comment detection. Through extensive experimentation, we propose a pipeline that minimizes the false-positive rate (marking non-abusive as abusive) so that these systems can detect abusive comments without undermining the freedom of expression.
【8】SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection
标题：SepsisAI调试器：一个容器化且可扩展的平台，用于在早期败血症检测中部署AI模型和实时监控
链接：https://arxiv.org/abs/2605.22331
备注：13 pages, 5 figures. Submitted to BioCARLA 2025 Workshop
摘要
：Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by systems-level barriers: heterogeneous data representations, the absence of standardized deployment workflows, and a mismatch between research prototypes and the concurrency and latency requirements of hospital environments. We present the SepsisAI-Orchestrator, an open-source modular platform that addresses this deployment gap for early sepsis detection. The platform integrates HL7 FHIR-inspired Clinical Document Architecture (CDA) preprocessing, NoSQL storage, a containerized LightGBM classifier served via REST APIs, and a Streamlit clinical dashboard, orchestrated with Docker and Kubernetes. A previously validated LightGBM model (F1 0.87-0.94 on PhysioNet 2019) is reused without modification; the contribution lies in the surrounding infrastructure and its empirical characterization under load. Using k6 with 50-1000 concurrent virtual users, we find that replica count must be matched to the physical CPU thread count of the host: scaling from 3 to 12 replicas on a 12-thread CPU reduces p95 latency from 3.3s to 1.41s (57.3% reduction) and eliminates all request failures, while over-provisioning to 24 or 48 replicas degrades performance due to scheduler contention. To our knowledge this U-shaped scaling behavior has not been quantified previously for clinical AI inference workloads. We do not claim prospective clinical validation. Source code and deployment manifests are available at https://github.com/nucleusai/sepsisai-orchestrator.
【9】Don't Collapse Your Features: Why CenterLoss Hurts OOD Detection and Multi-Scale Mahalanobis Wins
标题：不要崩溃您的功能：为什么CenterLoss会损害OOD检测和多规模Mahalanobis获胜
链接：https://arxiv.org/abs/2605.21493
摘要：The ability to detect out-of-distribution (OOD) inputs is fundamental to safe deployment of machine learning systems. Yet, current methods often rely on feature representations that are optimised solely for classification accuracy, neglecting the distinct requirements of epistemic uncertainty. We introduce GOEN (Geometry-Optimised Epistemic Network), a simple pipeline that combines multi-scale features, L2 normalisation, Mahalanobis distance, and a calibration head trained with real hard OOD examples. Through systematic ablation we uncover a counter-intuitive finding: CenterLoss, a popular regulariser for feature compactness, significantly degrades OOD detection performance, reducing average OOD AUROC from 0.9483 to 0.9366 despite improving classification accuracy. The best variant, GOEN-NoCenterLoss, achieves an average OOD AUROC of 0.9483, surpassing all baselines including deep ensembles (0.8827), KNN (0.8967), and ODIN (0.8870) on CIFAR-10 benchmarks, while maintaining competitive in-distribution accuracy. Our results challenge the prevailing assumption that better classification geometry automatically leads to better epistemic uncertainty. Instead, we show that overly tight feature clusters compress inter-class margins and distort the covariance structure needed for effective OOD detection. GOEN is efficient, training in under 20 minutes on a single GPU, and provides a practical blueprint for building AI systems that reliably recognise their own limitations.
分类|识别(7篇)
【1】Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
标题：激活后的阅读任务失败：GPT-2的稀疏特征审计（间接对象识别）
链接：https://arxiv.org/abs/2605.22719
备注：10 pages, 7 figures
摘要：
【2】Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning
标题：基于时间非同步对齐对比学习的跨学科脑电情绪识别
链接：https://arxiv.org/abs/2605.22379
备注：16 pages, 7 figures
摘要：With the advancement of science and technology, the importance of emotion research has become increasingly evident. Electroencephalography (EEG)-based emotion recognition has emerged as an active research area in recent years, owing to its objectivity and high temporal resolution. However, most existing methods focus on optimizing encoder structures to enhance feature extraction capabilities, while paying relatively little attention to similarity calculation strategies, particularly overlooking the potential temporal misalignment of responses among different subjects. To address these shortcomings, this paper draws inspiration from the late interaction mechanism of ColBERT in natural language processing (NLP) and proposes a Temporal Asynchronous Alignment-based Contrastive Learning (TA2CL) framework. This method transforms the traditional global "hard alignment" similarity calculation approach into a fine-grained local matching mechanism, enabling the model to adaptively search for and align "locally highly correlated" segments between two EEG signals, thereby effectively mitigating the effects of inter-subject differences and temporal delays. Experimental results demonstrate that the proposed method achieves strong performance across multiple public datasets. Specifically, on the FACED dataset, it achieves an accuracy of 64.5% for the nine-class classification task and 79.5% for the binary classification task, while on the SEED and SEED-V datasets, it achieves accuracies of 86.4% and 70.1%, respectively, validating the method's effectiveness and generalization capability.
【3】A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification
标题：在线Softmax分类中三分之一缩放的边界层机制
链接：https://arxiv.org/abs/2605.22341
备注：20 pages, 7 figures
摘要：Hard-label classification is usually trained with smooth surrogate losses, most prominently softmax cross-entropy. We isolate an asymptotic mechanism by which this mismatch between smooth surrogate and discrete labels produces power-law learning curves in an online teacher-student model. After subtracting the mean logit, the thermodynamic-limit dynamics close in centered variables: a growing centered student-teacher alignment $D$ and the residual student variance $Δ$. At late times, examples away from teacher decision boundaries are already classified confidently and contribute exponentially little. Only boundary layers of width $O(D^{-1})$ remain active, while the noise of fixed-learning-rate online gradient descent maintains a nonzero $Δ$. As a function of the training time $α$ the late-time solution yields a $α^{-1/3}$ power law not only for the test loss but also for the generalization error $ε_g$, i.e., one minus test accuracy. This is much slower than the $α^{-1}$ Bayes-optimal reference for the same model. We further show that learning-rate schedules can improve the generalization error towards a $ε_g \sim α^{-1/2}$ power law. Simulations support the predicted order parameter dynamics and learning curves. Controlled experiments with correlated Gaussian inputs and whitened pretrained features show that data structure can dominate transients. Therefore, our result is an asymptotic, complementary mechanism rather than an alternative to spectral explanations of neural scaling laws.
【4】An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion
标题：基于OSC辅助的异类传感器融合的Bayesian对象分类证据层次
链接：https://arxiv.org/abs/2605.22259
备注：6 pages, 1 figure; \c{opyright} 2026 The Authors. Submitted to the 2026 IEEE International Conference on Multisensor Fusion and Integration (MFI 2026). Under review
摘要
：Heterogeneous sensor fusion is vital for detecting, localizing, and classifying CBRNE threats. However, individual sensors are often only capable of detecting a subset of relevant threats with varying reliability or can even provide only indirect threat indications, making threat classification challenging. Furthermore, high clutter rates on the sensor side present a great challenge for fusion systems. Additionally, the limited availability of high quality datasets hinders the advancement of learning-based detection and classification models in smart sensors. To mitigate these sensor related shortcomings, a context-aware and domain knowledge-enhanced fusion process is proposed. First, a novel evidence hierarchy is established that enables modeling of direct, indicative, and contextual information. Second, contextual information about the environment is introduced into the fusion process, by collecting, processing, and exploiting OSINT inputs. Third, all levels of the evidence hierarchy are used to craft a Bayesian threat type classification mechanism with domain knowledge-informed priors. The proposed methodology is evaluated in simulated scenarios, and the results demonstrate the benefit of the proposed fusion approach in terms of robustness to clutter and prior mismatch, with an overall classification accuracy of up to 95%.
【5】Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series
标题：原型引导分类子任务脱钩框架：增强多元时间序列的概括性和可解释性
链接：https://arxiv.org/abs/2605.22055
摘要：Time Series Classification (TSC) is a long-standing research problem that has gained increasing attention in recent years with the rapid growth of large-scale temporal data. Despite substantial progress enabled by deep learning, designing TSC models that are both accurate and interpretable remains a challenging task. Many existing approaches adopt a direct feature-to-label classification paradigm, by collapsing high-dimensional temporal embeddings into class logits via a single linear projection (often after global pooling), the paradigm conflates feature extraction and decision logic into an inseparable mapping. To address these limitations, we propose PDFTime, a prototype-guided framework that reformulates time series classification as a multi-stage decision process. Instead of direct feature-to-label mapping, PDFTime leverages learned prototypes to approximate class-conditional feature distributions in the latent space, enabling progressive discrimination through classification sub-tasks of varying granularity. To our knowledge, PDFTime is the first framework to reformulate time series classification as a decoupled, multi-stage similarity-based reasoning process, breaking the long-standing paradigm of direct, black-box feature-to-label mapping. Extensive evaluations demonstrate that PDFTime achieves state-of-the-art (SOTA) performance across UEA and UCR benchmarks. Notably, it secures the top-$1$ accuracy on 80 out of 128 datasets in the UCR archive, significantly outperforming recent strong baselines in both consistency and generalization.
【6】CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
标题：CASE-NET：通过因果注意力和通道重新校准进行深度时空表示学习用于多元时间序列分类
链接：https://arxiv.org/abs/2605.22043
备注：9 pages, 6 figures, 2 tables
摘要：Multivariate time series (MTS) classification is foundational to pervasive computing and financial analysis, yet existing multi-scale paradigms are often constrained by suboptimal representation fidelity. We identify two critical bottlenecks: temporal non-causality in standard encoders that induces temporal confounding in non-stationary dynamics, and the absence of explicit channel saliency mechanisms that allows noise to contaminate the latent space. To address these challenges, we propose the Causal Attention and Spatio-temporal Encoder Network (CASE-NET), an architecture designed for structural manifold pre-conditioning. CASE-NET synergizes a Causal Temporal Encoder, which enforces physical arrow-of-time constraints via masked self-attention and causal convolutions, with an Adaptive Channel Recalibration module functioning as an information bottleneck to suppress detrimental noise. Comprehensive evaluations across six heterogeneous domains demonstrate that CASE-NET establishes new state-of-the-art benchmarks on four tasks, achieving a peak accuracy of 98.6% on the AWR dataset and superior robustness in non-stationary regimes.
【7】Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification
标题：纠正先验数据匹配网络中的类别不平衡以实现表格分类
链接：https://arxiv.org/abs/2605.21742
备注：5 pages, 6 figures, Information Theory Workshop (ITW)
摘要：Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the effect of class imbalance, resulting in poor performance for rare classes. Several techniques exist which attempt to mitigate the deleterious effect of class imbalance on classification performance, but the in-context learning (ICL) dynamic of PFNs means that loss-based strategies are impossible, and other techniques are unproven. We have adapted several classical techniques addressing class imbalance and analyzed their performance on PFN classification. We observe that thresholding performs exceptionally well because of the calibration characteristics of PFNs, and downsampling performs comparably because of PFNs exceptional limited-data performance, with the additional benefit of reduced computation cost for inference.
表征(2篇)
【1】The Matching Principle: A Geometric Theory of Loss Functions for Nuisance-Robust Representation Learning
标题：匹配原则：用于滋扰鲁棒性表示学习的损失函数几何理论
链接：https://arxiv.org/abs/2605.22800
备注：54 pages. 13 empirical task blocks. Companion software: matching-pmh (PyPI; this https URL). Related arXiv note: 2604.21395 (geometric blind spot / isotropic PMH)
摘要：
【2】Representation Gap: Explaining the Unreasonable Effectiveness of Neural Networks from a Geometric Perspective
标题：表示差距：从几何角度解释神经网络的不合理有效性
链接：https://arxiv.org/abs/2605.21692
摘要：Characterizing precisely the asymptotic generalization error of neural networks using parameters that can be estimated efficiently is a crucial problem in machine learning, which relies heavily on heuristics and practitioners' intuition to make key design choices. In order to mitigate this issue, we introduce the Representation Gap, a metric closely related to the generalization error, but admitting better-behaved asymptotic dynamics. Focusing on equivariant diffusion models and leveraging results from optimal quantization and point-process theory, we derive a precise asymptotic equivalent of the Representation Gap and show that it is governed by a single parameter, the \textit{intrinsic dimension} of the task, which is easy to interpret, efficient to estimate, and can be linked to the equivariances of common neural network architectures. We show that this asymptotic dynamic also extends to a broader range of tasks and training algorithms. Finally, we demonstrate empirically that our asymptotic law and intrinsic dimension estimation are accurate on a wide range of synthetic datasets, where these quantities are known, as well as on more realistic datasets, where we obtain results consistent with the related literature.
3D|3D重建等相关(2篇)
【1】Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration
标题：请记住保持好奇：3D探索的场景背景和持久世界
链接：https://arxiv.org/abs/2605.22814
摘要：
【2】SceneAligner: 3D-Grounded Floorplan Localization in the Wild
标题：SceneAligner：3D接地平面图野外本地化
链接：https://arxiv.org/abs/2605.22581
备注：Project Page: this https URL
摘要：
编码器(1篇)
【1】BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model
标题：BEiTScore：使用高效的交叉编码器模型进行无参考图像字幕评估
链接：https://arxiv.org/abs/2605.21728
摘要：Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating long-form and context-rich descriptions. State-of-the-art evaluation metrics involve extensive computational costs associated with the use of Large Language Models (LLMs) as judges, or instead suffer from the limitations of standard CLIP-based encoders, such as strict token limits, lack of fine-grained sensitivity, or lack of compositional generalization by treating captions as ``bags-of-words.'' We propose a new learned metric that tackles the aforementioned challenges, based on a lightweight cross-encoder that is initialized from a visual question-answering model checkpoint, balancing a strong weight initialization with computational efficiency. Our training scheme uses a carefully assembled data mixture for supervised learning, featuring adversarial LLM-based data augmentations to enhance model sensitivity to fine-grained visual-linguistic errors. We also introduce a new benchmark designed to assess detailed captioning evaluation across diverse scenarios. Experimental results demonstrate that the proposed metric achieves state-of-the-art performance while maintaining the efficiency required for large-scale benchmarking, quality-aware decoding, or reward guidance.
优化|敛散性(16篇)
【1】Vector Policy Optimization: Training for Diversity Improves Test-Time Search
标题：载体策略优化：多样性训练改善测试时间搜索
链接：https://arxiv.org/abs/2605.22817
备注：24 pages
摘要：
【2】Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning
标题：多个神经运算符实现多任务学习的接近最优速率
链接：https://arxiv.org/abs/2605.22724
摘要：
【3】A note on convergence of Wasserstein policy optimization
标题：关于沃瑟斯坦政策优化收敛的注释
链接：https://arxiv.org/abs/2605.22622
摘要：
【4】Regret-Based $(ε,δ)$-optimal Stopping Criteria for Bayesian Optimization
标题：基于遗憾的$（e，δ）$-最优Bayesian优化停止准则
链接：https://arxiv.org/abs/2605.22561
备注：21 pages
摘要：
【5】Bandit Convex Optimization with Gradient Prediction Adaptivity
标题：具有梯度预测自适应性的Bandit凸优化
链接：https://arxiv.org/abs/2605.22191
摘要：Bandit convex optimization (BCO) is a fundamental online learning framework with partial feedback, where the learner observes only the loss incurred at the chosen decision point in each round. In this work, we investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner. Specifically, given gradient predictions $m_t$, we seek regret bounds that scale with the cumulative prediction error $S_T=\sum_{t=1}^T \|\nabla f_t(x_t)-m_t\|^2.$ We first establish a negative result: under the single-point feedback protocol, an unavoidable $Ω(\sqrt{T})$ regret lower bound persists even when $S_T=o(T)$, showing that the variance of gradient estimation fundamentally obscures the benefit of accurate predictions. To overcome this barrier, we propose \emph{Two-Point Variance-Reduced Optimistic Gradient Descent} (TP-VR-OPT) for the two-point feedback setting. The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm. This yields a regret bound of $O\big(\sqrt{d\,\mathbb{E}[S_T]}\big),$ where $d$ is the decision dimension. Complementing this result, we establish an information-theoretic lower bound that scales as $Ω(\sqrt{\mathbb{E}[S_T]})$, providing a fundamental characterization of the best achievable prediction-adaptive regret and showing that TP-VR-OPT is optimal up to a factor of $\sqrt d$. We further develop adaptive variants that eliminate the need for prior knowledge of $\mathbb{E}[S_T]$ or the horizon $T$, and extend our framework to non-stationary environments, establishing dynamic regret guarantees that adapt simultaneously to the cumulative prediction error and the comparator path length.
【6】From Sequential Nodes to GPU Batches: Parallel Branch and Bound for Optimal $k$-Sparse GLMs
标题：从顺序节点到图形处理：最优$k$-稀疏GLM的并行分支和边界
链接：https://arxiv.org/abs/2605.22188
摘要：GPUs have significantly accelerated first-order methods for large-scale optimization, especially in continuous optimization. However, this success has not transferred cleanly to problems with discrete variables, combinatorial structure, and nonlinear objectives, such as certifying optimal solutions for cardinality-constrained generalized linear models. Major challenges include the sequential processing of heterogeneous nodes in branch and bound (BnB) and frequent data movement between the CPU and GPU. We propose a simple, generic, and modular CPU--GPU framework that processes multiple BnB nodes in batches on GPUs. The framework is built around a small set of GPU-efficient routines and uses padding together with lightweight custom kernels to handle irregular node data structures. Experiments show one to two orders of magnitude speedups and zero optimality gap on challenging instances. The framework can also be extended to collect the entire Rashomon set, enabling downstream statistical analysis such as variable-importance analysis and model selection under secondary user-specific measures (e.g., AUC in classification).
【7】ECPO: Evidence-Coupled Policy Optimization for Evidence-Certified Candidate Ranking
标题：ECPO：证据认证候选人排名的证据耦合政策优化
链接：https://arxiv.org/abs/2605.21993
摘要
：Ranking systems used in decision-support settings should not only order candidates but also expose evidence that can be independently checked. We study evidence-certified candidate ranking: given an intent_id, a predefined plan skeleton, a window-local candidate roster, and text-derived candidate trajectories with span provenance, a system must output a Top-K list together with doc_id:span evidence certificates whose cited spans are sufficient to recover the decision. We instantiate this task on MAVEN-ERE and RAMS with fixed upstream extraction, window-local randomized candidate identifiers, skeleton-aligned trajectory supervision, hard negatives, and audit references. We introduce Evidence-Coupled Policy Optimization (ECPO), a listwise policy-optimization objective whose action is the joint object of ranking and evidence certificate. ECPO first learns an interpretable trajectory reward from skeleton alignment, argument consistency, and optional graph features; it then optimizes a constrained policy with three coupled rewards: listwise ranking utility, span-level certificate validity, and an evidence-cycle reward computed by a label-free deterministic verifier that reconstructs candidate support from claim-stripped cited spans. This reframes the goal from maximizing ordinary NDCG alone to maximizing CertNDCG and decision-evidence coupling. The evaluation compares ECPO against zero-shot, SFT, and GRPO policies, RM-only scoring with deterministic evidence attachment, grammar/JSON-constrained decoding, validator retry, best-of-N RM selection, and post-hoc evidence rationalization under closed-roster, predicted-roster, and hybrid-roster settings.
【8】Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning
标题：审核Rényi差异私有机器学习的最佳保证
链接：https://arxiv.org/abs/2605.21938
备注：28 pages, 3 figures
摘要：We study black-box auditing for machine learning algorithms that claim R \ 'enyi differential privacy (RDP) guarantees. We introduce an auditing framework, based on hypothesis testing, that directly estimates Rényi divergence between neighboring executions using the Donsker-Varadhan (DV) variational estimator. Our analysis yields explicit and non-asymptotic confidence intervals for RDP auditing via class-restricted DV estimators, separating statistical estimation error from algorithmic privacy leakage. We prove matching minimax lower bounds showing that, up to logarithmic factors, our sample-complexity guarantees are information-theoretically optimal, thereby establishing the first optimal guarantees for auditing RDP via DV estimators. Empirically, we instantiate our framework for auditing DP-SGD in a fully black-box setting. Across MNIST and CIFAR-10, and over a wide range of privacy regimes, our auditors produce a strong overall improvement on empirical RDP lower bounds compared to prior state-of-the-art black-box methods especially at small and moderate Rényi orders where accurate auditing is most challenging.
【9】Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
标题：扩散模型的噪音时间表设计：最优控制的角度
链接：https://arxiv.org/abs/2605.21911
摘要：We develop a principled framework for analyzing and designing noise schedules in diffusion models. We show that one can recast this design problem as an optimal control problem, whose state is the Fisher information of the diffusion process which evolves according to an ODE and the control input is the noise schedule. The objective of the optimal control problem is a functional involving the Fisher information, which is shown to be an upper bound on the Kullback-Leibler sampling error. By solving this optimal control problem, we obtain sufficient conditions on noise schedules under which state-of-the-art $\tilde{\mathcal{O}} (d/n)$ sampling error is achievable, where $d$ is the data dimension and $n$ is the number of discretization steps. While existing theoretical work also prove that $\tilde{\mathcal{O}}(d/n)$ sampling error bounds are achievable, these results hold for specific noise schedules, which do not include the schedules used in practice. Under a further parametric assumption on the data distribution, we show that one can obtain closed-form expressions for the noise schedules. These noise schedules generalize standard empirical schedules such as exponential and sigmoid schedules by allowing additional parameters that can be tuned. Systematically tuning the parameters of these schedules yields new schedules that achieve superior FID scores on image generation benchmarks.
【10】Residual Skill Optimization for Text-to-SQL Ensembles
标题：Text-to-SQL集成的剩余技能优化
链接：https://arxiv.org/abs/2605.21792
摘要：Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K. On Spider2-Lite, DivSkill-SQL improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline, with consistent gains across two base models (Opus-4.6 and GPT-5.4). Skills optimized on a single dialect transfer without retraining across dialects (Snowflake, BigQuery, SQLite) and to a different task formulation, such as BIRD-Critic (+2.6 pts). Error diagnostics show up to 3x fewer hallucinated schema references and function calls, indicating that gains come from genuinely reliable complementary skills rather than surface-form variation.
【11】Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization
标题：模型可以建模，但不能绑定：文本优化中的结构化基础
链接：https://arxiv.org/abs/2605.21751
摘要：Text-to-optimization requires two separable capabilities: modeling -- choosing the right optimization structure -- and binding -- grounding every coefficient, index, and parameter in the concrete problem data. We study this via Text2Opt-Bench, a scalable benchmark of solver-verified optimization problems spanning 12 categories, from textbook linear programs to stochastic and multi-objective formulations with up to thousands of variables. Across 10+ models, we find that accuracy collapses as instance data grows, even when the formulation itself is simple. We call this the effective binding limit. We address this via a simple inference-time approach, BIND, which externalizes numeric data to structured files so the model binds data programmatically rather than transcribing from the prompt. BIND improves GPT-5-Nano from 59.1% to 82.4% accuracy, matching pass@5 (82.0%) at lower token cost than pass@1, and GPT-5 from 86.2% to 95.8%. Furthermore, we validate our hypothesis by finetuning a model exclusively on binding and show that it outperforms end-to-end SFT and RL across three structurally distinct optimization categories, with a 1.5B binding specialist alone matching a 7B end-to-end baseline.
【12】Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos
标题：Dropout普适性：标度律与混沌边缘的最优调度
链接：https://arxiv.org/abs/2605.21648
备注
：Accepted at the 43rd International Conference on Machine Learning (ICML 2026). 36 pages, 11 figures
摘要：We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos. Dropout shifts the perfect-alignment fixed point, making the depth scale for information propagation finite even at critical initialization. We derive critical and crossover scaling laws for correlation decay and establish that smooth activations and kinked, ReLU-like activations constitute distinct universality classes, with different critical exponents and a universal two-parameter scaling collapse in detuning and dropout strength. The distinction traces to the analytic structure of the correlation map: smooth activations admit a Taylor expansion near perfect alignment, while kinked activations develop a branch point with universal non-analyticity. As a corollary, the framework yields saturated dropout profiles under fixed budget; a rank-flow tie-breaker then selects front-loaded schedules, substantially reducing held-out test loss at no extra computational cost, with accuracy gains as a consistent secondary effect. We test the predictions in MLPs and Vision Transformers and discuss CNN/ResNet extensions.
【13】Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising
标题：超越单槽：多槽保证展示广告的联合优化
链接：https://arxiv.org/abs/2605.21556
备注：Accepted at SIGIR Industry Track 2026
摘要：Guaranteed display advertising is crucial for platform monetization, yet existing methods often operate under a single-slot assumption, limiting their ability to optimize allocation across multi-slot page views. In this paper, we propose a novel joint optimization framework for multi-slot GD allocation, addressing key challenges such as slot-level redundancy, contract imbalance, and exposure concentration. Our approach formulates the allocation as an offline bipartite matching problem with a contract roulette mechanism for slot exclusivity and Page View constraints for impression control, and incorporates a scalable allocation optimization algorithm for efficient large-scale deployment. Extensive online tests on the Meituan advertising platform demonstrate that our method significantly improves merchant ROI, platform revenue efficiency, and contract fulfillment robustness. Specifically, online A/B tests show a 28.99% increase in Average Revenue Per User under 70% traffic, and DID analysis further indicates improved contract stability, demonstrating the strong applicability and effectiveness of our framework in real-world advertising deployments.
【14】A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction
标题：一个可重复的日志驱动AutoML框架，用于医疗保健风险预测中的可解释管道优化
链接：https://arxiv.org/abs/2605.21528
摘要：Accurate and reproducible disease risk prediction remains challenging due to heterogeneous features, limited samples, and severe class imbalance. This study introduces yvsoucom-iterkit, a deterministic and log-driven automated machine learning framework that formulates pipeline optimization as a fully reproducible, configuration-level system. Each pipeline is encoded as a traceable log entity, enabling analysis of component attribution, interactions, similarity, and cross-seed robustness. Experiments on the Pima Indians Diabetes and Stroke datasets across more than 18,000 pipeline configurations reveal a structured and partially redundant search space, where performance is governed by a small subset of interacting components. Random Forest importance analysis identifies augmentation (0.454), model choice (0.198), and imbalance handling (0.101) as key drivers on Pima, while imbalance handling dominates Stroke (0.406). Component similarity analysis shows strong redundancy, with feature selection variants (biMax-biMean) exhibiting low RMS distance (0.0252), mixup closely matching no augmentation (0.0279), and TomekLinks aligning with no imbalance handling (0.0325), whereas Gaussian noise shows greater divergence from no augmentation (0.10). The framework achieves strong and stable performance using ensemble models (Weighted-F1 0.89, Macro-F1 0.88 on Pima; Weighted-F1 0.94 on Stroke), while Macro-F1 remains lower on Stroke (0.67) due to class imbalance. Cross-seed analysis reveals a performance-robustness trade-off, with ensembles showing lower variability (0.023-0.026) than SVM. These results indicate that effective AutoML optimization can focus on a reduced set of high-impact components.
【15】Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
标题：保守和非保守漂移模型的粒子收敛率
链接：https://arxiv.org/abs/2605.22795
摘要：We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting velocity by a kernel density estimator (KDE)-gradient velocity, namely the difference of the kernel-smoothed data score and the kernel-smoothed model score. This velocity is a gradient field, addressing the non-conservatism issue identified for general displacement-based drifting fields. We prove continuous-time finite-particle convergence bounds for the conservative method on $\R^d$: a joint-entropy identity yields bounds for the empirical Stein drift, the smoothed Fisher discrepancy of the KDE, and the squared center velocity. The main finite-particle correction is a reciprocal-KDE self-interaction term, and we give deterministic and high-probability local-occupancy conditions under which this term is controlled. We keep the quadrature constants explicit and track their possible bandwidth dependence: the root residual-velocity rate $N^{-1/(d+4)}$ holds under an additional $h$-uniform quadrature regularity condition, while a more general growth condition yields the optimized root rate $N^{-(2-β)/(2(d+4-β))}$, where $0\le β<2$. We also analyze the non-conservative drifting method with Laplace kernel, corresponding to the original displacement-based velocity proposed in~\cite{deng2026drifting}. For this method, a sharp companion kernel decomposes the velocity into a positive scalar preconditioning of a sharp-score mismatch plus a Laplace scale-mismatch residual, producing an analogous finite-particle rate with an unavoidable residual term. Finally, we explain how the continuous-time residual-velocity bounds translate into one-step generation guarantees through the explicit drift size $η$.
【16】Optimization over the intersection of manifolds
标题：多边形交集的优化
链接：https://arxiv.org/abs/2605.22736
备注：26 pages, 5 figures, 3 tables
摘要：Optimization over the intersection of two manifolds arises in a broad range of applications, but is hindered by the coupled geometry of the feasible region. In this paper, we prove that the regularities -- clean intersection and intrinsic transversality -- are equivalent, which yields a tractable projection onto the tangent space of the intersection. Therefore, we propose a geometric method that employs a retraction on only one manifold and updates the iterate along two orthogonal directions. Specifically, the iterates stay on one manifold, and the two directions are responsible for asymptotically approaching the other manifold and decreasing the objective function, respectively. Under intrinsic transversality, we derive the convergence rate for both the feasibility and optimality measures, and show that every accumulation point is first-order stationary. Numerical experiments on problems stemming from sparse and low-rank optimization, including fitting spherical data, approximating hyperbolic embeddings on real data, and computing compressed modes, demonstrate the effectiveness of the proposed method.
预测|估计(8篇)
【1】Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market
标题
：混合Kolmogorov-Arnold网络和XGBOP框架用于澳大利亚国家电力市场未来一周价格预测
链接：https://arxiv.org/abs/2605.22387
备注：The 24th IEEE International Conference on Industrial Informatics, 2026
摘要：Accurate electricity price forecasting (EPF) is essential for market participants to support operational planning and risk management, yet remains challenging due to strong volatility, nonlinear dynamics, and frequent extreme price spikes. These challenges are particularly pronounced in the Australian National Electricity Market (NEM), where high renewable penetration further increases uncertainty. This paper investigates week-ahead electricity price forecasting and proposes a hybrid KAN+XGBoost framework that integrates Kolmogorov-Arnold Networks (KAN) with tree-based learning. The proposed approach combines the global nonlinear representation capability of KAN with the local robustness of XGBoost to capture both long-term dependencies and short-term price fluctuations. Experiments are conducted on real-world NEM data using an expanding window evaluation strategy. The results demonstrate that the proposed model outperforms benchmark methods, including SARIMAX, Long Short-Term Memory (LSTM), standalone KAN, and XGBoost, reducing MAE by approximately 12% compared to XGBoost and by over 50% compared to a naive baseline. The results suggest that hybrid learning strategies provide an effective and robust solution for electricity price forecasting in highly dynamic electricity markets.
【2】TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting
标题：TimeGuard：针对时间序列预测中后门防御的队列池训练
链接：https://arxiv.org/abs/2605.22365
备注：44 pages, 30 figures. ICML 2026
摘要：Time Series Forecasting (TSF) plays a critical role across many domains, yet it is vulnerable to backdoor attacks. However, backdoor defenses tailored to TSF remain underexplored, due to data entanglement and task-formulation shift challenges. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to training-loss degeneration, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting $\mathrm{MAE}_\mathrm{P}$ by $1.96\times$ over the leading baseline, while preserving clean performance within 5% $\mathrm{MAE}_\mathrm{C}$.
【3】Learning Causal Orderings for In-Context Tabular Prediction
标题：学习上下文内表格预测的因果顺序
链接：https://arxiv.org/abs/2605.22335
摘要：In-context learning for tabular data sets strong predictive standards in observational settings; it however primarily relies on correlational structure, which becomes unreliable under distribution shift or intervention. While established methods to discover causal structure exist, they are often focused on structure identifiability and decoupled from the predictive architectures that could benefit from them. To bridge these perspectives, we study how to simultaneously infer and enforce causal structure in the form of topological variable orderings into tabular prediction. Unlike standard architectures, our model TabOrder uses causal order-constrained attention, basing predictions only on features that precede a target under a learned causal order. Similar to causal discovery methods, TabOrder learns the optimal variable ordering in an unsupervised manner through a likelihood-based objective. We justify this choice under standard functional model classes and also study how sample missingness, a common challenge in tabular data, interacts with causal direction identification. Empirically, we confirm that TabOrder recovers accurate variable orderings while addressing prediction and imputation tasks, as well as gives insight into real-world biological data under intervention.
【4】When to Switch, Not Just What: Transition Quality Prediction in Clash Royale
标题：何时切换，而不仅仅是什么：《《皇室战争》》中的过渡质量预测
链接：https://arxiv.org/abs/2605.21868
备注：11 pages, 2 figures, 4 tables; Accepted at IEEE Conference on Games (CoG) 2026
摘要：In competitive games, players frequently switch strategies after losing streaks, yet our analysis of 926,334 match records from 34,619 Clash Royale players reveals a counterintuitive pattern: switching frequency is inversely associated with the win rate, with effects that vary substantially across players and situational contexts. We attribute this to a limitation common in many prior recommendation systems, which evaluate strategies by expected quality while overlooking the behavioral cost of switching and individual differences in switching propensity. We refer to this implicit premise as the Zero Switching Cost Assumption. To address this, we reformulate strategy recommendation as a transition-level decision problem and instantiate it as TQP (Transition Quality Predictor), a three-stage pipeline structured as Who -> When -> What. PersonaGate suppresses recommendations for players whose strategic consistency is empirically associated with superior outcomes. TimingGate identifies moments when switching is likely to yield a net benefit over staying, using a subtype- and state-matched baseline to control for natural win-rate recovery. ScoreFusion ranks candidate strategies by combining an adoptability signal with predicted transition quality (delta WR). We further introduce SwitchGap, an evaluation metric that measures a policy's discriminative quality without treating observed player choices as optimal ground truth. This property is particularly important because the most frequent switchers record the lowest win rates. The full pipeline achieves a SwitchGap of +10.4 percentage points at a recommendation rate of 5.4%, and loss-triggered switchers, despite being the lowest-performing group, benefit the most from subtype-conditioned guidance.
【5】PeakFocus: Bridging Peak Localization and Intensity Regression via a Unified Multi-Scale Framework for Electricity Load Forecasting
标题：PeakFocus：通过统一的多尺度电力负荷预测框架弥合峰值本地化和强度回归
链接：https://arxiv.org/abs/2605.21550
摘要
：Electricity load peak forecasting (ELPF), simultaneously predicting peak timing and intensity, is a prerequisite for effective grid scheduling and risk management. However, existing methods face three limitations. First, they adopt a two-stage predict-then-locate paradigm, which severs the link between temporal localization and intensity regression. Second, they still struggle with the multi-scale representation conflict, leading to peak misjudgment and timing misalignment. Third, the lack of explicit peak timing context during intensity regression causes intensity smoothing because predictions are dominated by global smoothing trends. To address these limitations, we propose PeakFocus, a unified framework for ELPF. (i) A Unified Peak-Aware Pipeline (UPAP) utilizes a triple hybrid loss to jointly supervise temporal localization and intensity regression, alongside a tolerance-based evaluation protocol. (ii) A Multi-Scale Mixing Peak Locator (MSM-PL) exploits coarse-grained features to mitigate peak misjudgment caused by local fluctuations, and injects them into fine-grained features via a cascade mechanism to resolve timing misalignment. (iii) A Location-Aware Decoder (LAD) injects peak timing context into the intensity regression process, providing explicit guidance to counteract intensity smoothing and improve peak intensity estimation. Extensive experiments on the public Electricity (ELC) dataset and our industrial-scale World Large-scale Electricity Load (WLEL) dataset show that PeakFocus outperforms baselines in both timing precision and intensity estimation.
【6】Local Covariate Selection for Average Causal Effect Estimation without Pretreatment and Causal Sufficiency Assumptions
标题：在没有预治疗和因果充分性假设的情况下平均因果效应估计的局部协变量选择
链接：https://arxiv.org/abs/2605.21548
摘要：We study the problem of selecting covariates for unbiased estimation of the total causal effect.Existing approaches typically rely on global causal structure learning over all variables, or on strong assumptions such as causal sufficiency - where observed variables share no latent confounders - or the pretreatment assumption, which limits covariates to those unaffected by the treatment or outcome. These requirements are often unrealistic in practice, and global learning becomes computationally prohibitive in high-dimensional settings.To address these challenges, we propose a novel local learning method for covariate selection in nonparametric causal effect estimation that avoids both the pretreatment and causal sufficiency assumptions. We first characterize a local boundary that contains at least one valid adjustment set whenever one exists for identifying the causal effect, and then develop local identification procedures to efficiently search within this boundary.We prove that the proposed method is sound and complete. Experiments on multiple synthetic datasets and two real-world datasets show that our approach achieves accurate causal effect estimation while substantially improving computational efficiency.
【7】Visibility nowcasting in South Korea: a machine learning approach to class imbalance and distribution shift
标题：韩国的可见性即时预报：解决阶级失衡和分布转变的机器学习方法
链接：https://arxiv.org/abs/2605.21507
备注：Published in Theoretical and Applied Climatology
摘要：Atmospheric visibility is a critical variable for transportation safety and air quality management, however, accurate prediction remains challenging due to the complex interactions between meteorological conditions and air pollutants, as well as the rarity of low-visibility events. This study introduces a machine learning framework to nowcast visibility in six major South Korean cities. To handle the imbalance in the 2018-2020 training data, we applied the Synthetic Minority Over-sampling Technique with Nominal and Continuous (SMOTENC) and Conditional Tabular Generative Adversarial Network (CTGAN). An ensemble approach combining machine learning and deep learning models was then used and evaluated on a 2021 test dataset. The results revealed a marked decline in predictive performance in the test set compared to the cross-validation phase. This degradation was attributed to a distributional shift between training and testing periods, which was quantitatively confirmed by measuring the Wasserstein distance of the most influential feature identified by SHAP analysis. In general, this study presents a methodology that aims to simultaneously address the dual challenges of data imbalance and temporal distributional shifts, and emphasizes the necessity of accounting for evolving external environmental factors when implementing nowcasting models on time-series data.
【8】Conditional Neural Field based Reduced Order Model for Dynamic Ditching Load Prediction
标题：基于条件神经场的动态沟渠负荷预测降阶模型
链接：https://arxiv.org/abs/2605.21499
摘要：Grid-based neural networks such as convolutional autoencoders are widely used in dimension reduction-based surrogate models for computational fluid dynamics. In recent years, the use of coordinate-based approaches like conditional neural fields has emerged. Their independence of the spatial discretization is a beneficial feature for various applications in computational fluid dynamics. This paper discusses the spatio-temporal prediction of aircraft ditching loads using a conditional neural field approach. The model is evaluated using two datasets for the dynamic loads of the fuselage of a DLR-D150 aircraft, one of which relates to a single fixed spatial discretization and the other that includes data from different discretizations. When paired with a long short-term memory (LSTM) network in the latent space, the neural field-based model achieves a spatio-temporal prediction accuracy for the first data set that is close to that of grid-dependent convolutional autoencoder-based models, and with significantly less parameters. Results for the second data set demonstrate the ability of the neural field-based approach to reconstruct ditching loads accurately for heterogeneous spatial discretizations. This allows for flexible use of training datasets generated for different geometries and/or discretizations, as well as the use of the surrogate model to predict loads for different configurations.
其他神经网络|深度学习|模型|建模(29篇)
【1】MambaGaze: Bidirectional Mamba with Explicit Missing Data Modeling for Cognitive Load Assessment from Eye-Gaze Tracking Data
标题：MambaGaze：具有显式缺失数据建模的双向Mamba，用于根据眼睛凝视跟踪数据进行认知负荷评估
链接：https://arxiv.org/abs/2605.22775
备注：Submitted to IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI 2026)
摘要：
【2】Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
标题：重新审视均匀扩散模型：留一去降噪剂和吸收状态重新表述
链接：https://arxiv.org/abs/2605.22765
备注：preprint
摘要：
【3】Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
标题：现场音乐扩散模型：交互式扩散音乐生成器的高效微调和后训练
链接：https://arxiv.org/abs/2605.22717
摘要：
【4】Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms
标题：无卡人工智能银行创新：使用机器学习算法实现网络安全和欺诈缓解的综合框架
链接：https://arxiv.org/abs/2605.22604
摘要：
【5】Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network
标题：因子扩散政策：具有单评分网络的成分广义机器人控制
链接：https://arxiv.org/abs/2605.22596
摘要：
【6】A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models
标题：扩散理论：从方程到扩散模型
链接：https://arxiv.org/abs/2605.22586
备注：A detailed tutorial on Diffusion models and SDE
摘要：
【7】F-TIS: Harnessing Diverse Models in Collaborative GRPO
标题：F-TIS：在协作GRPO中利用多样化模型
链接：https://arxiv.org/abs/2605.22537
备注：Accepted to ICML 2026 Workshop Scalable Learning and Optimization for Efficient Multimodal AI Agents (SCALE)
摘要：
【8】Disentanglement Beyond Generative Models with Riemannian ICA
标题：利用Riemann ICA超越生成模型的解纠缠
链接：https://arxiv.org/abs/2605.22531
摘要：
【9】Generative Modeling by Value-Driven Transport
标题：价值驱动运输的生成建模
链接：https://arxiv.org/abs/2605.22507
摘要：
【10】The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning
标题：神经编译器：混合科学机器学习的程序到网络翻译
链接：https://arxiv.org/abs/2605.22498
备注：Use: 21 pages, 10 figures, 10 tables. Preprint; source code available at this https URL
摘要：
【11】Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
标题：神经网络的部分融合：集合和权重聚集之间的有效权衡
链接：https://arxiv.org/abs/2605.22350
备注：Accepted to ICML 2026
摘要：Ensembles of neural networks typically outperform individual networks but incur large computational costs, whereas weight aggregation produces less costly, yet also less accurate, aggregate models. We introduce partial fusion of networks, which interpolates between ensembles and weight aggregation and thus allows for a flexible tradeoff between computational cost and performance. A direct way to achieve this is to extend existing weight aggregation methods based on neuron-level similarity between different networks, where partial fusion then only aggregates weights of neurons which are most similar. We showcase one particular method to jointly identify which neurons are most similar and match them via partial optimal transport. Further, we consider the more general perspective of weight aggregation and partial fusion as generalized pruning of ensemble models, where neurons cannot just be deleted, but also linearly combined. Finally, we show that generalized pruning applied to a single network yields similar benefits as partial fusion by allowing for a tradeoff between isolating, deleting, and linearly combining neurons based on similarity. Our code is available at https://github.com/Fabian-Mor/partial_fusion_nn.
【12】From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching
标题：从快照到轨迹：通过条件流匹配学习单细胞基因表达动力学
链接：https://arxiv.org/abs/2605.22340
摘要：Single-cell RNA sequencing (scRNA-seq) provides high-dimensional profiles of cellular states, enabling data-driven modeling of cellular dynamics over time. In practice, time-resolved scRNA-seq is collected at only a few discrete time points as unpaired snapshot populations, leaving substantial temporal gaps. This motivates trajectory inference at unmeasured time points. Existing methods mainly follow two directions, optimal-transport (OT) alignment provides distribution-level matching between observed snapshots, while continuous-time generative models support forecasting via learned dynamics. However, two challenges remain: (i) unpaired snapshots render local transitions between adjacent time points ambiguous, leading to unstable supervision; and (ii) long-horizon prediction relies on repeated integration, where small modeling errors compound and cause distribution drift. To address these challenges, we propose single-cell Flow Matching (scFM), a latent generative framework based on coupling-conditioned flow matching. First, we compute entropically regularized OT couplings between adjacent snapshots and use them to construct soft, weighted flow-matching targets for learning time-dependent velocity fields. Second, we learn bidirectional velocity fields and leverage their consistency to refine couplings and improve temporal coherence under sparse supervision. Third, we introduce distribution-level alignment and latent dynamic regularization to anchor long rollouts and mitigate drift. Experiments on real-world time-series scRNA-seq datasets show that scFM consistently improves distributional prediction performance for both temporal interpolation and extrapolation. Moreover, scFM yields more accurate trajectory reconstruction and temporally coherent visualizations where intermediate time points are absent, indicating a more faithful recovery of underlying temporal gene expression dynamics.
【13】Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
标题：Riemann几何与fMRI的结合：建模相关流场和特征子空间的优势
链接：https://arxiv.org/abs/2605.22334
摘要
：Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curved geometry of correlation space. Existing geometric methods frequently lack closed-form operations or depend on arbitrary region ordering, limiting scalability. We introduce a scalable geometric framework with two components: (i) the Off-log metric, a smooth transformation mapping correlation matrices to symmetric zero-diagonal matrices. This enables closed-form expressions for distances, Frechet means, and linear models, allowing standard statistical modeling without complex manifold optimization. (ii) Grassmannian subspace discrimination, which compares subjects via principal-angle distances between eigenvector subspaces, resolving inherent sign and basis ambiguities. Both components integrate into standard machine-learning workflows for inference, regression, and classification. Validated across two clinical cohorts (Parkinson's and psychosis) and three ageing fMRI datasets, the Off-log metric increased sensitivity in permutation tests and matched or exceeded Riemannian and Euclidean baselines in classification. Brain-age prediction performance was comparable, with Riemannian metrics excelling in two of three cohorts. The Grassmannian method consistently outperformed Euclidean baselines, highlighting disease-relevant networks. Overall, geometry-aware representations improve sensitivity and predictive performance while remaining straightforward to deploy at scale.
【14】Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics
标题：利用Kolmogorov-Arnold网络实现复杂动力学的可解释发现
链接：https://arxiv.org/abs/2605.22235
备注：16 pages. Comments are welcome
摘要：Complex dynamical systems governed by holomorphic maps such as $z^2 + c$ exhibit fractal boundaries with extreme sensitivity to initial conditions. Accurately modelling these structures from data requires methods that respect the underlying complex-analytic geometry, yet Multi-Layer Perceptrons (MLPs) within Neural Ordinary Differential Equations (Neural ODEs) lack complex-analytic priors, violate the Cauchy--Riemann conditions, and function as opaque approximators incapable of yielding governing equations. We introduce Holomorphic KAN-ODE, a framework that replaces the MLP with a Kolmogorov-Arnold Network (KAN) whose learnable B-spline activations reside on network edges, and incorporates Cauchy--Riemann equations as a differentiable regularization to preserve holomorphic structure. We evaluate on six families of complex dynamical systems spanning polynomial and transcendental classes. With only 280 parameters ($16\times$ fewer than the MLP baseline), the network achieves velocity-field $R^2 > 0.95$ on all six systems, correctly identifies all six governing symbolic families through automatic spline-to-formula fitting, and reconstructs Julia set fractal boundaries with up to 98.0\% agreement. Crucially, the model exhibits only 4\% MSE degradation under 10\% observation noise versus $15.2\times$ for MLPs, and achieves 90.4\% improvement in transfer learning from quadratic to cubic dynamics. While the MLP attains lower pointwise reconstruction error due to its larger capacity, the KAN uniquely provides interpretable symbolic equations, enforced holomorphic structure, and superior noise resilience, capabilities that are entirely absent in black-box architectures. These results establish KANs as a parameter-efficient, interpretable alternative to MLPs for physics-informed discovery of holomorphic dynamics.
【15】ARC-STAR: Auditable Post-Hoc Correction for PDE Foundation Models
标题：ARC-STAR：针对DTE基础模型的可审计事后纠正
链接：https://arxiv.org/abs/2605.22222
备注：40 pages, including appendices
摘要：Partial differential equation (PDE) foundation models are pretrained networks that forecast how physical fields like velocity and pressure evolve from a single reusable solver. On unfamiliar flows their predictions drift step by step, errors concentrate in a few regions, yet retraining destabilizes the network and uniform post-hoc correction overlooks this spatial concentration. To address this, we propose a frozen-solver post-hoc correction framework, Adaptive Risk-Calibrated Spatial Triage for Auditable Refinement (ARC-STAR). ARC-STAR organizes correction into three stages: a global corrector removes broad solver bias, a blockwise local refiner cleans the post-global residual, and, at deployment, a label-free score routes refinement to high-risk blocks under a compute budget. The framework is designed to be (i) frozen-host, preserving the pretrained solver without fine-tuning; (ii) auditable, with global and local stages trained and evaluated separately for measurable contributions; and (iii) budget-aware, using a blockwise interface that either refines the full field or routes limited compute to high-risk regions. Across five flow benchmarks spanning ten regime cells, ARC-STAR is the only method that cuts velocity rollout error by at least 36x over raw Poseidon on every cell. The global stage reduces raw host error by 91-99%, and the local stage further reduces the remaining post-global residual by up to 94.4%. Our code implementation is available at https://anonymous.4open.science/r/arc_star.
【16】Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics
标题：超越欧几里得邻近性：用水平匹配的轨迹可达性预设修复潜在世界模型
链接：https://arxiv.org/abs/2605.22164
备注：26 pages, 7 figures
摘要：
【17】Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
标题：中小型数据集的代数机器学习与强标准基线具有竞争力
链接：https://arxiv.org/abs/2605.22155
备注：9 pages, 4 figures
摘要：
【18】RobustSpeechFlow: Learning Robust Text-to-Speech Trajectories via Augmentation-based Contrastive Flow Matching
标题：RobustSpeechFlow：通过基于增强的对比流匹配学习稳健的文本到语音轨迹
链接：https://arxiv.org/abs/2605.22083
备注：Submitted to INTERSPEECH 2026
摘要：
【19】stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
标题：稳定世界模型：可重复世界建模研究和评估的平台
链接：https://arxiv.org/abs/2605.21800
摘要
：World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols hindering reproducibility and fair comparison. Current practice is further limited by three key bottlenecks: fragile one-off codebases, slow video data loading, and the lack of standardized generalization benchmarks. We present stable-worldmodel (swm), an open-source platform for standardized and reproducible world modeling research and evaluation. It delivers (1) a high-performance Lance-based data layer with native support and conversion tools for MP4, HDF5, and LeRobot datasets, (2) clean, well-tested implementations of modern world model baselines and planning solvers, and (3) a broad suite of environments and tasks extended with controllable visual, geometric, and physical factors of variation for systematic in-silico evaluation of dynamics understanding, control performance, representation quality, and out-of-distribution generalization. By unifying the full pipeline under a single, scalable framework, \texttt{swm} dramatically reduces research overhead and accelerates trustworthy progress toward reliable world models.
【20】Position: The Time for Sampling Is Now! Charting a New Course for Bayesian Deep Learning
标题：位置：现在是采样的时候了！为Bayesian深度学习制定新路线
链接：https://arxiv.org/abs/2605.21765
备注：In Proceedings of the 43rd International Conference on Machine Learning, PMLR 306, 2026
摘要：The practical adoption of sampling-based inference (SAI) in Bayesian neural networks (BNNs) remains limited, partly due to persistent misconceptions about the feasibility and efficiency of sampling. This position paper argues that SAI has achieved computational parity with optimization-based methods and is at the verge of superseding such methods for effective and efficient inference in BNNs. This development should be in the interest of the whole community, promoting BNNs as a principled paradigm with its long-standing yet unfulfilled promise of providing principled uncertainty quantification for neural networks. SAI can even do more -- yielding superior prediction performance through model averaging, serving as the foundation for a plethora of possible downstream tasks, and providing crucial insights into the landscape of BNNs. In order to make such a change happen and unfold the potential of sampling, overcoming current misconceptions is a necessary first step. The next step is to realign research efforts toward addressing remaining challenges in SAI. In particular, the community must focus on two core problems: sufficient exploration of the posterior landscape and high-fidelity distillation of posterior samples for efficient downstream inference. By addressing conceptual and practical obstacles, we can unlock the full potential of SAI and establish it as a central tool in Bayesian deep learning.
【21】I-SAFE: Wasserstein Coherence Metrics for Structural Auditing of Scientific AI Models
标题：I-SAFE：科学人工智能模型结构审计的Wasserstein一致性标准
链接：https://arxiv.org/abs/2605.21731
摘要：Deep learning models are increasingly used in scientific prediction tasks where strong benchmark performance is often interpreted as evidence of scientifically meaningful behavior. This interpretation is fragile, as models may exploit shortcut features, dataset-specific regularities, or distributional biases that are predictive on held-out data but not aligned with domain-relevant structure. To address this limitation, we introduce the \textsc{I-SAFE} (Interventional Secure, Accurate, Fair and Explainable) framework, a post-hoc distributional auditing framework for scientific AI models centered on the Wasserstein Coherence Metric (WCM). Given a trained black-box predictor and an external structural prior encoding domain knowledge about task-relevant input structure, \textsc{I-SAFE} evaluates raw model outputs under structurally guided perturbations of the input. The proposed audit measures output-distribution coherence through three complementary metrics: a Quantile-Based Metric (QBM) for location-level coherence, the WCM for ordinal coherence, and a translation-invariant WCM variant for shape coherence. We instantiate \textsc{I-SAFE} on drug--target interaction (DTI) prediction using the Davis kinase benchmark, KLIFS (Kinase--Ligand Interaction Fingerprints and Structures) binding-pocket annotations, and three sequence-based DTI models: DeepConvDTI, DeepDTA, and TAPB. Although the models operate in a comparable predictive regime, \textsc{I-SAFE} reveals substantially different distributional response profiles, a distinction invisible to accuracy-based evaluation. The framework is model-agnostic and applicable to any domain where inputs admit a structured decomposition and an external prior is available.
【22】Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction
标题：放大，而不是学习：微调的AI文本检测器放大预训练的方向
链接：https://arxiv.org/abs/2605.21653
【23】Tabular foundation models for robust calibration of near-infrared chemical sensing data
标题：用于近红外化学传感数据稳健校准的表格基础模型
链接：https://arxiv.org/abs/2605.21544
备注：56 pages, 17 figures, including supplementary material
【24】Conditional Entropy of Heat Diffusion on Temporal Networks
标题：时间网络上热扩散的条件熵
链接：https://arxiv.org/abs/2605.21514
【25】Holographic functions and neural networks
标题：全息功能和神经网络
链接：https://arxiv.org/abs/2605.22666
【26】Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions
标题：不要相信拍卖师：学会在反馈操纵的拍卖中出价
链接：https://arxiv.org/abs/2605.22438
【27】Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
标题：浅层神经网络中的时间一致弱混乱分解
链接：https://arxiv.org/abs/2605.22010
备注：46 pages
【28】Causal Discovery in Structural VAR Models Under Equal Noise Variance
标题：等噪音方差下结构VAR模型中的因果发现
链接：https://arxiv.org/abs/2605.21846
【29】CryoNet: A Deep Learning Framework for Multi-Modal Debris-Covered Glacier Mapping. A Case Study of the Poiqu Basin, Central Himalaya
标题：CryoNet：用于多模式碎片覆盖冰川绘制的深度学习框架。喜马拉雅中部波伊曲盆地的案例研究
链接：https://arxiv.org/abs/2605.21527
备注：15 pages, 10 figures, 5 tables. Preprint submitted to IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS); currently under review
其他(57篇)
【1】Tokenisation via Convex Relaxations
标题：通过凸放松进行代币化
链接：https://arxiv.org/abs/2605.22821
【2】Integrable Elasticity via Neural Demand Potentials
标题：通过神经需求潜力整合弹性
链接：https://arxiv.org/abs/2605.22820
备注：44 pages, 7 figures
【3】MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
标题：MOSS：通过自治代理系统中的源级重写进行自我进化
链接：https://arxiv.org/abs/2605.22794
备注：12 pages, 3 figures, 2 tables. Preprint. Code: this https URL
【4】LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
标题：LCCuard：用于多代理系统中安全KV共享的潜在通信卫士
链接：https://arxiv.org/abs/2605.22786
【5】Proxy-Based Approximation of Shapley and Banzhaf Interactions
标题：Shapley和Banzhaf相互作用的基于代理的逼近
链接：https://arxiv.org/abs/2605.22738
【6】The Value of Covariance Matching in Gaussian DDPMs and the Lanczos Sampler
标题：高斯DDPM和Lanczos采样器中协方差匹配的价值
链接：https://arxiv.org/abs/2605.22723
【7】Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
标题：消除瓶颈：通过近边界信号的随机恢复稳定WLVR
链接：https://arxiv.org/abs/2605.22703
【8】Posterior Collapse as Automatic Spectral Pruning
标题：作为自动光谱修剪的后验折叠
链接：https://arxiv.org/abs/2605.22691
【9】The Secretary Problem with a Stochastic Precursor
标题：随机前兆的秘书问题
链接：https://arxiv.org/abs/2605.22653
【10】Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics
标题：为什么新元不是布朗运动：随机动力学的新视角
链接：https://arxiv.org/abs/2605.22644
备注：Preprint
【11】Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
标题：两个总比一个好：无崩溃的多奖励RIIF训练框架
链接：https://arxiv.org/abs/2605.22620
【12】SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations
标题：SynAE：用于测量工具调用代理评估的合成数据质量的框架
链接：https://arxiv.org/abs/2605.22564
【13】Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approcimations
标题：神经流算子可以近似任何算子：抽象框架和通用近似
链接：https://arxiv.org/abs/2605.22557
【14】Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets
标题：稳定网络安全人工智能中的解释脆弱性：公共基准数据集中多重共线性的影响和缓解
链接：https://arxiv.org/abs/2605.22529
备注：35 pages, 3 figures, submitted to ACM TAISAP
【15】Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
标题：具有次二次序列复杂度的实体跟踪的结构稀疏注意力
链接：https://arxiv.org/abs/2605.22476
备注：12 pages, 1 figure, 9 tables
【16】Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection
标题：单脉冲电磁故障注入下英特尔神经计算棒2的故障响应特征
链接：https://arxiv.org/abs/2605.22437
【17】AMUSE: Anytime Muon with Stable Gradient Evaluation
标题：AMUSE：具有稳定梯度评估的随时μ子
链接：https://arxiv.org/abs/2605.22432
备注：41 pages, 25 figures
【18】Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology
标题：跨物种RSA揭示人类fMRI和猕猴电生理学之间早期视觉对齐保守，但较高区域排名存在分歧
链接：https://arxiv.org/abs/2605.22401
备注：9 pages, 6 figures
【19】Efficient Higher-order Subgraph Attribution via Message Passing
标题：通过消息传递高效的更高级子图归因
链接：https://arxiv.org/abs/2605.22385
备注：Published in ICML 2022
【20】Towards Explainability of SLMs by investigating Token Level Activation
标题：通过调查令牌级激活来实现CRM的可解释性
链接：https://arxiv.org/abs/2605.22377
【21】ASAP: Attention Sink Anchored Pruning
标题：尽快：注意力下沉锚定修剪
链接：https://arxiv.org/abs/2605.22372
【22】Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction
标题：物理信息生成求解器：弥合数据驱动先验和保守定律以实现稳定时空场重建
链接：https://arxiv.org/abs/2605.22338
【23】Long-term Fairness with Selective Labels
标题：选择性标签的长期公平
链接：https://arxiv.org/abs/2605.22291
【24】What are the Right Symmetries for Formal Theorem Proving?
标题：形式定理证明的正确对称性是什么？
链接：https://arxiv.org/abs/2605.22257
【25】No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
标题：没有哪个时代像现在这样：稳健的气候模拟需要分布外的概括
链接：https://arxiv.org/abs/2605.22248
备注：36 pages, 12 figures
【26】Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations
标题：用已知的随机参数化分解Lorenz ' 96中的群体传播
链接：https://arxiv.org/abs/2605.22242
【27】Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
标题：生存还是崩溃：自我游戏强化学习中数据门控和奖励基础的非对称作用
链接：https://arxiv.org/abs/2605.22217
【28】OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025
标题：OSS：开放缝合技能基于愿景的评估挑战2024-2025
链接：https://arxiv.org/abs/2605.22200
备注：Stefanie Speidel and Behrus Hinrichs-Puladi jointly supervised this work. Submitted to MEDIA
【29】IKNO: Infinite-order Kernel Neural Operators
标题：IKNO：无限阶核神经运算符
链接：https://arxiv.org/abs/2605.22182
【30】Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability
标题：测量跨模态协同：VLM可解释性的基准
链接：https://arxiv.org/abs/2605.22168
【31】Aerodynamic force reconstruction using physics-informed Gaussian processes
标题：使用物理信息高斯过程重建空气动力
链接：https://arxiv.org/abs/2605.22111
【32】TextTeacher: What Can Language Teach About Images?
标题：文本老师：语言可以教图像什么？
链接：https://arxiv.org/abs/2605.22098
备注：Published at TMLR
【33】TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
标题：TwINGS：用于稀疏视图高斯飞溅的薄片样条经向毛刺
链接：https://arxiv.org/abs/2605.22069
备注：Accepted to CVPR 2025, Project page: https://sandokim.github.io/twings/
【34】RADAR: Defending RAG Dynamically against Retrieval Corruption
标题：雷达：动态防御RAG免受检索腐败
链接：https://arxiv.org/abs/2605.22041
【35】How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverability
标题：稀疏性分配如何验证无标签修剪后可恢复性
链接：https://arxiv.org/abs/2605.21972
【36】Dynamic Mixture of Latent Memories for Self-Evolving Agents
标题：自我进化主体的潜在记忆动态混合
链接：https://arxiv.org/abs/2605.21951
备注：19 pages, 5 figures, 5 tables
【37】Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale
标题：超越规模目标：专家反馈驱动的纳米级科学发现自主实验
链接：https://arxiv.org/abs/2605.21820
【38】Same Architecture, Different Capacity: Optimizer-Induced Spectral Scaling Laws
标题：相同的架构，不同的容量：优化器诱导的光谱缩放定律
链接：https://arxiv.org/abs/2605.21803
备注：31 pages, 10 figures, 30 tables. Project page: https://optimizer-scaling-laws.github.io
【39】Manifold-Guided Attention Steering
标题：气道引导注意力引导
链接：https://arxiv.org/abs/2605.21770
【40】TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes
标题：TBP-mHC：通过运输多表位实现受总管限制的超级连接的全面表达
链接：https://arxiv.org/abs/2605.21724
【41】Hierarchical Variational Policies for Reward-Guided Diffusion
标题：奖励引导扩散的分层变分政策
链接：https://arxiv.org/abs/2605.21661
【42】EntmaxKV: Support-Aware Decoding for Entmax Attention
标题：Entmax GV：支持感知解码以吸引Entmax的注意力
链接：https://arxiv.org/abs/2605.21649
【43】ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage
标题：CLARBLAGE-DEEPPHISTORY：具有时间覆盖的交叉构建二进制数据集
链接：https://arxiv.org/abs/2605.21615
【44】AgForce Enables Antigen-conditioned Generative Antibody Design
标题：AgForce实现抗原条件生成抗体设计
链接：https://arxiv.org/abs/2605.21610
【45】TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems
标题：TONIC：面向任务的无线系统的以令牌为中心的语义通信
链接：https://arxiv.org/abs/2605.21553
备注：15 pages, 10 figures
【46】Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
标题：预期一致性损失：协变量变化下重新思考信心校准
链接：https://arxiv.org/abs/2605.21552
备注：Accepted by ICML 2026
【47】Discovering Entity-Conditioned Lag Heterogeneity: A Lag-Gated Neural Audit Framework for Panel Time Series
标题：发现贫困条件滞后异源性：面板时间序列的滞后门神经审计框架
链接：https://arxiv.org/abs/2605.21542
备注：Preprint/technical paper. An interpretable neural audit framework for entity-conditioned lag discovery in panel time series. 10 pages, 5 figures, 16 tables. Code available at the GitHub repository
【48】Double descent for least-squares interpolation on contaminated data: A simulation study
标题：污染数据上最小二乘插值的双下降法：模拟研究
链接：https://arxiv.org/abs/2605.21494
【49】The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
标题：归因的不可能性：共线性下没有特征排序是忠实、稳定和完全的
链接：https://arxiv.org/abs/2605.21492
备注：66 pages, 12 figures, 305 Lean 4 theorems. Code at https://github.com/DrakeCaraker/dash-impossibility-lean
【50】Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
标题：稀疏数据下精确Maxwell动力学的快速重建
链接：https://arxiv.org/abs/2605.20514
备注：31 pages, 8 figures
【51】A Martingale Kernel Independence Test
标题：一个Martingale核独立性测试
链接：https://arxiv.org/abs/2605.22549
【52】Departure from Regularity: Degree Heterogeneity and Eigengap as the Structural Drivers of ASE-LSE Latent Subspace Disagreement
标题：偏离规律性：度异方差和特征间隙是ASE-LSE潜在子空间不一致的结构驱动因素
链接：https://arxiv.org/abs/2605.22346
备注：12 pages (excluding references + appendices), 5 figures
【53】From Betting to Empirical Bernstein LIL
标题：从投注到经验伯恩斯坦LIL
链接：https://arxiv.org/abs/2605.22124
【54】Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
标题：Q-PhotoNAS：光电子设备上的混合量子神经架构搜索框架
链接：https://arxiv.org/abs/2605.22097
【55】Thermodynamic Irreversibility of Training Algorithms
标题：训练算法的热力学不可逆性
链接：https://arxiv.org/abs/2605.21933
备注：preprint
【56】Support-aware offline policy selection for advertising marketplaces
标题：广告市场的支持意识离线政策选择
链接：https://arxiv.org/abs/2605.21736
【57】MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
标题：MetaDNS：通过深思熟虑的元逻辑学增强离散神经采样器的探索
链接：https://arxiv.org/abs/2605.21722
备注：Accepted at ICML 2026
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/196686
本文地址：http://www.python88.com/topic/196686