机器学习学术速递[9.2]

AI 总结：该研究提出硬件-算法协同设计框架FFD，利用注意力稀疏性实现长上下文解码的高效性，获内核级11.6倍加速、端到端吞吐量2.37倍提升，在基准数据集上保持精度。

链接：https://arxiv.org/abs/2609.00097

机构：Fudan University（复旦大学）； Shanghai Innovation Institute（上海创新研究院）； Harbin Institute of Technology（哈尔滨工业大学）

作者：Zhigeng Liu, Zhiyuan Ning, Ruixiao Li, Xiaoran Liu, Yuerong Song, Min Zhang, Ziwei He, Xipeng Qiu

英文摘要：The development of long-context Large Language Models (LLMs) is constrained by the memory bandwidth bottleneck and quadratic complexity of the attention mechanism during decoding. To overcome the inherent trade-offs between the memory overhead of metadata-based metrics and the computational inefficiency of adaptive selection strategies, we present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding. FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning via low-bit quantization. Furthermore, we introduce the top-delta strategy, which dynamically filters blocks to achieve distribution-adaptive sparsity without global synchronization. Offering a training-free and plug-and-play solution, FFD also enables the reuse of scanning results for computation, achieving up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement. Empirical validation on RULER and LongBench confirms that FFD maintains model accuracy while delivering high-ratio sparsity, with code available at this https URL

AI 总结：研究人员推出ECCBench基准与评估协议，从效率、压缩性、校准性三方面评估视觉-语言模型的记忆能力，发现预训练VLM对文本记忆可压缩但视频不行，部分非Transformer架构的压缩-校准权衡优于RoPE Transformer。

链接：https://arxiv.org/abs/2609.00103

机构：Princeton University（普林斯顿大学）

作者：Shmuel Berman, Jia Deng

英文摘要：Memory is widely viewed as an important unsolved problem for LLMs and VLMs, and current benchmarks typically evaluate it by testing accuracy over long text or video. However, accuracy alone misses properties that matter for real long-horizon tasks. We introduce ECCBench, a benchmark and evaluation protocol that measures memory beyond a system's capacity--its raw accuracy at a specific budget--via three axes we call ECC: efficiency--the computation, in FLOPs, needed to answer from memory; compression--whether compressible inputs are remembered more accurately or efficiently; and calibration--whether the system abstains in response to its own uncertainty and the cost of an error. We find that pretrained VLMs compress their memory over text but not video and are poorly calibrated on both. Among a broader set of memory backbones, several non-Transformer architectures achieve better compression-calibration tradeoffs than RoPE Transformers, suggesting they may be useful components for agents operating over long horizons.

AI 总结：本文阐述高阶张量运算对深度学习的重要性，开展训练神经网络高阶现象的实证研究，引入多层感知机的超图泛化形式并探索其与进化算法的关联，最后探讨未来研究方向。

链接：https://arxiv.org/abs/2609.00472

机构：Combinatorial Labs（组合实验室）； University of Colorado Boulder（科罗拉多大学博尔德分校）

作者：Michael L. Roberts, Carlos Zapata Carratalá. Nicholas J. Cooper, Lijun Chen, François G. Meyer, Danna Gurari

英文摘要： We provide an expository introduction on the importance of higher-arity tensor operations to deep learning. Then, we conduct a novel empirical investigation of higher-arity phenomenon in trained neural networks, introduce a hypergraphical generalization of the multilayer perceptron, and explore connections to evolutionary algorithms. We conclude with a discussion of promising directions for future research.

AI 总结：该研究通过分析CNN与LLM的内部激活，探究概念分离现象，发现其能揭示输出准确率无法体现的模型表征结构，可用于诊断模型的概念表征鲁棒性。

链接：https://arxiv.org/abs/2609.00764

机构：Ashoka University（阿肖克大学）； Truth Audit Labs（真相审计实验室）； Karya AI（卡尔亚人工智能公司）

作者：Jaee Ponde, Roshni Agarwal, Subhashis Banerjee

英文摘要：Neural networks are increasingly employed to identify both well-defined and ambiguous concepts, yet output-level metrics reveal little about how those concepts are represented internally. Our study asks if these networks exhibit \textit{conceptual separation}: if examples of the same concept form coherent representations, and whether related concepts lie closer together in the representation space. We examine this conceptual organisation in Convolutional Neural Networks (CNNs) and Large Language Models (LLMs) through geometric and distributional analysis of their internal activations. In CNNs, familiar ImageNet concepts form coherent and semantically ordered representations, while this coherence weakens for unseen concepts and suffers within-class domain shift. In LLMs, clearly distinct domains remain well separated, related subdomains move closer together, and the distinction between ambiguous topics collapses at both the mean and covariance level. These results suggest that conceptual separation can reveal structure that output accuracy alone cannot, and may serve as a useful diagnostic of how robustly a model represents the concepts it is asked to identify. Code and data available on \href{ this https URL }{GitHub}.

AI 总结：该综述针对Transformer推理部署需求，分析FPGA平台的最新进展、设计选择与优化技术，为学术界和工业界研究人员提供指南。

链接：https://arxiv.org/abs/2609.01212

机构：University of Twente（特温特大学）； Faculty of Engineering Technology, University of Twente（特温特大学工程技术学院）

作者：Arjan Blankestijn, Uraz Odyurt, Amirreza Yousefzadeh

英文摘要：With the rapid and continuous growth in the incorporation of machine learning models based on the Transformer architecture, capable deployment is in high demand. In this context, capable deployment refers to operational performance aspects, e.g., throughput and latency, as well as efficiency aspects, e.g., energy consumption. When it comes to the task of inference using such models, purpose-built hardware accelerators provide a lucrative alternative to common deployment choices, such as Central Processing Units (CPUs) and Graphics Processing Units (GPUs). The Field Programmable Gate Array (FPGA) platforms category is an example of such alternative accelerators, promising implementation flexibility, energy efficiency, improved latency and suitability for on-site deployment. We investigate the most recent advances, trends, and design choices for Transformer inference on FPGA platforms. We perform a systematic literature review, extracting and delving into preferred techniques for implementation and optimisation. This study and the provided taxonomy of topics could act as a guide for researchers from the academia and industry alike.

AI 总结：该研究证明多头缩放点积注意力是参数识别策略，头数越多模型越易识别，还探讨了RoPE、GQA等Transformer改进对参数比值的影响，为Transformer架构提升性能提供了统计解释。

链接：https://arxiv.org/abs/2609.01231

作者：W. Ross Morrow

英文摘要：We prove that a multi-head scaled dot product attention can be viewed as a parameter identification strategy. The ratio of unidentified parameters to the total number of parameters scales like the reciprocal of the number of heads ($1/2 \to 1/(2H)$), meaning models with more heads are structurally more identified. A subtle side effect of the mathematics observation that attention can never be fully identified. Similarly we also show that some bias terms can have no effect on softmax-based attention layers in both the single- and multiple-head settings, though this is mostly a curiosity that should have a marginal effect on model size and model training/prediction efficiency. We also touch on modern improvements to transformers including RoPE and GQA from this perspective, illustrating how those as well can improve the ratio of ``meaningful'' parameters to all parameters. Simple numerical examples demonstrate that training can indeed involve updates that overlap model-invariant subspaces that arise from a lack of identification. As part of our experiments we use a ``rebalancing'' approach that can ``fix'' updates that overlap unindentified subspaces but do not try to present evidence this should actually be adopted. Instead we simply view our numerical results as exploring and confirming the theoretical results. As a whole we discuss a purely mathematical/statistical explanation, identification, for why specific architectural choices in transformers may have improved performance.

AI 总结：本研究通过单变量搜索实验，探究监督微调中的学习率、批量大小等关键决策，在Qwen3、Llama模型及客户SFT数据集上揭示了各超参数的变化规律与模型性能的关联，为监督微调提供了可迁移的决策建议。

链接：https://arxiv.org/abs/2609.01244

机构：Baseten（巴斯滕）

作者：Charles O'Neill, Mudith Jayasekara, Harry Partridge

英文摘要：Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, which optimiser, and what data to feed the model. Each of these is typically rediscovered from scratch for every new model and dataset. Here we measure them under one instrument: a sweep that varies one lever at a time, and spans dense and mixture-of-experts models in two families (Qwen3 and Llama), on four real-world customer SFT datasets, for both LoRA and full fine-tuning. These datasets give a controlled testbed: each task carries an evaluation built with the customer, and its training data is produced by iterative supervised fine-tuning that refines model outputs until they pass that evaluation, so the supervised target is internally consistent and the task judge we report against is the criterion the data was built to satisfy. We ask how the optimal learning rate and batch size move with model scale, family, and data, and whether one selection rule transfers across them; what LoRA trades against full fine-tuning, and how its rank and alpha set what the adapter can learn; whether validation loss (or other metrics, such as loss landscape flatness) faithfully ranks downstream quality; whether post-training gains scale with model size and data volume, on a model ladder extended through mixtures-of-experts to 235B parameters; how many epochs to train before general instruction-following erodes; and whether a geometry-aware optimiser improves on AdamW. Each recommendation is paired with a measure of its uncertainty.

AI 总结：该研究在严格匹配关键预算指标的前提下，提出SMELT方案，通过循环MoE Transformer中间层，提升了模型性能并节省了训练FLOPs，为Transformer架构优化提供了实用方案。

链接：https://arxiv.org/abs/2609.01343

机构：Tsinghua University（清华大学）； ByteDance Seed（字节跳动Seed）； M-A-P

作者：Shaowen Wang, Ge Zhang, Kairong Luo, Yuhao Wu, Shaofan Liu, Jiaheng Liu, Wenhao Huang, Shen Yan, Jian Li

英文摘要：Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating architectural advantage with extra FLOPs. We study looping on Mixture-of-Experts Transformers while closely matching per-token FLOPs, total non-embedding parameters, and KV cache. Through a series of ablations, we arrive at a recipe we call SMELT (Sparse MoE Transformer, middle layers Loop Twice), which loops the middle half of layers twice while matching the unlooped Baseline on all three budgets. We scale SMELT across four sizes up to 54B non-embedding parameters and fit a separate Chinchilla-style scaling law for each architecture. SMELT's loss drops faster with compute, saving 6.8--18.0\% of training FLOPs on the compute-optimal frontier. The advantage transfers to downstream benchmarks beyond what validation loss predicts, is largest on Code, and grows with sample length and the number of in-context examples. Mechanistic analysis shows that the second visit reduces the attention sink and redirects mass toward content-relevant tokens, an inductive bias that may underlie the observed performance gains. These results show that looping can improve Transformers even under budget matching, offering a practical recipe that turns depth reuse into measurable gains.

AI 总结：针对大型AI模型的内存瓶颈，提出线性可复用神经基架构，通过共享神经基的线性组合实现高压缩率，实验显示其收敛更快、损失更低且训练稳定。

链接：https://arxiv.org/abs/2609.01550

机构：The George Washington University（乔治·华盛顿大学）

作者：Binshuai Wang

英文摘要：As large AI models become increasingly prevalent across a wide range of applications, memory cost has become a critical bottleneck in both training and inference. To mitigate this issue, we introduce the Linear Reusable Neural Bases Architecture (LRNBA), a novel framework aimed at improving parameter efficiency and reducing memory cost. Inspired by recurrent neural network (RNN) designs, the core idea of our approach is to represent each network block as a linear combination of a shared set of neural bases, thereby enjoying highly network compression rate while maintaining stable training. The proposed architecture allows for the construction of significantly wider and deeper networks under the same parameter budget. Extensive experiments demonstrate that our model achieves comparable or even faster convergence and lower loss than classical architectures, while maintaining stable training dynamics.

AI 总结：MUGEN是首个面向多学习任务的不可学习图示例生成框架，通过TASO与TAP技术，生成可跨GNN骨干和任务迁移的防御性扰动图数据，在多基准实验中表现有效。

链接：https://arxiv.org/abs/2609.00696

机构：Harrisburg University of Science and Technology（哈里斯堡科技大学）； Arizona State University（亚利桑那州立大学）

作者：Ziyan Liu, Chengshuai Zhao, Huan Liu

英文摘要： Graph data across diverse domains can expose valuable relational information to unauthorized representation learning, creating a pressing need for protection against such misuse. Unlearnable examples offer a data-level defense by perturbing a training release so that models trained on it fail to generalize to clean data. Existing methods generate unlearnable graph examples for only a specified downstream task. Consequently, a release protected against one task may remain learnable for other plausible uses, including node classification, graph classification, and link prediction, which the data owner cannot anticipate. We introduce MUGEN, to our knowledge the first framework for generating unlearnable graph examples that jointly protect all enabled tasks. From one clean dataset, MUGEN produces a single feature-perturbed release that protects every enabled task through a shared GNN encoder and task-specific heads. We devise a Task-Aligned Separability Objective (TASO), which leverages task prediction and classwise separability to strengthen unlearnability and its transfer across GNN backbones and enabled tasks. We further introduce Type-Adaptive Perturbation (TAP), which tailors perturbation optimization to node-attribute type, with direct search over feasible hard flips that accept only loss-improving updates for discrete node attributes and customized gradient-based updates for continuous node features, thereby enabling strong unlearnability across both settings. Experiments across five benchmarks, four backends and three learning paradigms demonstrate that MUGEN generates transferable unlearnable graph examples across GNN backbones and all three tasks, and remains effective under adversarial training and data augmentation.

AI 总结：本研究提出表内预测（ITP）问题，采用自监督学习方法，通过新型神经层处理连续特征缺失值，基于合成数据评估MLP、Resnet、Transformer性能，发现注意力结构在合适条件下表现更优。

链接：https://arxiv.org/abs/2609.01262

机构：Offenburg University（奥芬堡大学）； Institute for Machine Learning and Analytics（机器学习与分析研究所）

作者：Xiao Zhao, Daniela Oelke

英文摘要：Tabular deep learning (TDL) leverages neural networks (NN) to extract patterns from tabular data. Traditional TDL methods follow a supervised learning paradigm, where a target feature is explicitly given. In this work, however, we explore a different approach by employing deep NNs to learn relationships among individual columns within a given table. We investigate whether NNs can predict the values of arbitrarily selected columns in a given table based on the remaining known columns. We call this problem In-Table Prediction (ITB), which is slightly different from table imputation methods and the pretraining task of TDL. Three potential usage scenarios are identified, which, to our best knowledge, have not been extensively studied in the literature. A self-supervised learning approach is applied to address this problem by randomly selecting columns to be masked out and used as learning targets. This work focuses on tabular datasets containing only continuous features. To handle missing values in continuous features, a novel neural layer is proposed to embed both numerical and empty values. Synthetic data is generated based on predefined column relationships, with empty values inserted using two distinct mechanisms. Additionally, an adapted masking strategy is employed to create test data. Performances of three NN architectures, namely MLP, Resnet and Transformer, are evaluated using the generated synthetic data. We conclude that, the attention-based structure outperforms the other two networks, when a sufficiently large number of training examples is available and a relatively large embedding length is chosen. We stress that these findings are obtained under controlled, synthetic conditions with a small number of columns and it should therefore be regarded as an initial, narrowly-scoped investigation rather than a general characterization of ITP on real-world tabular data.

AI 总结：EW-SFT是一种统一有效的分子优化方法，通过奖励指导精英选择并基于预训练损失更新模型，适用于多种分子生成器与设计任务，性能优于原生优化器。

链接：https://arxiv.org/abs/2609.00189

机构：Biogen（渤健公司）

作者：Shiyun Wa, Yifei Wang, Anna G. Green, Simone Sciabola, Ye Wang

英文摘要：Goal-directed optimization is essential for steering molecular generators to propose candidates with desired properties. However, it is often implemented with policy-gradient reinforcement learning, which requires a generation-trajectory log-probability whose form depends on the model architecture and generation procedure. This makes an optimizer difficult to reuse across architectures and conditional generative designs. Supervised fine-tuning needs none of that machinery, but its update is driven by a fixed dataset, so the reward never enters the update. We introduce Elite-Weighted Supervised Fine-tuning (EW-SFT), which uses reward to guide elite selection of high-scoring molecules, and updates the model by its own pretraining loss on that set. Ablations show that reward information is passed primarily through elite selection, rather than through continuous weighting within the selected set. Because the update consumes only scored molecules and the model's native loss, the same rule applies across autoregressive, masked-diffusion, and discrete-flow generators, and across de novo, motif-extension, and linker-design tasks. Under a fixed budget of 3D shape alignment oracle calls on two kinase reference compounds, EW-SFT consistently outperforms the corresponding native optimizers. It further improves goal-directed optimization under a 2D similarity oracle on four held-out references and achieves comparable performance on a sample-efficiency benchmark without a trajectory-level RL formulation. These results demonstrate that EW-SFT is a unified and effective optimizer across molecular generators, design constraints, references, and oracles.

AI 总结：该研究针对GRPO的固定裁剪局限，提出GAPO方法，通过自适应调整裁剪边界提升了Qwen、Llama模型在低通过率数学推理与编码任务上的Pass@1和Pass@k指标。

链接：https://arxiv.org/abs/2609.00444

机构：University of Toronto（多伦多大学）； Amazon（亚马逊公司）

作者：Sheng Jia, Xiao Wang, Shiva Prasad Kasiviswanathan, Rein Houthooft

英文摘要： Group relative policy optimization for reinforcement learning with verifiable rewards (RLVR) typically uses a fixed importance-sampling (IS) ratio clipping boundary across all rollouts. We identify a key limitation: rare correct rollouts on harder problems and abundant correct rollouts on easier problems are clipped at comparable rates, despite contributing very different learning signals. Rollouts with low group success exhibit larger IS ratios and carry stronger gradient signal for exploration and solving new problems, yet are disproportionately suppressed by fixed clipping. To address this, we propose Group Adaptive Clipping Policy Optimization (GAPO), a plug-in modification to GRPO methods that adapts the clipping boundary to the rollout advantage. GAPO is motivated by a reverse-KL trust-region perspective, which suggests that rollouts with larger learning signal should receive proportionally greater update headroom. GAPO requires no reward shaping and preserves the standard PPO/GSPO surrogate while adapting only the clipping threshold. Across Qwen and Llama models, GAPO consistently improves both Pass@1 and Pass@k over fixed clipping and advantage-shaping baselines on math reasoning and coding benchmarks where the pass rates by the base model are relatively low.

AI 总结：本研究探索将关系Transformer嵌入作为软令牌注入大语言模型的可行性，经多任务评估发现该混合模型表现不佳，需更强对齐目标与感知模式设计才能成为关系预测可靠途径。

链接：https://arxiv.org/abs/2609.00457

机构：Kunumi Institute（库鲁米研究所）； Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）

作者：Francisco Galuppo Azevedo, Clarissa Lima Loures

英文摘要：Injecting frozen relational-encoder embeddings as soft tokens into a large language model (LLM) is a conceptually appealing fusion strategy: the encoder handles multi-table structure, the LLM handles language and reasoning, and no lossy text serialization is required. We test this hypothesis concretely by injecting embeddings from a frozen Relational Transformer (RT) into Qwen3.5-4B via a learned MLP projection and LoRA adaptation, trained first with supervised fine-tuning (SFT) on chain-of-thought reasoning traces and then with group-based reinforcement learning (GSPO). We evaluate across 10 binary classification tasks on 6 relational databases from RelBench, under four supervision regimes: single-task (ST), within-dataset (WD), cross-dataset (CD), and all-task (ALL). The hybrid model does not consistently outperform standalone RT: it is frequently below random, highly sensitive to serialization format and relational-token budget, and unstable under RL training. We report these negative results and analyze the failure modes, arguing that soft-token fusion requires stronger alignment objectives and schema-aware design before it can serve as a reliable route to relational prediction.

AI 总结：该研究针对多智能体组合优化的性能局限，提出GeoPAR框架，通过三个关键组件优化几何建模与冲突处理，在两类问题上实现了更好的大规模泛化与高效推理。

链接：https://arxiv.org/abs/2609.00577

机构：Soochow University（苏州大学）； School of Future Science and Engineering（未来科学与工程学院）

作者：Wenjian Wu, Zesheng Jia, Jiaying Tang, Benyuan Yang, Jin Wang

英文摘要：Multi-agent combinatorial optimization problems are notoriously challenging due to their NP-hard nature. Recent parallel autoregressive neural solvers improve inference efficiency by allowing agents to make decisions simultaneously, but their performance often degrades on large-scale instances. This is largely attributable to weak modeling of local geometric structures and the fact that conflicting task selections are handled only after action generation. To address these limitations, we propose GeoPAR, a geometry-guided parallel autoregressive reinforcement learning framework for scalable multi-agent combinatorial optimization. GeoPAR integrates three key components: (1) a projection-window sparse geometry mechanism that builds lightweight local candidate neighborhoods through multi-directional projections, (2) sparse edge-biased attention that injects these geometric relations into node representations, and (3) cache-guided conflict-aware assignment that reuses the geometric cache during decoding to suppress duplicate selections of exclusive tasks. Experiments on heterogeneous vehicle routing and open multi-depot pickup-and-delivery problems show that GeoPAR improves large-scale zero-shot generalization while substantially reducing rollout steps and maintaining efficient inference.

AI 总结：该研究提出在线自加权微调（OSW-FT）方法，通过少量在线rollout估计模型成功率以调整SFT损失，在Qwen3系列模型上提升了中小规模模型在二元可验证推理任务的性能，计算性能权衡良好。

链接：https://arxiv.org/abs/2609.00734

机构：University of Liverpool（利物浦大学）； University of Sheffield（谢菲尔德大学）

作者：Haiquan Wen, Yiwei He, Bei Peng, Guangliang Cheng

英文摘要：Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Reinforcement learning (RL) based methods adapt update strength using model-generated rollouts, but often require substantially more sampling and can be unstable on hard tasks. We propose \textbf{Online Self-Weighted Fine-Tuning (OSW-FT)}, a simple method that augments SFT with online, trajectory-level weighting. For each query, OSW-FT estimates the model's current success rate using a small number of inference-only rollouts and rescales the standard SFT loss accordingly. The optimization direction remains anchored to the expert trajectory, while the update magnitude adapts online. For binary-verifiable reasoning, we connect this weighting to SFT and RL at the gradient level, inspired by variance-reduction principles. The resulting estimator is unbiased for the exact OSW-FT surrogate update for any finite rollout count, and we analyze convergence with respect to the corresponding surrogate objective. Evaluated across Qwen3 series ranging from 0.6B to 4B on multiple challenging benchmarks (e.g., AIME), OSW-FT consistently improves over SFT on small-to-medium scale models. OSW-FT offers a favorable compute-performance trade-off as a practical approach for fine-tuning small-to-medium LLMs on binary-verifiable reasoning tasks with only \textbf{2 online rollouts}.

AI 总结：本文提出CANOPY协议，通过解决信号匮乏与策略漂移问题，使仅基于结果的强化学习在小型开放模型上实现长视距交互任务，在AppWorld和SWE-bench Verified基准上取得优异性能。

链接：https://arxiv.org/abs/2609.01245

作者：Liming Pu, Xiaoxia Li, Yifu Liu, Teng Cao, Bin Yang

英文摘要：Reinforcement learning is a natural way to post-train LLM agents for long-horizon interactive tasks judged only by end-of-task verification, yet a shared belief holds that outcome-only RL soon hits a ceiling on small open models. Recent work therefore compensates around the training with denser rewards, SFT priors, skill libraries, curated memory, or multi-agent orchestration. We argue the ceiling is an artifact of two failures of common practice. Signal starvation: group-relative RL with sparse outcome-only rewards yields a gradient only when a task's rollout group mixes successes and failures, so under-scaled exploration silences exactly the hardest, most instructive tasks. Policy drift: squeezing many updates out of a small task pool degrades the policy itself, as an unanchored objective lets the sampling distribution collapse exactly when saturation has already made informative groups rare. We present CANOPY (Coverage-ANchored On-PolicY RL), a minimalist protocol attacking both directly: scale same-task exploration until the natural signal reappears, keep every update on-policy, KL-anchored, and confined to the agent's own action tokens, then cash in an enlarged interaction budget at test time. On AppWorld, a long-horizon interactive coding benchmark, a Qwen3-14B policy trained with CANOPY through environment interaction alone--without task-specific supervision, auxiliary credit signals, or elaborate agent scaffolding--topped the public leaderboard (Feb. 2026; Test-Normal TGC 86.9, Test-Challenge 67.6), and the same design principles lift Qwen3.5-9B on SWE-bench Verified by 16.6 points. Agentic RL alone thus internalizes long-horizon capability directly into a small open model; we plan to release the complete training stack at this https URL.

AI 总结：该研究针对生产系统推理时超参数优化的问题，提出IMABO框架，结合IMOSS策略与三类神谕，在多类OHPO场景中实现了更低的累积遗憾。

链接：https://arxiv.org/abs/2609.01335

机构：Tiime

作者：Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine

英文摘要：Many production systems can assess a configuration only by using it on live requests and observing noisy feedback. Modern agentic systems are a prominent example, with inference-time choices such as model selection, retrieval depth, prompting strategy, and decoding temperature, yet often with no representative validation data. We formalize this setting as Online Hyperparameter Optimization (OHPO) and cast it as an infinitely many-armed bandit over mixed and conditional search spaces. We introduce IMABO, a general framework that combines any bandit policy for choosing among already sampled configurations with any oracle for proposing new ones. We instantiate it with IMOSS, a restart-free anytime policy whose active set grows as $t^{\beta}$, and prove an expected cumulative quantile-regret bound of $O(p_\rho^{-1/\beta} + T^{(1+\beta)/2})$, where $\beta\in(0,1)$ controls active-set growth and $p_\rho$ lower-bounds the probability that a proposed configuration falls in the top-$\rho$ fraction of the search space. We combine IMOSS with three practical oracles: a Tree-structured Parzen Estimator, an incumbent-mutation oracle driven by a per-coordinate bandit, and a pretrained tabular foundation model, all three improving over the uniform random oracle baseline. IMABO obtains the lowest cumulative regret across diverse OHPO settings, from tuning classical machine-learning models to configuring LLM-based agents.

AI 总结：该研究针对安全仿真到现实迁移问题，在无奖励安全强化学习框架下设计高效算法，可减少现实交互并保证安全探索，还能计算接近最优的可行策略，刻画了仿真器的益处。

链接：https://arxiv.org/abs/2609.01418

机构：EPFL（洛桑联邦理工学院）

作者：Tingting Ni, Maryam Kamgarpour

英文摘要：To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where samples are cheap, and then deploy the learned policy in the real world with the hope that it generalizes effectively. Such direct sim-to-real transfer is not guaranteed to succeed: simulator-trained policies can be suboptimal in the real world due to sim-to-real mismatch. Correcting this mismatch requires collecting data from the real system, but in many applications, such as robotics and healthcare, this data-collection process is itself subject to safety constraints. This gives rise to the problem of safe sim-to-real transfer: how can an agent exploit an imperfect simulator while ensuring safe real-world data collection and learning a near-optimal feasible policy for the target system? We address this problem by formulating safe sim-to-real transfer within the framework of reward-free safe RL. We design a computationally efficient algorithm that exploits simulator information to provably reduce real-world interaction while ensuring safe exploration and enabling the computation of a near-optimal feasible policy for any potential reward function. Our real-world sample complexity bound characterizes the benefit of using the simulator in terms of the sim-to-real mismatch.

AI 总结：本文针对基于模型的强化学习在零和非完全信息博弈中应用不足的问题，提出NashDreamer框架，引入MARSSM模型，经四基准游戏验证可提升样本效率，并分析了Dreamer系列算法的后验崩溃问题。

链接：https://arxiv.org/abs/2609.01549

机构： Artificial Intelligence Center（人工智能中心）； Faculty of Electrical Engineering, Czech Technical University in Prague（布拉格捷克技术大学电气工程学院）

作者：Tomáš Holeček, Viliam Lisý

英文摘要：Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across four benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge.

AI 总结：本文针对复杂几何下PDE求解难题，提出GeoLAMP模型，通过双编码器、流匹配Transformer与灵活解码器实现稳定预测，构建多物理场基准数据集并取得最优性能。

链接：https://arxiv.org/abs/2609.00297

机构：Stanford University（斯坦福大学）

作者：Zi Wang, Minghui Xu, Tapan Mukerji

英文摘要：Solving multiphysics partial differential equations (PDEs) remains a major challenge in scientific computing, especially for highly complex $\mu$m-scale tortuous geometries critical to energy and chemical engineering. We address this challenge by proposing a Geometry-aware Latent Autoregressive generative Model for PDEs (GeoLAMP) for solving physics within highly irregular and tortuous structures. GeoLAMP introduces a dual-encoder architecture on graph representations to jointly capture global topology and fine-scale geometric features, enabling an effective transition from real-space fields to compact latent representations. In the latent space, we propose a causal self-attention transformer with flow matching to model temporal dynamics, allowing stable and scalable block-wise autoregressive prediction. A flexible decoder reconstructs high-resolution physical fields on arbitrary points. We establish three multiphysics benchmark datasets in complex geometries, covering reactive flow, heat convection, and elasticity. GeoLAMP consistently achieves the most stable autoregression performance on these datasets, maintaining low errors throughout the entire rollout horizon. Our results provide a systematic study of geometry-aware learning for PDEs in $\mu$m-scale complex geometries and offer new insights into block-wise time marching of latent autoregressive PDE modeling via a flow matching framework.

AI 总结：该研究提出结合神经均值与Matérn核修正的算子学习方法，在结构力学、OCO-2辐射传输仿真问题上，优于或匹配已发表基准，还揭示了残差特性与不确定性信号等关键机制。

链接：https://arxiv.org/abs/2609.00389

机构：Einstein Institute of Mathematics, The Hebrew University of Jerusalem（耶路撒冷希伯来大学爱因斯坦数学研究所）

作者：Yitzchak Shmalo

英文摘要：We combine neural network means with exact Matérn kernel regressions of their residuals and of their learned features, and evaluate the pairing on two public emulation problems with published baselines: the structural-mechanics benchmark of de Hoop et al. and the OCO-2 radiative-transfer emulator of Lamminpää et al. On structural mechanics the combination reaches 4.55% test error, matching the best published architecture, and 5.38% against a published 6.49% in the low-data regime. On OCO-2 it improves on the published Gaussian-process emulator on that problem's own test points, outright on two of the three spectral bands; the same kernel that trails the network tenfold on the raw state overtakes it on the network's features, and we measure why (the target's squared native-space norm drops about fortyfold at fixed effective dimension) and prove the mechanism. Where the two families tie instead, the residuals of every architecture we train correlate above 0.86 and their shared component is flat in diversity and sample size, which reads the published plateau as a property of the data. Supporting results include a second-moment identity that predicts stacking outcomes from measured correlations, an optimal-recovery certificate, and a distribution-free coverage band, the only uncertainty signal that survives our tests.

AI 总结：本研究提出GenONet，将DeepONet作为GAN的生成器，结合对抗训练与物理信息损失，实现了长时程高分辨率降水预报，在多数指标上优于基线模型。

链接：https://arxiv.org/abs/2609.00544

作者：Mohammad Kian Golkar, Luciano Alves de Oliveira, Mohammad Khanjani

英文摘要： High-resolution precipitation nowcasting is critical for reducing the impacts of severe weather but remains difficult because of rapid storm evolution. Deep learning models have shown great promise for this task, but their predictive skill often deteriorates over longer forecast horizons. This leads to increasingly blurry forecasts that fail to capture the complex, non-linear evolution of storm systems. In order to address these limitations, we introduce Spatio-Temporal U-DeepONet (GenONet), a novel architecture for long-range precipitation forecasting up to 3 hours, specifically designed to produce sharp and physically consistent results. GenONet's architecture pioneers the use of a Deep Operator Network (DeepONet) as a generator within a Generative Adversarial Network (GAN) framework for this task. The DeepONet learns the continuous-time dynamics of precipitation, ensuring stability over long forecast horizons. Adversial training against a spatio-temporal discriminator compels the model to produce sharp, coherent forecasts, while a physics-informed loss regularizer, derived from the Moisture Conservation Equation, improves physical plausibility in our ablation setting. Quantitative evaluations show that our model achieves consistently higher scores on most of the metrics, especially for highintensity events and at longer lead times. Qualitatively, GenONet produces structurally coherent forecasts that maintain their integrity, whereas baseline models degrade into indistinct patterns. Finally, an ablation study confirms the benefit of this physics-informed loss, highlighting the strength of combining operator learning with adversarial training.

AI 总结：本研究将条件流匹配（CFM）集成至EngiOpt，在EngiBench的两项基准任务上对比条件扩散模型与cGAN，结果显示CFM的性能更优、采样速率更高且所需网络评估次数更少。

链接：https://arxiv.org/abs/2609.00863

机构：ETH Zürich（苏黎世联邦理工学院）； University of Maryland, College Park（马里兰大学帕克分校）

作者：Juliana Felder, Milad Habibi, Soheyl Massoudi, Mark Fuge

英文摘要：Engineering inverse design is often limited by the high computational cost of iterative solvers for optimization problems constrained by partial differential equations (PDEs) and by their sensitivity to initialization. Deep generative models can produce candidate designs without rerunning the simulator at inference time. Generative adversarial networks (GANs) sample in one forward pass, whereas diffusion models require iterative reverse-time integration. In this work, we add conditional flow matching (CFM) to EngiOpt and compare it with a conditional diffusion model and a conditional generative adversarial network (cGAN) on structural (beams2d) and thermal (heatconduction2d) benchmarks from EngiBench using the same downstream optimization protocol. We use cumulative optimality gap (COG) and final optimality gap (FOG) as the primary metrics for evaluating the generated designs as warm starts for gradient-based refinement. On the evaluated EngiOpt implementations and two EngiBench tasks, CFM achieves the lowest measured COG, FOG, maximum mean discrepancy (MMD), and volume-fraction deviation on both tasks. CFM has mean volume-fraction deviations of 0.4% and 1.0% on beams2d and heatconduction2d, respectively, compared with 3.8% and 11.2% for diffusion. At Euler s = 16, CFM achieves 53.2 samples/s on beams2d, about 66 times the measured throughput of the evaluated diffusion baseline using 1000 network evaluations under the same timing protocol, with COG 1.182 +/- 3.126, compared with 1.173 +/- 3.100 for Euler s = 32. Across the two tasks, CFM produces warm starts with lower measured COG than both baselines and uses fewer network evaluations than diffusion.

AI 总结：该研究针对均匀离散扩散模型提出无需训练的采样器 CRS，通过将所选 token 作为持久上下文插入后续输入，在 8-64 NFE 预算下实现更优的 GenPPL-熵权衡。

链接：https://arxiv.org/abs/2609.01043

机构：The University of Tokyo（东京大学）

作者：Satoshi Hayakawa

英文摘要：Uniform-state discrete diffusion models update all tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a training-free sampler that stores selected argmax tokens and inserts them into subsequent model inputs. Our analysis gives a rationale for selecting later and for keeping selected tokens visible. Under the exact forward process, the Bayes error of selecting a clean token cannot increase as noise decreases, while in a simple latent-mode model, keeping the selected token visible helps later parallel predictions agree on the same sequence-level choice. Empirically, paired experiments on Duo-distilled then separate this persistent effect from single-step top-$p$ restriction and scalar temperature scaling. Under the same finalization rule, CRS without top-$p$ truncation reaches lower generative perplexity (GenPPL) than fixed $p=0.95$ and $p=0.9$ baselines across budgets of 8--64 function evaluations (NFE). At 64 NFE, the comparison at matched unigram entropy also gives lower GenPPL for CRS, yielding a more favorable GenPPL--entropy tradeoff. Base Duo shows the same direction in a descriptive comparison, while other diversity and continuation metrics can rank these operating points differently. These results identify support restriction and persistent context as distinct controls of that tradeoff.

AI 总结：该研究通过为扩散去噪器添加持久隐藏状态、移除时间步长条件，提出一种随时可用的迭代推理求解器，在极端数独、唯一迷宫上取得高求解率，核心是利用扩散的去噪训练课程。

链接：https://arxiv.org/abs/2609.01449

机构：University of Geneva（日内瓦大学）； McGill University（麦吉尔大学）； Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）； CIFAR（加拿大高级研究所）

作者：Mariia Drozdova, Aidan Sirbu, Pietro Miotti, Robert Obryk, Mayalen Etcheverry, Eyvind Niklasson, Blake Richards

英文摘要： Diffusion models and recursive reasoners are both iterative, but they carry information across iterations differently. We add a persistent hidden state to a diffusion denoiser and remove its timestep conditioning, leaving a single shared update that can be run to arbitrary depth. The result is an anytime solver: accuracy keeps improving with inference depth far beyond the rollout lengths and backpropagation window used in training, reaching 99.90% exact solve on Sudoku-Extreme. We also obtain 98.93% solve rate on Maze-Unique. Surprisingly, progressive denoising is unnecessary at inference: holding corruption at its maximum by replacing every non-clue variable with fresh Gaussian noise at each step retains near-perfect solving and converges to stable solutions. This simple noise-injection mechanism enables a single trajectory to efficiently explore the solution space and settle on the correct answer without parallel rollouts, candidate selection, or external verifiers required by prior reasoning models. Nonetheless, ordered annealed corruption remains critical during training, which suggests that diffusion's primary contribution to our anytime solver is not a sampling procedure at inference, but a denoising training curriculum.

AI 总结：针对现有大语言模型训练后量化方法的信息失配问题，REAL-Q采用端到端损失对齐代理与动态块级梯度下降，在主流模型W4A16量化下将端到端KL散度最高降低约49%。

链接：https://arxiv.org/abs/2609.00049

机构：Peking University（北京大学）； Northeastern University（东北大学）； ZTE Corporation（中兴通讯股份有限公司）

作者：Qian Zhang, Yaoming Li, Zhewen Tan, Yanshu Wang, Heng Lu, Kun Su, Zongwei Lv, Wenhan Yu, Yongge Ma, Yinjun Han, Ruikuang Liu, Tong Yang

英文摘要：Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ methods quantize each layer with a single closed-form second-order solver: to remain analytically tractable, they heavily approximate the global loss (dropping cross-channel coupling, pooling output rows into groups), and they then freeze the resulting Hessian across the entire layer, with no way to refresh it as the loss landscape shifts column by column--a phenomenon we call information misalignment. We propose REAL-Q (Real-time E2E-loss Aligned LLM Quantization), a novel PTQ paradigm that breaks this compromise: instead of diluting the objective for the sake of analytic tractability, REAL-Q targets an end-to-end-aligned surrogate of the global loss and refines it via fine-grained, dynamic Block-wise Gradient Descent applied after every column block (128 columns). By coupling this fine-grained correction with a sliding window mechanism for smooth cross-layer transitions, REAL-Q effectively mitigates error propagation across the network. On LLaMA-3.1 (8B and 70B) and Qwen3 (0.6B-32B) at W4A16, REAL-Q reduces end-to-end KL divergence by up to ~49% relative to state-of-the-art globally-guided methods.

AI 总结：本文将基于奇异学习理论的模式化方法用于去偏奖励模型，利用偏好对的敏感性重新加权，在RM-Bench Hard上取得显著提升，权重可跨模型迁移，为奖励模型去偏提供了新方案。

链接：https://arxiv.org/abs/2609.00699

机构：Resolution（睿策尔（Resolution））

作者：George Wang, Elizabeth Donoway, Daniel Murfet

英文摘要：Reward models trained on human preferences are known to suffer from length, formatting, and other stylistic biases. In this paper we use patterning, which reweights each preference pair according to its measured effect on posterior expectation values of benchmark losses (its susceptibility), to debias a Gemma 2 9B Instruct reward model trained on Skywork-Reward-Preference v0.2. We obtain $+14.2 \pm 1.2$ pp on RM-Bench Hard, the split where style cues point against correctness (mean $\pm$ s.e.\ over 5 seeds), with overall RM-Bench accuracy preserved, comparable to the strongest Hard-split gain reported by the closest published comparator (SteerRM, $+13.2$ pp). We demonstrate in a simple case that the reweighting is interpretable by tracing a side effect of the intervention (a regression on a safety subset of RM-Bench) to a small class of training pairs, which we confirm by ablation. The weights also transfer: those computed on Gemma 2 9B debias Gemma 2 2B and 27B with no recomputation, and transfer partially to Llama 3.1 8B. This is the first application of patterning, a program grounded in singular learning theory, beyond small models and synthetic tasks.

AI 总结：本研究针对中小规模神经网络训练中LM算法开销随参数增长的问题，评估子空间LM算法在回归分类任务的表现，并与经典LM、SGD、Adam等方法对比性能。

链接：https://arxiv.org/abs/2609.00789

机构：University of California, Davis（加州大学戴维斯分校）

作者：M. Duc Hoang

英文摘要：The Levenberg-Marquardt (LM) algorithm is a well-known second-order method for rapid convergence and strong robustness when training small- to medium-sized neural networks (NNs). However, its computational and memory costs increase significantly as the number of parameters in an NN grows. To address this limitation, subspace methods have been proposed, such as the Krylov subspace LM (KSLM) and the hybrid subspace LM (HSLM), making second-order algorithms more efficient. In this work, we evaluate the subspace Levenberg-Marquardt algorithms for regression and classification tasks in neural networks. We compare the performance of subspace LM variants with the classical LM method, as well as other popular first-order algorithms, such as stochastic gradient descent (SGD) and Adam.

AI 总结：该研究针对Cohen等人2025年提出的启发式推导的中心流，通过多尺度微扰方法，分析稳定性边界上梯度下降的三个时间尺度，推导中心流及自稳定机制，解释波动持续的原因。

链接：https://arxiv.org/abs/2609.01034

机构：Sorbonne Université（索邦大学）； Inria（法国国家信息与自动化研究所）； Centre Inria de Sorbonne Université（索邦大学法国国家信息与自动化中心）

作者：Raphaël Berthier

英文摘要：The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning, However, its derivation is heuristic. We propose a perturbative regime in which the central flow is the limit of gradient descent: we assume that the loss decomposes as $f = g + \varepsilon h$; in the limit $\varepsilon \to 0$, the dynamics of gradient descent with learning rate $\eta$ converge to the gradient flow of $h$ constrained to the minimizers of $g$ of sharpness at most $2/\eta$. Our approach is formal rather than rigorous; it treats gradient descent as a singularly perturbed dynamical system in $\varepsilon$. Three timescales emerge: a fast timescale of oscillations along the sharpest direction, an intermediate timescale of the self-stabilization mechanism, and a slow timescale of the dynamics along the minimizers of $g$-the central flow. Using the method of multiple scales, a classical formal method from singular perturbation theory, we derive the expansion of the dynamics in $\varepsilon$: the central flow emerges as the leading-order term in the expansion, while the self-stabilization mechanism appears in the next-order term. We study this mechanism beyond previous analyses: with a single eigenvalue at the edge of stability, we compute the slow drift of the energy of the fluctuations; with several eigenvalues at the edge of stability, we derive the self-stabilization system and explain why fluctuations persist.

AI 总结：该研究提出幂律熵搜索（PLES），一种基于多保真度贝叶斯优化的获取函数，可高效估计LLM的最优超参数缩放定律，其计算预算仅为传统网格搜索的十分之一。

链接：https://arxiv.org/abs/2609.01431

机构：Meta； National University of Singapore（新加坡国立大学）； Atomic Machines（原子机器公司）

作者：Zhiliang Chen, Sebastian Ament, David Eriksson, Maximilian Balandat, Eytan Bakshy, Jihao Andreas Lin

英文摘要：Optimal hyperparameter scaling laws describe how the best hyperparameters for large language model (LLM) training change with model and data scale, enabling practitioners to predict optimal configurations at production scales without expensive large-scale tuning. However, estimating these scaling laws conventionally requires exhaustive grid searches over thousands of training runs, consuming enormous computational resources. We introduce Power-Law Entropy Search (PLES), a computational cost-aware acquisition function built on multi-fidelity Bayesian optimization that efficiently estimates optimal hyperparameter scaling laws through adaptive experimentation. A key innovation in PLES is that it searches for candidates that reduce the overall uncertainty of a scaling law estimate, instead of optimizing a single objective function. At each iteration, PLES selects the candidate configuration that maximally reduces the uncertainty of the scaling law estimates per unit computational cost, naturally favoring informative small-scale experiments. We evaluate PLES on synthetic benchmarks, surrogate models fitted to real LLM training data, and actual LLM pre-training runs. Across all settings, PLES converges to accurate optimal hyperparameter scaling laws using less than one-tenth of the computational budget required by conventional grid search and other baselines.

AI 总结：本文提出算法依赖型可学习性，设计轨迹学习框架，提出UGTL方法，在五个Design-Bench任务上的25种方法中取得最佳综合平均排名3.1/25，验证了轨迹构建的重要作用。

链接：https://arxiv.org/abs/2609.01493

机构：Nanjing University（南京大学）

作者：Chao Qian, Chen-Guang Wang, Rong-Xi Tan, Ke Xue

英文摘要：Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficiency of BBO algorithms by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires no additional online evaluations. Many offline optimization methods have been proposed, but a fundamental question remains unanswered: what learnability is sufficient for offline optimization? Prior theoretical studies show that Probably Approximately Correct (PAC) learnability is insufficient, as the optimal region may remain poorly learned even when most regions are well learned. In this paper, we propose algorithm-dependent learnability, which requires accuracy only on the optimizer's trajectory. We prove that its value-query form is sufficient for representative discrete settings, including greedy and local search for submodular maximization, while its first-order analogue is sufficient for projected gradient descent on convex minimization. Motivated by this notion, we formalize a trajectory-learning framework comprising trajectory construction, trajectory modeling, and candidate generation, and analyze existing trajectory-based methods under it. We further propose Uncertainty-aware Gradient-guided Trajectory Learning (UGTL), which constructs locally coherent improvement trajectories reflecting plausible search paths, models them with conditional diffusion, and selects a diverse candidate set. On five Design-Bench tasks, UGTL achieves the best aggregate mean rank, $3.1/25$, among 25 methods. Controlled trajectory analyses and cross-architecture replacements confirm that our trajectory construction plays a significant role in the improvement.

AI 总结：针对低数据下材料属性预测依赖结构的问题，提出 DISTAL 框架，结合自监督组成预训练与结构感知蒸馏，在 39 项基准任务中表现最优，实现仅基于组成的稳健预测。

链接：https://arxiv.org/abs/2609.00059

作者：Weiran Wang, Xintong Huo, Yueying Wang, Yusi Fan, Wenyan Wang, Xin Feng, Ruihao Xin, Lan Huang, Kewei Li, Fengfeng Zhou

英文摘要：Materials property prediction remains difficult in low-data settings, where many target properties are supported by only a limited number of labeled samples. Models with the strongest predictive accuracy often depend on crystal structures, which restricts their use in early-stage screening when structural information is limited or unavailable. To address this challenge, we propose DISTAL, a dual-prior framework for structure-agnostic materials property prediction that combines self-supervised compositional pretraining with structure-aware knowledge distillation. DISTAL first learns transferable compositional representations from a large virtual composition space using 145 composition-derived descriptors. It then distills structural knowledge from a pretrained ALIGNN teacher into a composition-conditioned student. This setting allows structural priors to be used during training without requiring structural inputs at inference. By integrating explicit compositional descriptors, pretrained latent features, and distilled structural features within a unified prediction pipeline, DISTAL captures complementary signals that are difficult to recover from any single representation alone. Across 39 benchmark tasks, the best-performing multimodal configuration combines all three signals, and improves over the reference benchmark on 37 tasks. DISTAL achieves the strongest overall performance among all evaluated feature combinations. These results indicate that compositional pretraining and structural distillation provide complementary priors and offer a practical route to robust composition-only prediction in small-data materials informatics. The source code and the pre-trained models are anonymously available at: this https URL and will be released at the official link after acceptance.

AI 总结：本文提出特质方向漂移作为阈下学习的机制，并提出探针空间走廊正则化方法，可有效降低隐藏特质转移，同时保留任务性能，尤其在Qwen设置下表现稳定。

链接：https://arxiv.org/abs/2609.01091

机构：Shanghai Jiao Tong University（上海交通大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Fudan University（复旦大学）

作者：Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang

英文摘要：Beyond intended capabilities, model distillation can transfer hidden traits from a teacher. A teacher biased by a system prompt can generate semantically clean training data, such as numeric sequences, that still causes a downstream student to inherit the hidden preference, a phenomenon known as subliminal learning. Prior work has identified several parts of this process. How the signal builds up during training and produces behavioral transfer remains unclear, making targeted mitigation difficult. We propose and validate trait-direction drift as a mechanism for subliminal learning: biased generation creates measurable preference gaps in teacher data, and student-recognizable gaps induce trait-aligned updates during supervised fine-tuning that accumulate into behavioral transfer. Guided by this mechanism, we propose probe-space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction during distillation. The method substantially reduces hidden-trait transfer, preserving task performance: for example, it lowers malicious-response transfer from 29.55% to 6.45% with low main-task accuracy cost, and consistently suppresses animal-preference transfer across the main Qwen setting. The preference-gap, training-trajectory, and intervention evidence links subliminal learning to trait-direction drift and motivates corridor regularization as a targeted control during distillation.

AI 总结：该研究针对传统联邦学习的同质性假设局限，提出CRAD框架，通过类别级可靠性加权融合对等教师预测，在三类图像分类基准的异构非IID场景中实现更优全局准确率。

链接：https://arxiv.org/abs/2609.00446

机构：University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）

作者：Baraa Bilbeisi, Mengchen Fan, Baocheng Geng, Qing Tian

英文摘要：Conventional federated learning (FL) relies on parameter averaging, which forces clients to be doubly homogeneous: it demands an identical architecture and degrades under non-IID data. Real-world deployments usually break both assumptions. We sidestep both by building a decentralized knowledge distillation framework in which each client evaluates its peers' model snapshots on its own local data and distills from the resulting soft predictions. Because knowledge is transferred through the shared class posterior, clients are free to run different architectures; and because every teacher is evaluated on the student's own device, raw data never leaves the client, with no central server or public dataset required. Within this setting, we identify and address an under-examined problem: how to combine the peer teacher predictions. Existing methods, like uniform averaging, ignore how knowledge reliability varies across teachers and classes. We propose Class-wise Reliability-Aware Distillation (CRAD), which, per class, first discards teachers that disagree with the peer consensus and then takes a weighted average of the rest, weighting each teacher by its per-class reliability (precision, or inverse variance). Since the variance of an accuracy from $n$ samples scales as $1/n$, support enters automatically: among the teachers that survive filtering, a teacher is trusted for a class to the degree that it is both accurate and well-evidenced for it. On three image-classification benchmarks (CIFAR-10, CIFAR-100, and PathMNIST colon pathology), across heterogeneous architectures under severe non-IID skew, CRAD consistently outperforms competing methods in global accuracy.

AI 总结：针对LLM遗忘中遗忘集与模型知识错位的问题，提出数据盲框架CONFS，通过构建与模型对齐的遗忘集，实现了良好的遗忘-效用平衡，优于其他数据盲遗忘集构建方法。

链接：https://arxiv.org/abs/2609.00605

机构：Dongguk University-Seoul（东国大学首尔校区）

作者：Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee

英文摘要：Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequently breaks in realistic privacy settings where the original training data is inaccessible. We term this gap forget-set misalignment and identify two cases. In Under Unlearning, the forget set omits memorized information and leakage persists. In Out-of-Knowledge Unlearning, the algorithm is driven to "forget" knowledge the model never learned, perturbing parameters and degrading utility. Using gradient-level analysis, we show these behaviors arise from misaligned unlearning targets rather than specific optimization choices. We then propose CONfession-to-Forget-Set (CONFS), a data-blind framework that constructs model-aligned forget sets by eliciting and formalizing the model's memorized knowledge. Across synthetic, multimodal, and real-world benchmarks, CONFS approaches Gold-standard performance on several metrics and achieves a competitive forgetting-utility balance, while preserving utility better than other data-blind forget-set constructions.

AI 总结：该研究针对去中心化联邦学习（DFL）中拜占庭节点放置被忽视的问题，提出拜占庭放置影响力（BPI）度量并开发优化算法，经实验验证其能有效识别高破坏性配置，是DFL鲁棒性评估的关键维度。

链接：https://arxiv.org/abs/2609.01495

机构：Sapienza University of Rome（罗马大学）

作者：Edoardo Gabrielli, Gabriele Tolomei

英文摘要：Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication graph, the placement of Byzantine nodes determines how malicious influence propagates through the network. We therefore treat Byzantine placement as an explicit adversarial decision and formulate the attacker's objective as selecting, under a fixed compromise budget, the set of participants that maximizes its finite-time impact on honest nodes. To approximate this objective without executing the learning process for every candidate placement, we introduce Byzantine Placement Influence (BPI), a set-level measure derived from the actual gossip dynamics that quantifies the cumulative exposure of honest nodes to Byzantine sources over the training horizon. Unlike placement criteria based on node centrality heuristics, BPI directly accounts for weighted multi-hop propagation and interactions among compromised nodes. We develop efficient algorithms for optimizing BPI and evaluate them across six heterogeneous graph families, untargeted model poisoning, and backdoor attacks. BPI-guided placements consistently identify highly damaging configurations across different network structures and remain effective when the linear gossip assumption is relaxed through Byzantine-robust aggregation. Our results show that Byzantine placement is a critical but under-modeled dimension of DFL threat models and robustness evaluations.

AI 总结：AdaptNTK是面向神经网络势的单模型框架，通过神经正切核特征空间的正则化马氏距离量化不确定性，在rMD17和Transition-1X主动学习任务中实现低力误差与2.6倍加速，提升了数据效率。

链接：https://arxiv.org/abs/2609.00488

机构：Center for Applied Mathematics, Cornell University（康奈尔大学应用数学中心）； R. F. Smith School of Chemical and Biomolecular Engineering, Cornell University（康奈尔大学R.F.史密斯化学与生物分子工程学院）

作者：Prajwal Ananth, Shuwen Yue

英文摘要：Machine learning interatomic potentials bridge the gap between quantum chemical precision and classical computational speed, enabling molecular dynamics simulations with first-principles accuracy. Their reliability is often improved through active learning, which iteratively expands the training set by identifying uncertain, out-of-distribution configurations. Existing uncertainty-quantification methods often involve a trade-off between computational cost and reliability, and generally cannot account for redundancy as an acquisition batch is assembled. Here, we introduce AdaptNTK, a single-model framework that measures uncertainty as a regularized Mahalanobis distance in empirical neural tangent kernel (NTK) feature space. With the NTK features fixed during acquisition, the uncertainty depends on the acquired configurations but not their reference labels. This allows the uncertainty to be updated recursively after each selection without retraining, reducing redundancy within an acquisition batch. On held-out rMD17 data, AdaptNTK achieves the highest mean correlations with force errors (Spearman 0.68, Pearson 0.71) and matches a three-member ensemble in error retention. In active learning experiments, AdaptNTK achieves the lowest force errors across rMD17 and Transition-1X, with particularly strong performance on transition-state configurations in Transition-1X. AdaptNTK provides a 2.6-fold speedup per Transition-1X cycle relative to the ensemble, providing efficient single-model uncertainty estimation with sequential updates for data-efficient active learning.

AI 总结：该研究提出判决不稳定性概念，通过重采样参考集衡量OOD检测器分数的判决变动，给出闭式解，发现远OOD查询对应可复现判决，符号错误的弃权效果差。

链接：https://arxiv.org/abs/2609.00691

机构：Hongik University（弘益大学）

作者：Donghoon Lee, Shinjin Kang

英文摘要： Post-hoc out-of-distribution detectors are fitted on a finite reference set, so every score they produce is an estimate. If we had chosen a different set, some verdicts would have moved. We measure that movement by resampling the reference set and recording the bootstrap standard deviation of the score, which we call verdict instability. It admits a closed form with no fitted parameters. The instability of a verdict is the within-class dispersion of the assigned class along the query's direction, divided by the square root of that class's reference count. That count is what separates verdict instability from the geometry of the score distribution, and it is identifiable only under class imbalance. Instability grows with the local dispersion. Far-OOD queries lie along the low-variance directions of an anisotropic embedding, so every distance-based score we test assigns its highest values to the verdicts that are most reproducible. Only estimators of local dispersion carry the sign a practitioner expects. We give a rule that predicts this sign for any score from a single label-free correlation, and abstention driven by a wrong-signed score turns out worse than abstention at random on every dataset we test.

AI 总结：该研究针对事后校准会改变Top-1预测的问题，提出CORD适配器，通过修复校准概率向量实现零预测改变率，同时降低ECE、NLL和Brier等指标，在多数据集及分布偏移下均有效。

链接：https://arxiv.org/abs/2609.01072

机构：Hanyang University（汉阳大学）； Hankuk University of Foreign Studies（韩国外国语大学）

作者：Daehwan Kim, Haejun Chung, Ikbeom Jang

英文摘要：Post-hoc calibration corrects reported confidence, yet a multiclass calibrator can also change the associated top-1 prediction. Accuracy captures only the net effect of these changes on correctness, not how often predictions change; the Top-1 Prediction Change Rate (TPCR) instead measures this frequency. We propose Calibrator-Output Repair for Top-1 Decision Preservation (CORD), the first post-fit adapter to impose exact prediction preservation by repairing the full calibrated probability vector. From the original and calibrated outputs alone, CORD determines the mass assigned to the original top-1. The calibrated conditional distribution allocates the remaining mass over the other classes, yielding a repaired vector whose own argmax recovers the original prediction. On the calibration split, CORD coordinates the repaired masses to retain the calibrated outputs' mean mass on original predictions whenever attainable. The adapter alters neither the fitted calibrator nor its direct output, fits no additional supervised map, and requires no user- or validation-tuned hyperparameter. Across CIFAR-10/100 and ImageNet-1K, CORD attains zero TPCR by construction and lowers mean ECE, NLL, and Brier relative to the corresponding direct outputs in every dataset; paired gains persist under distribution shift and across calibration-set sizes. CORD thus removes the preservation constraint from calibrator fitting and assigns exact recovery of the original decision to subsequent output repair. Our code is available at this https URL.

AI 总结：本研究提出一种神经符号回归框架，将神经网络作为符号发现的预处理器，结合LASSO与分布式超参数优化，在Nguyen基准上的实验显示其性能优于SINDy及未调参神经基线，为科学机器学习提供了可扩展的神经符号方法。

链接：https://arxiv.org/abs/2609.01102

机构：Indian Institute of Space Science and Technology（印度空间科学与技术学院）

作者：Ravi Kumar U, Sumitra S

英文摘要：Symbolic Regression (SR) seeks to find succinct mathematical expressions that represent the fundamental relationships within data, providing interpretability and scientific understanding that exceeds that of black-box models. Nevertheless, traditional methods like Genetic Programming face challenges with scalability and are highly sensitive to noise, while sparse regression techniques such as SINDy rely significantly on predetermined feature libraries. In this work, we present a Neural Symbolic Regression (NSR) framework that treats neural networks as functional preconditioners for symbolic discovery. Our approach uses a decoupled pipeline: a neural network first learns a smooth, noise-robust approximation of the target function in an interaction- aware nonlinear feature space. LASSO is then applied to extract sparse, interpretable closed-form expressions. To improve predictive accuracy and symbolic fidelity by integrating distributed hyperparameter optimization with Ray Tune and ASHA scheduling. Experiments on the Nguyen benchmark suite show that our approach consistently outperforms SINDy and non-tuned neural baselines in RMSE, noise robustness, and out-of-distribution generalization. Ablation studies confirm the significance of feature interactions, neural depth, and tuning strategies. In general, this study presents a scalable and understandable neural-symbolic framework, creating a solid link between neural approximation and the discovery of sparse equations for scientific machine learning.

AI 总结：本文针对电商优惠券滥用检测中欺诈模式演变引发的分布偏移问题，提出CATeye框架，通过AIS与EIS选择不变属性和边，构建多视图优化，在Lazada数据集及公开基准上较9种基线最高提升平均F1分数8.61%。

链接：https://arxiv.org/abs/2609.01425

机构：Nanyang Technological University（南洋理工大学）； Lazada Inc.（来扎达公司）； Alibaba Group（阿里巴巴集团）

作者：Tian Tian, Shuaicheng Niu, Hao Kuang, Yuanhang Hu, Dong Li, Zhiqi Shen

英文摘要： Voucher abuse poses a major challenge in e-commerce, where malicious users exploit promotional vouchers for profit. Unfortunately, fraud patterns evolve rapidly over time and across regions, causing distribution shifts that degrade existing detection models unless retrained frequently. To tackle this, we propose the Coupled Attribute-Topology Invariance Learning framework (CATeye). The key challenge arises from coupled attribute-topology shift, where edges built from attribute proximity cause environment-driven attribute shift to induce shifted topology, thereby amplifying variant signals through GNN message passing. CATeye sees through such coupled shifts with two learnable selectors. First, an Attribute Invariance Selector (AIS) learns node-adaptive masks to filter out non-invariant attributes. Then, conditioned on retained invariant attributes, an Edge Invariance Selector (EIS) samples an invariant subgraph and isolates non-invariant edges. Using the resulting invariant and non-invariant components, CATeye constructs multiple views and applies view-specific objectives to emphasize domain-invariant representations while suppressing domain-specific variations. Experiments on both a proprietary dataset from Lazada, a major Southeast Asian e-commerce platform, and a public benchmark show that CATeye consistently outperforms nine strong domain generalization and graph anomaly detection baselines, achieving up to an 8.61% improvement in average F1 score over the strongest baseline. Source code is publicly available at this https URL.

AI 总结：该研究提出图神经网络原子间势的多层完备性理论，证明超图神经网络是势能面通用近似器，为实际应用的多层消息传递设置提供严格依据，并表明DPA3、CHGNet具备通用近似能力。

链接：https://arxiv.org/abs/2609.00528

机构：Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences（中国科学院数学与系统科学研究院计算数学与科学工程计算研究所）； Institute of Applied Physics and Computational Mathematics（应用物理与计算数学研究所）； College of Engineering, Peking University（北京大学工学院）

作者：Pingbing Ming, Han Wang

英文摘要：We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy surfaces. Our main contribution is a multi-layer completeness theory. We show that $L$ layers of message passing on sparse, cutoff-based graphs achieve the same representational power as having access to the full $L$-hop neighborhood, provided the configurations are generic, satisfy an overlap condition and a connectivity condition. This provides the first rigorous justification for the common practice of using multi-layer message passing with a per-layer cutoff smaller than the physical interaction range, the setting used by virtually all practical graph neural network based machine-learned interatomic potentials. As immediate consequences, we show that both DPA3 and CHGNet architectures inherit universal approximation.

AI 总结：本文提出将边围长及其重数作为结构边特征，构建EGAGNN模型，在ZINC-12k回归基准上表现优于对比模型，但在BREC基准的特定图对上无法突破1-WL界限。

链接：https://arxiv.org/abs/2609.01441

机构：LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI、巴黎电信学院、巴黎综合理工学院）

作者：Lilian Marey, Charlotte Laclau

英文摘要：Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot tell apart receive identical representations, however deep or wide the network. A common remedy augments node or edge features with precomputed structural descriptors, most often counts of a fixed small subgraph such as triangles or longer cycles, but such counts require committing in advance to the size of the substructure counted, a choice usually made blind to the data. We study a descriptor that avoids this choice. The edge-girth of an edge is the length of a shortest cycle through it, and its multiplicity is the number of such shortest cycles; together they form a per-edge invariant that reports cycles of arbitrary length, computable exactly by a single breadth-first search per edge. Injected into a gated message-passing architecture, EGAGNN, it reaches a test MAE a factor three below the closest gated comparator on the ZINC-12k regression benchmark at 104k parameters; against bounded cycle-counting descriptors under the same architecture, it matches only a dictionary counting cycles up to length eight, using twice as many channels, while a dictionary capped at length four performs no better than no structural information at all. On graph discrimination we prove a matching limitation: on graphs where every edge sees the same number of shortest cycles of the same length, the descriptor becomes constant and any model built on it collapses back to the 1-WL bound. This holds without exception across all 400 pairs of the BREC benchmark: not one of the 90 such pairs is distinguished.

AI 总结：本文提出RW-LoRA，一种基于随机游走的去中心化LoRA微调方法，无需多副本同步，可降低通信计算成本且避免聚合误差，在NLP任务上性能与gossip式LoRA相当但开销显著减少。

链接：https://arxiv.org/abs/2609.00078

机构：Singapore University of Technology and Design（新加坡科技设计大学）； LinkedIn（领英公司）； Technical University of Munich（慕尼黑工业大学）； Texas A&M University（德克萨斯农工大学）； Rutgers University（罗格斯大学）

作者：Xingran Chen, Rohit Bhagat, Ghadir Ayache, Rawad Bitar, Yanmin Gong, Salim El Rouayheb

英文摘要： Parameter-efficient fine-tuning methods such as LoRA have become a standard approach for adapting large foundation models. Adopting fine-tuning to distributed settings faces several challenges. Most existing distributed LoRA methods rely on centralized aggregation, and gossip-based decentralized LoRA requires repeated synchronization among multiple model copies. Both methods incur significant communication overhead and introduce errors due to simultaneous aggregation of multiple model updates. In this paper, we take a different perspective and propose a random-walk-based LoRA fine-tuning scheme. Instead of maintaining multiple model replicas, a single model token traverses the network and is updated sequentially using local fine-tuning objectives. This design eliminates the need for global synchronization, substantially reduces communication and computation costs, and avoids aggregation errors. We provide rigorous convergence guarantees for non-convex objectives under standard assumptions. Through empirical results on multiple NLP tasks and graph topologies, we show that the proposed method achieves competitive task performance with substantially less communication and computation than gossip-based LoRA.

AI 总结：Safin-1 是遵循「内在安全」理念的基础模型系列，基于 MARCH 架构实现内存路由与状态演化，可提升下游安全任务性能，为安全能力的原生自适应维持提供路径。

链接：https://arxiv.org/abs/2609.00092

作者：Ming Zhang, Kaisen Yang, Shu Yu, Ermo Hua, Zhekai Chen, Cheng Jin, Jingnan Zheng, Yi Zhang, Zhongtian Ma, Jiawei Zhou, Sirui Chen, Qiaosheng Zhang, Xiang Wang, Ning Ding, Xia Hu, Bowen Zhou, Youbang Sun, Chaochao Lu

英文摘要：Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic property of the model itself, rather than a behavioral constraint relying solely on external safeguards or post-hoc alignment such as supervised fine-tuning. This motivates Safety from Within, where safety-relevant capabilities are represented and invoked through the model's native computation. We present Safin-1, a family of foundation models realizing this principle through memory routing and state evolution. Safin-1 is built on Memory-Anchor Routing across Context History (MARCH), a network architecture that maintains structured memory states and selectively retrieves relevant historical information through content-conditioned routing. It supports test-time adaptation of persistent capability states without repeatedly modifying the backbone, enabling controlled specialization over a shared foundation. We investigate this interface on downstream safety tasks through a Safety State, demonstrating effective state-based adaptation with substantial safety improvements. More broadly, the routed-state interface unifies contextual memory and persistent capability adaptation within the model's native computation, reframing memory from a passive record of prior context into an active substrate for maintaining and evolving model behavior. Evaluations across general capabilities, long-context understanding, retrieval, and efficiency further validate Safin-1. These findings provide a path toward safety as a state-native and adaptively maintainable capability. This work is only an initial architectural exploration of Safety from Within, and substantial further work is needed to realize this broader vision.

AI 总结：本文提出无梯度测试时适应方法CASTER，针对冻结模型部署，其在多数场景优于k-NN且状态量更小，还提出传输性证书判断仿射传输可靠性，门控可提升性能，证书具机制特异性。

链接：https://arxiv.org/abs/2609.00374

机构：Talan Research Center（塔兰研究中心）

作者：Salim Khazem, Ibrahim Mohamed Serouis

英文摘要：Test-time adaptation (TTA) typically assumes that model parameters can be updated at inference time. This assumption is restrictive for inference-only accelerators, frozen or third-party models, and memory-constrained deployments, and standard BatchNorm-based TTA configurations may also become inactive on architectures without BatchNorm. We study adaptation when the learned model must remain frozen. We introduce CASTER, a gradient-free method that stores source class statistics in a discriminative subspace, estimates a class-shared affine transformation from target-batch moments, and analytically transports the source class distributions before classification. CASTER requires no backward pass, optimizer state, or stored source feature bank. Across four backbones and seven datasets, it outperforms k-NN on identical frozen features in 27 of 28 backbone-dataset settings while retaining a median of 18x less state. Affine transport is not always reliable. On ImageNet-C, where batches contain only 64 samples for 1000 classes, unconditional transport loses 21.2 top-1 points. We therefore introduce an empirical residual-to-margin transportability certificate. Across 307 evaluation cells, every transport losing more than 10 points has certificate value above 3.9, although benign and destructive regimes are not perfectly separated. Gating converts an average $-3.35$-point effect of unconditional transport into a +1.69-point gain, and performance remains within 0.3 points of the best threshold over a broad threshold range. Finally, we show that this certificate is mechanism-specific: when applied to Tent, it accepts only $4.3\%$ of updates and preserves 0.6% of Tent's available gain. These results position CASTER as a lightweight adaptation mechanism for frozen-model deployment, together with an explicit account of when its safety signal is informative and when it is not.

AI 总结：本文针对6G RAN中电信LLM的预可解释性冷启动障碍，提出CRAFT方法，通过生成验证数据集微调SLM，在低能耗下实现高准确率与F1值，为可审计AI部署提供可行方案。

链接：https://arxiv.org/abs/2609.00590

机构：NextG Wireless Lab（下一代无线实验室）； NCSU（北卡罗来纳州立大学）

作者：Pranshav Gajjar, Vijay K Shah

英文摘要： The next generation of mobile networks is envisioned as fully AI-native, with AI-RAN architectures embedding small language models (SLMs) to perform reasoning over real-time telemetry. The state-of-the-art training paradigms for telecom LLMs, exemplified by RANSTRUCT-style supervised fine-tuning (SFT) on curated instruction data, are limited to post hoc rationalization. Here, the explanations, when produced at all, are generated after or independently of the decision, leaving the decision process unauditable. Pre-hoc reasoning, where a causal reasoning trace is produced before the output label, is preferable, and the broader LLM reasoning literature has made real progress toward it via RL methods such as Group Relative Policy Optimization (GRPO). Here we observe that transplanting this recipe into the telecom setting runs into a cold-start barrier: SLMs either learn to output the desired format or learn to predict the label, but rarely both. We identify this barrier and propose CRAFT, which stands for Cold-start Reasoning Alignment via Fine-Tuning, a data-centric method to autonomously generate a verified dataset of (input, trace, label) triplets. CRAFT fine-tunes SLMs on this verified data using low-rank adaptation (LoRA), requiring substantially less compute and wall-clock time than GRPO-based methods. On the TRACTOR and IC xApp telecom datasets, CRAFT achieves up to 86.5% and 94.6% for accuracy and F1 with no parse failures, while direct GRPO and SFT+GRPO fail to exceed 28% and 53.5% F1 with multiple parse failures. We further show that CRAFT-initialized policies serve as a robust foundation for subsequent GRPO fine-tuning, as under diverse reward functions the performance remains consistent with no parse failures. Finally, we demonstrate that CRAFT consumes 59% less energy than GRPO-based baselines, making it a sustainable path to deployable, auditable AI in 6G RAN.

AI 总结：针对秩异质性联邦学习中现有方法无法捕捉客户端特定特征的问题，本文提出FedRoRA框架，通过解耦适配方向与幅度实现细粒度个性化，在NLU与NLG基准上性能优于现有最优方法。

链接：https://arxiv.org/abs/2609.00632

机构：University of Florida（佛罗里达大学）； Middle Tennessee State University（中田纳西州立大学）

作者：Lei Wang, Jieming Bian, Letian Zhang, Jie Xu

英文摘要：Large Language Models (LLMs) have achieved remarkable success across diverse domains, but their adaptation to privacy-sensitive, distributed datasets remains a challenge. While Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) provides a resource-efficient paradigm for collaborative fine-tuning, practical deployments are hindered by the dual challenges of resource heterogeneity and data heterogeneity. Existing rank-heterogeneous methods primarily focus on bridging dimension mismatches for aggregation but typically provide a unified global model for all clients sharing the same rank, failing to capture client-specific features in non-IID scenarios. In this paper, we propose FedRoRA (Federated Rank-wise Personalized LoRA), a novel framework that enables fine-grained personalization within rank-heterogeneous federations. FedRoRA decouples adaptation into shared global directions and personalized rank-wise magnitudes governed by learnable diagonal scales. On the server side, it extracts a global subspace via singular value decomposition (SVD) and redistributes client-specific initializations through a personalized projection and top-$k$ selection mechanism. Extensive experiments on NLU and NLG benchmarks demonstrate that FedRoRA consistently outperforms state-of-the-art methods.

AI 总结：该研究提出FCCA方法，通过固定权重矩阵基并优化小尺寸核心，在低资源预算下实现大语言模型高效适配，在多任务多模型上表现优异，参数规模远低于LoRA、DoRA等方法。

链接：https://arxiv.org/abs/2609.00762

机构：Zhejiang University（浙江大学）； Hunyuan, Tencent（腾讯混元）

作者：Wentao Ye, Zhanming Shen, Zhiqing Xiao, Yao Ding, Haobo Wang, Gang Chen

英文摘要：Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is equally consequential. We study this choice through frozen-core adaptation: a calibration pass fixes left and right bases for each weight matrix, and fine-tuning optimizes only an $r\times r$ core. This removes the ability of trainable factors to repair a poor initial span and makes subspace quality directly observable. We introduce FCCA, which estimates the signed input--error cross-covariance, whitens it with diagonal Fisher moments, truncates it in the resulting local metric, maps the selected directions back, and applies thin QR to obtain stable core coordinates. Under a matched $r^2$ budget, we compare eight basis constructors on 11 tasks, four model settings, and three seeds. On Qwen2.5-3B, FCCA reaches an 83.0 macro-average, 2.3 points above the next-best matched-budget constructor, and exceeds its unwhitened RawGrad control on all 11 tasks. It ranks first at all three Qwen scales and finishes within 0.13 points of the best method on Llama-3.2-1B. Controlled ablations show gains of 2.7--17.2 points from whitening and identify QR as necessary for stable core optimization in the tested regime. Finally, FCCA comes within 0.32 and 0.23 average points of LoRA and DoRA while optimizing 36.9K rather than roughly 7.4M parameters. These results show that a carefully selected fixed span can recover most of the benefit of movable low-rank factors at a much smaller trainable and optimizer-state cost.

AI 总结：该研究针对大语言模型推理的块量化设计空间不足问题，提出分层块量化HBQ，通过二级尾数缩放补偿大块误差，实现了比现有权重量化和块量化更高的面积、能量效率与推理速度，达到最优精度。

链接：https://arxiv.org/abs/2609.00450

机构：Cornell University（康奈尔大学）； Intel Corporation（英特尔公司）

作者：Chun-Ting Chen, Dongmin Han, Hangyeol Mun, Jake Hyun, Arnab Raha, Amit Agarwal, Mark Anders, Mohamed Abdelfattah, Jae-sun Seo

英文摘要： Block Quantization (BQ) is a promising approach for efficient deployment of large language models (LLMs), enabling low-precision computation with controlled accuracy degradation. Compared to scalar weight-only quantization (WoQ), BQ quantizes both weight and activation, offering higher hardware efficiency and end-to-end inference on a unified datapath, but its design space, spanning bit-width, block size, scaling, and numeric formats, remains underexplored. We provide hardware/benchmark results through design space exploration (DSE). We find that increasing block size improves hardware efficiency by amortizing dequantization and accumulation costs, but degrades accuracy. This trade-off limits conventional BQ methods. Motivated by this insight, we propose Hierarchical Block Quantization (HBQ). Unlike prior methods [1], [2], which use small blocks and conventional Power-of-Two (PoT) or integer-based scaling, HBQ uses large blocks to maximize efficiency and introduces low-overhead significand (SIG) scaling for second-level quantization. By allocating quantization levels effectively and accounting for distinct activation and weight distributions, SIG scaling compensates for large-block errors more effectively than prior PoT and INT schemes. HBQ-A (accurate) achieves W4A16-level accuracy using only W4A5 while requiring less silicon area than NVFP4. HBQ-E (efficient) further reduces hardware cost by 17% while maintaining higher accuracy than all existing BQ methods. We implemented a 28nm ASIC accelerator applying HBQ to weights, activations, and KV cache, and integrated a novel partial-sum BQ scheme to further reduce EMA energy. Compared to state-of-the-art WoQ, HBQ delivers $2.3\times$/$4.6\times$ higher area/energy efficiency at the same accuracy level; $1.6$--$3.3\times$ system energy reduction and $1.5$--$3.0\times$ speedup over prior BQ methods while providing best accuracy.

AI 总结：研究发现现有关系基础模型处理高基数关系数据时存在上下文窗口失效问题，在合成金融数据集Animus上，经简单时间预聚合可显著提升模型预测客户收入的R²值。

链接：https://arxiv.org/abs/2609.00460

机构：Kunumi Institute（库纳米研究所）； Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）

作者：Denis Oliveira Correa, Francisco Galuppo Azevedo

英文摘要：Recent Relational Deep Learning architectures have been proposed as foundation models for multi-table relational data, yet they impose constrained neighborhood budgets that force row truncation when an entity has many related records. We introduce Animus, a synthetic financial dataset in which predicting customer income requires aggregating up to tens of thousands of transactions. On the raw representation, three recently proposed models (RT, Griffin, RelGT) achieve $R^2 \le 0.18$; a single, routine, temporal pre-aggregation step recovers $R^2$ up to $0.65$. This questions whether current relational foundation models are ready for high-cardinality real-world data.

AI 总结：本研究提出跨级别基准CopyShield，对比三种不同干预级别的大语言模型版权防御方法，在两类模型上揭示其合规性-实用性权衡，发现针对性非逐字抑制为待解决挑战。

链接：https://arxiv.org/abs/2609.01161

机构：Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学（MBZUAI））

作者：Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi, Martin Takac, Salem Lahlou, Nils Lukas

英文摘要：Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchmark comparing three representative defenses at distinct intervention levels: contrastive decoding (output), Direct Preference Optimization (behavioral), and activation intervention (representation). We evaluate CopyShield on two model families, LLaMA-3.1-8B and Mistral-7B-v0.3, using controlled memorization over five public-domain books and a shared protocol measuring literal leakage, calibrated non-literal leakage, utility, and degeneracy. Across these methods, intervention level is associated with distinct compliance-utility trade-offs. On LLaMA-3.1-8B, contrastive decoding remains near-degeneracy-free (0-2%) but reaches a literal-suppression floor at NV-Recall 0.192-0.203. DPO nearly eliminates literal leakage (0.263 to 0.002) but induces paraphrase-loop degeneracy in 58% of QA outputs, with no utility gain over the SFT baseline. Activation intervention attains the lowest non-literal flagging rate (1/200) by blocking 84% of non-literal queries before generation. Human evaluation confirms that DPO has low coherence, whereas activation lowers perceived copyright risk through broad refusal. On Mistral-7B-v0.3, the output- and representation-level patterns persist, while DPO degeneracy falls to 10-14%, showing that its severity is model-dependent. Together, CopyShield provides cross-level reference baselines and identifies targeted non-literal suppression as an open challenge. The code is available at this https URL.

AI 总结：该研究对比9种基础模型变体与两种电价预测基准，发现TabPFN模型统计表现最优但经济价值受策略影响，得出基础模型无法普遍替代特定市场模型的结论。

链接：https://arxiv.org/abs/2609.00089

机构：Wrocław University of Science and Technology（弗罗茨瓦夫科技大学）； Aarhus University（奥胡斯大学）

作者：Arkadiusz Lipiecki, Rafał Weron

英文摘要：Foundation models promise accurate forecasts with little or no task-specific training, but whether they can replace models designed specifically for electricity price forecasting remains unclear. We compare nine variants from five foundation model families, evaluated in zero-shot mode, with two state-of-the-art electricity price forecasting benchmarks in Germany, Poland, and Spain over 2021-2025. Their performance is assessed in terms of point and probabilistic forecasting accuracy, as well as economic value in battery energy storage arbitrage. Only the TabPFN models consistently and significantly outperform the benchmarks across all three markets and all statistical measures. However, this statistical dominance does not translate directly into economic dominance: TabPFN performs best under unlimited bids and riskier quantile-based strategies, whereas the Distributional Deep Neural Network benchmark is more profitable when risk tolerance is lower. Thus, foundation models cannot universally replace market-specific models, and their value depends on both model architecture and the decision problem.

AI 总结：该研究针对非定常分离翼型流动，提出VATO算子，通过两种机制结合涡量力图方法，在多轨迹CFD数据上显著降低流场及气动力误差，提升预测精度与泛化性。

链接：https://arxiv.org/abs/2609.00507

机构：King’s College London（伦敦国王学院）

作者：Xingxin Yang, Zhan Zhang, Yichen Li, Juan Li

英文摘要：Accurate prediction of unsteady separated flows is challenging because the aerodynamic loads depend on nonlinear separation and vortex-shedding dynamics. Although high-fidelity CFD resolves these mechanisms, its cost limits repeated use in design and control. Standard field-level surrogate training, however, does not distinguish the flow regions that contribute most strongly to the aerodynamic loads. We introduce VATO (Vortex-Force-Aware Transformer Operator), which couples the Vortex Force Map (VFM) method to a geometry-aware neural operator through two complementary mechanisms. VATO-S adds training-only supervision of the local VFM force-contribution field, with no increase in model size or inference cost. VATO-A uses VFM contribution and sensitivity fields to prioritise force-relevant source locations for residual cross attention. The methods are evaluated on unsteady CFD data for double-edged-plate aerofoils over 54 trajectories from nine geometries. Over lead times of 1-20~ms, VATO-S reduces velocity, pressure, and vorticity errors by 10.4\%, 1.0\%, and 15.6\%, respectively, while VATO-A achieves reductions of 15.8\%, 7.5\%, and 31.2\%. VATO-S gives the lowest VFM-derived drag error, whereas VATO-A gives the lowest pressure-derived lift and drag errors. Over lead times extending 50\% beyond the training range, VATO-A retains a 26.9\% reduction in vorticity error and larger improvements in all four force readouts, despite reduced gains in velocity and pressure. These results show that force-aware operator learning can improve both flow-field prediction and aerodynamic functional accuracy in unsteady separated flows.

AI 总结：DeSyR是一种结合PINN引导结构搜索与物理信息系数优化的解耦符号恢复框架，可从神经近似中恢复微分方程的紧凑显式解，在多类微分方程问题上实现了极低的优化误差与极高的收敛率。

链接：https://arxiv.org/abs/2609.00530

机构：Chengdu University of Information Technology（成都信息工程大学）； Sichuan University（四川大学）； Hong Kong Polytechnic University（香港理工大学）； Southwest Petroleum University（西南石油大学）

作者：Pancheng Niu, Jun Guo, Qiaolin He, Jingcai Guo, Yanchao Shi

英文摘要：Recovering compact explicit solutions from neural approximations is challenging when imperfect teacher data guide symbolic topology search and coefficient estimation. We present DeSyR, a decoupled symbolic recovery framework for differential equations. A physics-informed neural network guides repeated searches to construct candidate topologies with provisional constants. Once a topology is fixed, its coefficients are refined solely from the governing equation and prescribed constraints, followed by gated selection and verification. For linear fixed-topology parameterizations, we characterize teacher-error inheritance and show that finite-weight mixed data--physics fitting retains an $O(\beta^{-1})$ teacher-dependent contribution when the teacher error projects onto the model space. Under well-posedness, representability, zero-residual attainment, and discrete determinacy, physics-only refinement conditionally recovers exact coefficients; for nonlinear parameterizations, the corresponding guarantees are local. DeSyR is evaluated on 15 differential-equation problems across 18 configurations covering high-order, space--time, multidimensional, nonlinear, and coupled systems. A candidate-level audit yields a 99.23% convergence rate among free-parameter refits, while every selected refinement involving free coefficients converges. Configuration-level median refined relative $L_2$ errors are $2.31\times10^{-14}$ or lower. In same-topology comparisons, refinement reduces error by eight to fourteen orders of magnitude. These results show that an approximate neural teacher can guide topology discovery without imposing its error scale on final recovered coefficients, provided a target-capable topology is retained and physics-only refinement converges.

AI 总结：提出逆物理信息神经网络iPINN，结合Transformer编码器与多视图一致性损失，在BCARS相位 retrieval任务中，于公共基准和跨溶剂、焦点的零样本测试上均实现优于基线的鲁棒精度。

链接：https://arxiv.org/abs/2609.00883

机构：Friedrich Schiller University Jena（弗里德里希·席勒大学耶拿分校）； Leibniz Centre for Photonics in Infection Research (LPI)（莱布尼茨感染研究光子学中心）； Leibniz Institute of Photonic Technology（莱布尼茨光子技术研究所）； Leibniz Health Technologies（莱布尼茨健康技术中心）

作者：Ravi Teja Vulchi, Carl Messerschmidt, Mohammadsadegh Vafaeinezhad, Rajendhar Junjuri, Tobias Meyer-Zedler, Juergen Popp, Thomas Bocklitz

英文摘要：Phase retrieval in broadband coherent anti-Stokes Raman spectroscopy (BCARS) is an ill-posed inverse problem. The Raman-like signal is encoded in the imaginary part of the resonant susceptibility, which mixes coherently with a non-resonant background (NRB) that varies across acquisitions. We introduce an inverse physics-informed neural network (iPINN) that predicts Lorentzian peak parameters from raw BCARS spectra and reconstructs the resonant susceptibility through a differentiable analytical forward model. A transformer encoder assigns spectral features to 24 learnable peak slots, and a multi-view consistency loss enforces invariance across NRB pattern, NRB strength, and noise. Unlike direct spectral regression approaches, the method retains accuracy under varying acquisition conditions. On a public benchmark, iPINN achieves the lowest error among the tested baselines (MAE 0.016 vs. next-best 0.046). On 28 zero-shot test spectra acquired across seven solvents and four focal positions, accuracy is depth-invariant in five of seven solvents. These results show that inverse parametric prediction with a differentiable physical decoder supports robust phase retrieval across measurement conditions.

AI 总结：该研究针对边缘时间序列预测，通过无泄漏评估明确了预热预算、优化器学习率选择等因素对在线自适应收益的影响，提出仅验证的调试流程，为边缘场景的时间序列预测自适应提供了关键指导。

链接：https://arxiv.org/abs/2609.01126

机构：Keio University（庆应义塾大学）

作者：Takumi Fujimoto, Hiroaki Nishi

英文摘要：Online adaptation can help edge time-series forecasting under distribution drift, but its measured benefit is sensitive to evaluation choices. We study six public multivariate streams, including building-sensor and smart-meter data, under a leakage-free streaming protocol. We identify two additional sources of comparison bias. First, the warmup budget of the static baseline has a two-sided effect: insufficient warmup undertrains the baseline, whereas excessive warmup can degrade its pre-drift generalization. Across six dataset-backbone settings, the estimated adaptation benefit changes by 3.0 to 18.8 percentage points (pp) over the 1,000-20,000-step warmup range. Second, comparing SGD with momentum (SGD+m) and Adam at a shared default learning rate conflates optimizer quality with rate sensitivity. We select both the warmup budget and each optimizer's online rate using a held-out pre-drift validation slice without accessing test data. Under this validation-only procedure, Adam outperforms SGD+m in 310 of 360 evaluated cells, while 4 Adam cells remain below the static baseline. We further characterize accuracy against adaptation-state memory and A100-measured per-update latency for full, head-only, and calibration-based adaptation. In the evaluated PatchTST frontier settings, several parameter-efficient variants are nondominated on the adaptation-state-memory axis. Smart-meter analyses also show that reported gains depend on meter-selection rules. These findings support a validation-only commissioning procedure, while target-device latency and energy remain to be measured. Code, data, and all reported numbers: this https URL.

AI 总结：本研究将物理信息神经网络（PINNs）与探地雷达（GPR）数据预测结合，构建含CNN、SFCA、ConvLSTM及TFFA的专用模型，提升了GPR数据预测精度，助力民用基础设施劣化评估。

链接：https://arxiv.org/abs/2609.01417

作者：Mehrdad Shafiei Dizaji, Hoda Azari

英文摘要：The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction. This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws governing subsurface structures or in medical terms, human tissues the model effectively embeds the physics of electromagnetic wave propagation into its architecture. This ensures that predictions not only align with fundamental physical principles but also mirror the precision needed in medical diagnostics for detecting and monitoring tumors. The suggested deep learning structure comprises three components: a CNN, a spatial feature channel attention (SFCA) mechanism, and ConvLSTM, along with temporal feature frame attention (TFFA) modules. The attention mechanism computes channel attention and temporal attention weights using self-adaptation, thereby fine tuning the visual and temporal feature responses to extract the most pertinent and significant visual and temporal features. By integrating physics directly into the neural network, our model has shown enhanced accuracy in forecasting GPR data. This improvement is vital for conducting effective assessments of bridge deck conditions and other evaluations related to civil infrastructure. The use of Physics Informed Neural Networks (PINNs) has demonstrated the potential to transform the field of Non-Destructive Evaluation (NDE) by enhancing the precision of infrastructure deterioration predictions. Moreover, it offers a deeper insight into the fundamental mechanisms of deterioration, viewed through the prism of physics-based models.

AI 总结：该研究针对物理信息神经网络（PINNs）训练中存在的梯度更新不匹配（GUM）问题，提出梯度更新对齐（GUA）方法，可实现无冲突更新并提升性能，大幅降低相对$L_2$误差。

链接：https://arxiv.org/abs/2609.01558

机构：National University of Defense Technology（国防科技大学）； School of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机学院）

作者：Jing Xiao, Xinhai Chen, Qinglin Wang, Menghan Jia, Zhiquan Lai, Dongsheng Li, Jie Liu, Tiejun Li

英文摘要： Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before optimizer transformation. However, even when the constructed direction is conflict-free, this property may not be preserved after optimizer transformation. Let $a_t$ denote the direction constructed by gradient surgery, $u_t$ the optimizer proposal, and $\mathcal{C}_t$ the conflict-free cone induced by the loss-specific gradients. We show that modern optimizers can transform $a_t$ through mechanisms such as historical state, adaptive scaling, preconditioning, or decoupled weight decay, so $a_t \in \mathcal{C}_t$ does not generally imply $u_t \in \mathcal{C}_t$. We refer to this optimizer-induced discrepancy in conflict-freeness between $a_t$ and $u_t$ as Gradient-Update Mismatch (GUM). Accordingly, we propose Gradient-Update Alignment (GUA), which projects $u_t$ onto $\mathcal{C}_t$ to obtain the aligned update $p_t$ and applies $p_t$ to the parameters. When the optimizer maintains internal state, GUA further adjusts this state toward targets reconstructed from the applied update. We conduct extensive experiments and find that GUM is widespread across momentum, adaptive, and curvature-based optimizers, with conflict rates reaching up to 86.3%. Across all PINN settings, GUA achieves conflict-free applied updates and consistently improves various gradient surgery methods, reducing the relative $L_2$ error by up to 98.2% in individual settings. Data and code are available at this https URL.

AI 总结：该研究针对多任务图预训练中提示空间与结构特征对齐差的问题，提出双先验提示初始化方案TPGC，在6个主流基准的少样本设置下性能优于现有方法。

链接：https://arxiv.org/abs/2609.00047

机构：School of Computer Science and Cyber Engineering, Guangzhou University（广州大学计算机科学与网络工程学院）； Hunan University of Technology and Business（湖南工商大学）

作者：Zhiyang Qiu, Yangtao Wang, Xiaocui Li, Yanzhao Xie, Siyuan Chen, Wensheng Zhang

英文摘要：Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing multi-task graph pre-training frameworks generally use randomly initialized prompts, leading to poor alignment between the prompt space, pretext objectives and graph structural characteristics. This greatly weakens the task relevance, structural awareness and transferability of prompt representations. To address this challenge, we propose TPGC, a dual-prior prompt initialization solution that explicitly models the synergy between task prior and structural prior. Specifically, the Task-Prior Injection Module first conducts a short homologous multi-task pre-training on an auxiliary graph, enabling prompt initialization to inherit optimization preferences associated with multiple pretext tasks. Built on the task-aware representations, the Structure-Prior Injection Module further extracts transferable global structural context from the auxiliary graph, converting it into layer-wise prompt vectors by aggregating structurally informative node embeddings. Extensive experiments on 6 mainstream benchmarks covering node and graph classification show that TPGC achieves consistently better performance under few-shot settings than state-of-the-art baselines, with fewer downstream tunable parameters and lower runtime. The code is available at this https URL

AI 总结：本文研究基于AOC-偏序集的关系概念分析（RCA）的收敛性问题，说明其收敛性丧失的原因，确定可保证收敛的条件，提出保留AOC-偏序集结构的收敛变体。

链接：https://arxiv.org/abs/2609.00054

机构：Univ. de Strasbourg（斯特拉斯堡大学）； ENGEES（国立高等环境、农业与工程学校）； CNRS（法国国家科学研究中心）； ICube（立方体实验室）； LIRMM（蒙彼利埃计算机科学、机器人学与微电子实验室）； Univ. Montpellier（蒙彼利埃大学）

作者：Xavier Dolques, Agnès Braud, Alain Gutierrez, Marianne Huchard, Florence Le Ber

英文摘要：Formal Concept Analysis (FCA) is an approach for conceptual classification building and rule discovery from a binary table describing a set of objects by a set of attributes. Extensions have been proposed to deal with non-binary and more complex data, such as Relational Concept Analysis (RCA) for multi-relational data. RCA aims to highlight groups of objects characterized by their relationships with other groups of objects. The richer and more complex nature of the underlying data allows RCA to produce richer results than FCA, at the expense of higher computational and interpretive complexity. The most commonly used conceptual classification structure in FCA is the concept lattice. However, in many applications, concept lattice substructures, such as AOC-posets, are preferred over the full lattice, either to mitigate combinatorial blow-up or to focus on the most informative parts of the structure. Indeed, in an AOC-poset, only concepts introducing an object or an attribute are represented, which makes AOC-posets smaller and easier to compute and use than concept lattices. Although RCA was originally defined on concept lattices, it can also be instantiated on AOC-posets. RCA is iterative and its convergence is guaranteed in the lattice-based setting, but this guarantee is lost when using AOC-posets. In this paper, we investigate this loss of convergence in detail. We show why convergence is no longer guaranteed in the general case, identify conditions under which it can still be ensured, and discuss how a dataset can be transformed to recover convergence. We also propose a convergent variant of the process, which preserves the AOC-poset structure: relational attributes, once created, are never removed, which guarantees convergence at the price of attributes that may refer to concepts absent from the final structures.

AI 总结：ReNFT 是一种从扩散生成器内部修复奖励后训练模式崩溃的方法，在保留 NFT 高奖励的同时显著提升了 DreamSim-Div，为外部干预提供互补方案。

链接：https://arxiv.org/abs/2609.00061

机构：Southern University of Science and Technology（南方科技大学）； Tencent Youtu Lab（腾讯优图实验室）

作者：Yuchen Bao, Chao Wen, Haowei Wang, Ruoxin Chen, Donghao Luo, Jiahui Zhan, Wenjian Huang, Shen Chen, Yiting Wang, Taiping Yao, Chengjie Wang, Shouhong Ding, Jianguo Zhang

英文摘要： Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing methods for mitigating collapse rely on external signals or interfaces, augmenting the reward with perceptual objectives, adjusting reference regularization, or modifying the text encoder, but none repairs an adapter that has already collapsed while preserving the acquired reward. We observe that online post-training primarily reallocates probability mass over capabilities inherited from pretraining rather than learning new visual content. Collapse is therefore suppression, not deletion, and can be reversed from within the generator. We propose ReNFT, which repairs a high-reward, low-diversity adapter through internal probability-mass recalibration. Unconditional probes first prioritize "anti-hub" prompts where the prompt-independent bias is easiest to expose. Two policy-dominated mixed routes then generate matched counterfactual proposals from the same prompt and initial noise, one probing the frozen base direction for suppressed alternatives and the other exposing the post-trained unconditional tendency. Reward ranking with an adaptive flipping guard assigns pull and push roles, and a joint-and-paired NFT update realizes the repair. On PickScore and GenEval, ReNFT retains 98.9% and 99.0% of NFT's reward while improving DreamSim-Div by 58.8% and 55.0%, respectively, offering a complementary alternative to external interventions.

AI 总结：本文针对Llama-2-7B，发现微调下注意力层级的ICL代理与实际行为分离，提出ICS指标，验证其需经行为差距验证才适合作为训练目标。

链接：https://arxiv.org/abs/2609.00064

机构：Hubei University（湖北大学）

作者：Jinyuan Zhang, Peng He, He Hu, Yin Yuan, ShengShuo Jiao

英文摘要：In-context learning (ICL) lets large language models adapt to new tasks from demonstrations, and fine-tuning can erode this behaviour. Many preservation diagnostics inspect attention: if attention changes when demonstrations change, the model is treated as context-sensitive. This paper asks how far that proxy can be trusted once it is optimised. We formalise \emph{In-Context Sensitivity} (ICS), the average row distance between last-token attention on matched and mismatched demonstration prefixes, and pair it with \emph{ICL-GAP}, the behavioural accuracy gap between the same prefixes. In a controlled four-arm ablation on Llama-2-7B, an ICS-maximising regulariser ($\armKL$) drives ICS to $1.413$, within $0.5\%$ of its geometric ceiling. The behavioural readout tells a different story: ICL-GAP stays near zero and MMLU accuracy moves from $0.371$ to $0.279$, a Goodhart dissociation of the bounded attention proxy. Endpoint statistics locate the mechanism: attention grows sharp and near-disjoint across prefixes yet routes to formatting and demonstration-body tokens rather than labels. A random-label protocol confirms that the behavioural probe family retains dynamic range at the same checkpoints. In a constructive sweep, behaviour gating partially mitigates the effect, while objectives anchored to pretrained computation hold the high-MMLU, moderate-ICS region that divergence maximisers leave. The main lesson is diagnostic: attention-level ICL proxies earn their place as training targets only after validation against behavioural gaps.

AI 总结：本文针对含聚类结构向量的随机概率计算问题，提出线性时间的递归公式计算NML模型归一化常数，将原多项式时间复杂度优化为线性，为MDL原理下的聚类相关任务提供了高效理论支撑。

链接：https://arxiv.org/abs/2609.00084

机构：Medicel Oy（麦迪赛尔公司）； Institute of Signal Processing, Tampere University of Technology（坦佩雷理工大学信号处理研究所）

作者：Daniel Nicorici, Olli Yli-Harja, Jaakko Astola

英文摘要：This paper studies the problem of computing the stochastic probability (shortest code length) of the encoded vectors containing cluster structure using Normalized Maximum Likelihood (NML) model. This is of great theoretical and practical importance in data clustering based on Minimum Description Length (MDL) principle, such as for estimating the best number of clusters and best cluster structure for the data. Straightforward computation of the shortest code length of the vector containing cluster structure based on the NML model requires polynomial time with respect to the size of the vector and number of clusters. We show that this is a tractable problem by introducing a recursion formula for the efficient computation of normalizing constant from the NML model. The time complexity of the new formula is linear opposed to previous polynomial time with respect to the size of the vector and number of clusters.

AI 总结：本研究将特征重要性方法（FIMs）嵌入证据权重（WoE）的假设检验框架，提出可评估FIMs对齐性与稳定性的新方法，并通过LIME、SHAP的实证分析验证了策略的适用性。

链接：https://arxiv.org/abs/2609.00090

机构：SMARTEST Research Center（SMARTEST研究中心）； eCampus University（eCampus大学）； Barcelona Supercomputing Center（巴塞罗那超级计算中心）； University of Florence（佛罗伦萨大学）； University of Pisa（比萨大学）

作者：Eddie Conti, Claudio Daka, Álvaro Parafita, Antonio L. Alfeo, Axel Brando, Mario G.C.A. Cimino

英文摘要：Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited insight into the underlying reasoning process. In this work, we introduce a novel perspective by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE). We quantify how strongly the observed evidence supports any given hypothesis on feature importance. The reference hypothesis can stem from domain knowledge, ground truth, or be derived from the FIM itself. This formulation enables a principled evaluation of FIMs, capturing both their alignment with prior knowledge and their variability. We further provide theoretical results linking WoE to attribution variance. Empirical results shows the applicability and flexibility of our strategy analyzing LIME and SHAP explanations in settings with different reference hypotheses. Overall, our framework offers a complementary tool for assessing FIMs through a contrastive, evidence-based lens.

AI 总结：针对不平衡时间序列分类中少数类特征空间局部可靠性不足的问题，提出LRG模块，通过增强特征提升分类性能，验证其在多类表示及高风险区域的有效性。

链接： https://arxiv.org/abs/2609.00093

作者：Chuanhang Qiu, Yanran Xu, Yue Wang, Anthony Bagnall

英文摘要：Imbalanced time series classification is often addressed by changing the training distribution, objective, logits, or final threshold. These interventions address important biases, yet leave a representation-level question unmeasured: after minority support is reduced, does a learned feature space remain locally reliable around minority regions? We identify a training-local geometry failure: under imbalance, minority cases can lie in sparse, rest-dominated, or mixed feature-space neighborhoods, even when the representation retains useful global class structure. To diagnose and repair this failure, we propose Local Reference Geometry (LRG), a lightweight post-hoc feature augmentation module applied between a fixed feature extractor and the classifier head. Using training features only, LRG measures local exposure and class-mixture risk, then augments each fixed feature with a standardized signed displacement from nearby training geometry and an LDA-projected residual summary. On controlled UCR/Bake Off Redux imbalance benchmarks, paired raw-versus-LRG comparisons show gains for learned, pretrained, and fixed representations, including when LRG is combined with training-level interventions and post-encoder classifier corrections. Ablations show that the gain comes from the signed local residual appended to the original feature, rather than from generic prototype distances, affinity features, scalar statistics, or VLAD-style codes. Further analyses support the proposed local-geometry failure hypothesis: minority neighborhoods become increasingly rest-exposed under imbalance, training-local risk identifies error-prone regions, and LRG gains concentrate in those high-risk regions.

AI 总结：本研究提出领域适配的检索增强生成框架，结合Reason Map命题图框架，实现腐蚀机理的可靠推理，相关架构可泛化至其他工程领域。

链接：https://arxiv.org/abs/2609.00099

作者：Bharath M N, R K Singh Raman, Alankar Alankar

英文摘要：Corrosion accounts for approximately 4% of global GDP, and reliable prediction is essential for timely mitigation. Machine learning effectively predicts corrosion rates from composition, microstructure, and environmental variables, but cannot explain the underlying mechanisms. A reliable approach in safety-critical materials engineering requires not only accurate retrieval but also mechanistically defensible reasoning, a capability that existing factuality metrics cannot assess. This work presents a domain-adapted retrieval-augmented generation framework for corrosion knowledge synthesis, demonstrated on magnesium alloy corrosion. Three open-weight language models (Llama-3.1-8B, Qwen-2.5-7B, Mistral-7B) are fine-tuned on 3,309 expert-verified question-answer pairs from 840 peer-reviewed papers and integrated with a hybrid dense-lexical retrieval pipeline. Retrieval augmentation produces Token F1 gains of 143-194%, with system faithfulness of 0.964 and context recall of 0.988. Blind external validation on newly published literature and in-house electrochemical data confirms trend-level generalisation. Reason Map, a proposition-graph framework, is further introduced; it independently constructs directed evidence graphs from generated answers and retrieved literature, enabling systematic detection of causal direction inversions and unsupported inferential leaps that flat factuality metrics cannot expose. The modular architecture can be applied across domains, offering a generalizable blueprint for trustworthy AI-assisted knowledge synthesis to circumvent corrosion, which can also be applied to other engineering domains.

AI 总结：该研究提出“本质有缺陷，进化臻完美”机制，通过突变模型系数使模型群对冲环境非平稳性，可减少遗憾，在合成任务中约80%环境变化下生成最优模型，为AI系统提供新设计原则。

链接：https://arxiv.org/abs/2609.00129

机构：Allora Foundation（阿罗拉基金会）

作者：J. M. Diederik Kruijssen (Allora Foundation)

英文摘要：The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near-universal feature of real-world problems, which often change unpredictably. Biological evolution has achieved intelligence by overcoming this obstacle through natural selection acting on heritable variation. AI/ML techniques have long incorporated forms of natural selection, but it has been challenging to maintain model diversity as optimization naturally drives convergence. Here we show that a swarm of AI/ML models subjected to deliberate mutations of their model coefficients away from optimality can reliably and sustainably improve performance in changing environments by acting as a statistical hedge against non-stationarity. We call this mechanism 'Flawed in Nature, Perfect through Evolution', reflecting that the collective performance gain goes at the expense of individual performance. We prove via four theorems that the resulting regret reduction is guaranteed under general conditions, establishing the Flawed-in-Nature mechanism as a generalizable design principle for AI/ML systems. We validate these results on synthetic linear regression tasks, demonstrating that the mutated swarm delivers the best model in $\sim80\%$ of environment changes and that inference synthesis successfully translates this individual advantage into a collective one. The mechanism proves to be most effective when the mutation drift rate matches the drift rate of the environment. We outline a simple, adaptive controller that enables practical applications by tuning the mutation drift rate to match the unknown drift rate of the environment. The close analogy of the Flawed-in-Nature mechanism to biological evolution suggests it may have been a critical missing ingredient for the organic discovery of AI forms that more closely mimic biological intelligence.

AI 总结：该研究针对智能体性能受模型权重与 harness 代码单独优化瓶颈的问题，提出 WHALE 交替优化方案，结合在线拒绝采样微调与 Meta-Harness，在多领域 Qwen 智能体上较基线方法提升了准确率与 rollout 效率。

链接：https://arxiv.org/abs/2609.00196

机构：KRAFTON（克拉夫顿公司）； KAIST（韩国科学技术院）； Stanford University（斯坦福大学）

作者：Haechan Kim, Yoonho Lee, Gisang Lee, Chelsea Finn, Kangwook Lee

英文摘要：Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model. We instantiate these two phases with online rejection-sampling fine-tuning and Meta-Harness, respectively. When to switch is a key design choice: to separate real improvements from noise without over-optimizing against a changing counterpart, WHALE uses either fixed phase durations or an adaptive patience rule over training signals. Using Qwen3.5-2B/4B agents across three domains (search question answering, mathematical reasoning, and chess puzzles), WHALE outperforms weight-only, harness-only, and Fast-Slow Training by 4.15-24.38 percentage points in best mean@8 accuracy. Either component can be the bottleneck: harness search matches peak weight-only accuracy with far fewer rollouts in SearchQA, but improves math accuracy only after a weight update. Small interleaved updates also outperform stagewise weight-then-harness optimization in accuracy and rollout cost. The code is available at this https URL.

AI 总结：QTEA是一种亚2比特的三值后训练量化框架，通过按列优化、半结构化稀疏性和误差衰减提升三值LLM的精度与推理速度，在Qwen3-14B和Llama3-8B上均取得显著性能提升。

链接：https://arxiv.org/abs/2609.00224

机构：University of Notre Dame（圣母大学）

作者：Yipin Guo, Arun M George, Jie Fu, Tareq Mahmoud, Sixue Xing, Siddharth Joshi

英文摘要：Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2 bits. Many leverage unstructured sparsity to mitigate this loss, but at the cost of regularity and GPU-friendly execution. We present QTEA, a sub-2-bit PTQ framework that quantizes weights into ternary values and uses salient weights as residual error compensators. To maintain hardware efficiency, residuals are assigned to selected columns with semi-structured \(1{:}4\) sparsity within the salient columns. We further add column-wise rescale refinement to GPTQ-style column-by-column quantization, alternately updating per-column scales and ternary assignments to reduce reconstruction error. We also identify order-dependent error propagation in GPTQ and introduce error decay to attenuate late-stage error accumulation. On Qwen3-14B, QTEA compresses all weights to an effective 1.7 bits per weight while improving average accuracy over the strongest ternary PTQ baseline by 16.7\%. It also achieves 1.40\(\times\) and 2.61\(\times\) lower perplexity on WikiText and C4 respectively. This trend holds on Llama3-8B, where QTEA obtains a 6.6\% accuracy gain and 1.34\(\times\)/1.95\(\times\) lower perplexity on the same datasets. Finally, we develop a lookup-table based kernel that achieves 7.2\(\times\) faster per-token generation over an FP16 baseline. Code is available at this https URL.

AI 总结：该研究针对四个美国大都市区，以人口普查区块组为单位评估零样本LLM的社区层面流动性预测能力，发现其准确率低于监督基线，且存在受保护群体预测因子不对称处理的偏差，提出需审计其结构对齐性与潜在偏差。

链接：https://arxiv.org/abs/2609.00345

机构：University of Maryland（马里兰大学）

作者：Saad Mohammad Abrar, Eesha Kurella, Arnav Dadarya, Naman Awasthi, Kazi Tasnim Zinat, Vanessa Frias-Martinez

英文摘要：Human mobility is central to urban planning, transportation, public health, and emergency response, yet fine-grained trajectory data are often proprietary, restricted, and privacy-sensitive. Large language models (LLMs) offer a potential alternative by generating plausible mobility traces and predicting individual movement, but their ability to infer aggregate neighborhood-level mobility remains unclear. We evaluate zero-shot LLMs on Census Block Group-level mobility prediction across four U.S. metropolitan areas using anonymized Cuebiq data to construct point-level, trajectory-level, and temporal mobility outcomes, paired with sociodemographic and built-environment predictors. We compare LLM predictions with supervised baselines and introduce a directional alignment analysis to test whether LLM-implied predictor effects agree with empirical OLS and Jonckheere-Terpstra trends. Supervised models achieve 0.580 average accuracy, compared with 0.435 for the best LLM, with spatial extent outcomes showing the strongest predictability but also the largest LLM-baseline gaps. Directional analysis shows that LLMs often rely on coarse, stable predictor-level priors that remain similar across outcomes and cities, including asymmetric treatment of protected-group predictors. Overall, LLMs can partially recover aggregate mobility patterns from urban context, but their predictions should not be treated as structurally grounded without auditing empirical alignment and potential bias.

AI 总结：本文研究量化GEMM内核一致性检查套件的检测极限，发现基于1个间距容忍度的套件无法检测多数尾声故障，将权重尺度重新量化为二的幂次可提升CUTLASS与Triton的一致性及生成序列的字节级匹配度。

链接：https://arxiv.org/abs/2609.00363

机构：Krixvon（克里克斯冯）

作者：Teng-Ruei Chen

英文摘要： Conformance suites for quantized GEMM kernels ask whether two implementations agree within a tolerance. We measure what such a suite can detect. Injecting nine faults into a reference INT8 pipeline over 8,232 layer--fault--regime cells of Qwen3-1.7B, we find that every one of five epilogue faults -- scale precision, double rounding, multiplication order, output truncation, fused ordering -- moves the output by at most a single bfloat16 spacing, and by exactly one whenever it moves it at all, across 5,880 cells. A tolerance of one spacing is therefore blind to the entire class by construction: four of the five faults are detected by no check in the suite, and the fifth only under power-of-two scales. Faults that violate the accumulator's exactness preconditions, or that break operand sharing, are detected without exception, and a null fault never fires. What a tolerance-based suite of this shape establishes is therefore narrower than interchangeability: that the preconditions hold, that operands are shared, and that differences stay within one spacing. The power-of-two constraint that exposes the one detected fault is also deployable. Requantizing every weight scale to its nearest power of two makes CUTLASS and Triton agree bitwise at every linear layer (196/196 and 252/252, against 8/196 and 10/252 under the checkpoints' own scales) and yields byte-identical generated token sequences at 1.7B, 8B and 14B (8/8 prompts, against 0/8 at all three). Observed perplexity point estimates are +0.32%, -0.28% and +0.48%; the 90% intervals cover zero at the two smaller sizes but not at 14B, reaching +0.71% and +0.76%. A previously reported +157% perplexity for this intervention was an artifact of a probe that rewrote scales without requantizing the weights; separating the effects attributes 99.8% of it to the resulting weight--scale mismatch rather than to the power-of-two constraint itself.

AI 总结：该研究提出反事实脆弱性证书（CFC），用于审计表格决策系统中高置信度预测的脆弱性，CFC-FDS在识别脆弱高置信度案例上表现优于现有方法，为模型可靠性评估提供了新框架。

链接：https://arxiv.org/abs/2609.00366

机构：Macquarie University（麦考瑞大学）

作者：Filippo Cenacchi, Longbing Cao, Runze Yang

英文摘要：High test accuracy and good aggregate calibration do not show whether an individual prediction is structurally supported by its evidence. In tabular decision systems, failures often occur when a feature family becomes unavailable, delayed, noisy, stale, or low-trust while the model remains highly confident. Existing calibration, uncertainty, selective-prediction, explanation, and perturbation methods provide scalar scores or attribution maps, but not a recomputable audit object answering: under a declared evidence-failure protocol, what trajectory makes this prediction lose support? We introduce Counterfactual Fragility Certificates (CFC), a model-agnostic protocol-level audit certificate-not a formal robustness certificate-that maps each prediction into an ordered evidence-failure trajectory summarized by greedy flip budget, normalized margin-collapse area, degradation thresholds, and fragility dominance score. Across seven tabular benchmarks and strong linear, tree-based, boosting, and neural baselines, CFC-FDS identifies independently brittle high-confidence cases with 0.915 AUROC, improving over the strongest non-certificate score by +0.405. The advantage persists across perturbation, permutation-importance, group-SHAP, baseline-choice, seed-variance, budgeted-review, and naturalistic field-unavailability checks. Under a 20% review budget, CFC-FDS captures 88.9% of brittle high-confidence cases, compared with 31.8-37.4% for confidence and energy scores. We also evaluate fragility-aware regularization and brittleness-aware temperature correction as secondary uses. CFC provides a concrete reliability framework for exposing high-confidence brittleness missed by ordinary score-centric evaluation.

AI 总结：该研究提出融合ELM与TPB的多分支框架，结合Transformer语义与心理线索，检测健康虚假信息并引入CPS辅助传播风险推理，在三个基准数据集上表现优异，提升了检测性能。

链接：https://arxiv.org/abs/2609.00403

机构：Manchester Metropolitan University（曼彻斯特城市大学）

作者：Mkululi Sikosana, Sean Maudsley-Barton, Oluwaseun Ajao

英文摘要：This paper presents a multi-branch fusion framework for detecting and characterising the propagation of health misinformation in online social networks (OSNs). Grounded in the Elaboration Likelihood Model (ELM) and the Theory of Planned Behaviour (TPB), the model fuses transformer-based semantics with rhetorical cues, stance representations, and psychologically motivated proxies in a unified multi-task architecture. In addition to binary classification, we introduce the Cognitive Propagation Score (CPS), an interpretable post-hoc auxiliary score computed from psychologically motivated, text-derived cues capturing argument complexity, emotional intensity, and content-derived virality potential, to support diffusion-risk reasoning when engagement ground truth is incomplete or unavailable. Experiments on three benchmark datasets, Constraint, COVID--19\_FNIR, and Monkeypox, show strong classification performance, achieving ROC--AUC up to 0.9999 on COVID--19\_FNIR, while propagation-oriented ranking achieves near-perfect agreement when engagement-derived supervision is available (Monkeypox, Spearman's $\rho = 0.9952$) and similarly high ranking alignment under proxy-based supervision on COVID--19\_FNIR ($\rho = 0.9954$). Compared with representative literature baselines, the fusion model improves detection on Constraint and COVID--19\_FNIR, while Monkeypox remains more challenging, reflecting domain- and signal-specific differences. Ablation analysis further indicates that psychological and rhetorical branches provide complementary gains beyond semantic embeddings. Overall, the framework bridges cognitive theory and neural modelling to improve transparency and to support scalable misinformation monitoring, with future work required to validate CPS against human-centred diffusion judgements.

AI 总结：本研究针对线性循环神经网络，推导了相关输入下的学习动力学，揭示了时间相关性对记忆的影响，解释了相关数据使循环网络成为变化检测器的原因。

链接：https://arxiv.org/abs/2609.00420

机构： University of Buea（布埃亚大学）； minoHealth AI Labs（minoHealth人工智能实验室）

作者：Arnol Manuel Fokam, Fasseu Sieyondji Akpevwoghene, Edem Fiifi Dawson

英文摘要：The linear recurrent neural network (LRNN) is a simple model for studying how much memory a network builds up as it trains. For uncorrelated inputs, earlier work found that training itself settles the network between keeping the past and reacting only to the present. Real sequences are correlated, and we solve the learning dynamics exactly for correlated inputs. In the solution, keeping the past carries a cost. The whole effect of correlation lands on that cost. This cost reduces to the earlier one when inputs are uncorrelated and grows once they are positively correlated. Three findings follow. (1) Correlation reshapes the course of learning, not only its end. Memory builds, overshoots, and is partly removed, and the settled network keeps less of the past. (2) Memory switches off at a threshold set by one number, how much each input resembles the one just before it. Neither sequence length nor longer-range correlation moves this threshold. Memory is worth keeping only when the task needs the previous input more than the current input already supplies it through correlation with the past. (3) The best network changes too. Zero error demands a feedthrough, a path that passes the current input straight to the network's output and remembers nothing, and training builds it unprompted when given one spare hidden dimension. Our work turns one property of the input into a prediction of whether a network learns memory and explains why correlated data turns recurrent networks into change detectors.

AI 总结：该研究探究用小型量子神经网络替代基于注意力的路由模型的参数密集型模块，发现编码器前馈替换可减少56.6%参数，是可行的混合模块压缩策略，未体现量子优势。

链接：https://arxiv.org/abs/2609.00489

机构：Instituto de Pesquisas Eldorado（Eldorado研究所）； Universidade Federal de Santa Catarina（圣卡塔琳娜联邦大学）； Universidade Federal do Rio Grande do Sul（南里奥格兰德联邦大学）

作者：Marcus Rolf Peter Ritt, Alexsandro Santos da Rosa Júnior, Marcos Vinicius Reballo, Cesar Augusto do Amaral, Fernando Augusto Caletti de Barros

英文摘要：This work studies hybrid quantum-classical neural networks for learning routing heuristics. Specifically, this paper asks whether small quantum neural networks can replace parameter-heavy modules inside a competitive attention-based routing model while maintaining solution quality. For the capacitated vehicle routing problem, encoder feed-forward replacement emerges as the most promising design: it reduces the number of model parameters by 56.6% while keeping the hybrid model close to the classical neural baseline at small and medium instance sizes, although the gap grows for larger instances. This work also compares to classical routing algorithms, which remain highly competitive and often superior on the fixed Euclidean test sets. Our results therefore do not indicate quantum advantage or solver dominance, but identify encoder feed-forward replacement as a viable hybrid-module compression strategy for neural combinatorial optimization.

AI 总结：该研究提出功能感知掩码算法，通过对齐特定功能先验的掩码位置塑造抗体表征空间，提升了结构、CDR等相关任务性能，还开发了混合掩码策略平衡多维度目标。

链接：https://arxiv.org/abs/2609.00518

机构：School of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电气与计算机工程学院）； School of Computer Science, Georgia Institute of Technology（佐治亚理工学院计算机科学学院）

作者：Ayan Goel, Thomas A. Walton, Amirali Aghazadeh

英文摘要：Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

AI 总结：本文针对现有编码计算未利用数据内在结构的问题，提出流形感知通用编码策略，在神经网络推理和高维多项式评估实验中，该策略可显著降低抗掉队节点场景下的均方恢复误差。

链接：https://arxiv.org/abs/2609.00552

机构：University of Minnesota, Twin Cities（明尼苏达大学双城分校）

作者：Parsa Moradi, Mohammad Ali Maddah-Ali

英文摘要： Existing coded-computing designs do not explicitly exploit the intrinsic structure of the input data. In communication systems, statistical structure and redundancy are often removed through source coding (or compression) before channel coding is applied. This principle, however, does not transfer directly to coded computation. In many computational tasks, particularly in machine learning, the structure of the data is precisely what the computation seeks to exploit to infer outputs or learn meaningful patterns. Consequently, coded-computing schemes should preserve and leverage this structure in their code design, rather than ignoring or eliminating it through source coding. This observation motivates a different perspective on code construction. In many channel-coding schemes, such as Reed-Solomon codes, coded symbols are generated by evaluating a low-dimensional algebraic representation at selected points. In contrast, many high-dimensional datasets naturally concentrate near low-dimensional manifolds. In this paper, we exploit this intrinsic geometry by designing coded samples that follow the natural manifold of the data, rather than imposing an artificial low-dimensional structure unrelated to the data distribution. Inspired by graph-based manifold learning, we propose a manifold-aware encoding strategy for general coded computing (GCC). Experiments on neural network inference and high-dimensional polynomial evaluation demonstrate that the proposed strategy consistently and significantly reduces the mean squared recovery error under straggling compared with standard GCC.

AI 总结：本研究提出EEG-VID预训练框架，通过指数移动平均目标编码器与弱任务引导实现EEG解码，在多数据集及场景任务中提升准确率，为EEG解码与辅助目标选择提供可迁移预训练策略。

链接：https://arxiv.org/abs/2609.00566

机构：School of Information and Control Engineering, China University of Mining and Technology（中国矿业大学信息与控制工程学院）； School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）； Shanghai Innovation Institute（上海创新研究院）

作者：Guanzhong Sun, Junyi Ma, Yuxuan Wu, Yanzi Miao

英文摘要：We propose EEG-VID, a task-guided latent predictive pretraining framework for EEG decoding under session and subject shifts. EEG-VID predicts future latent EEG states from recent history using an exponential-moving-average target encoder and weak task guidance, followed by supervised fine-tuning. Across VIG-48 and BCI Competition IV-2a/IV-2b, Stage 1 improves mean accuracy in 41 of 42 matched backbone-dataset-protocol comparisons, including all 12 leave-one-subject-out settings, with a maximum gain of 16.22 percentage points. On the 48-region cross-day VIG-48 task, EEG-VID achieves 6.52% Top-1 and 30.50% Top-5 accuracy. In a separate six-participant offline robot-scene study, candidate-constrained target selection reaches 40.24% versus a 25% chance level after subject-specific calibration. These results support task-guided latent prediction as a transferable pretraining strategy for EEG decoding and scene-constrained assistive target selection.

AI 总结：针对现有大语言模型行为控制方法易受局部扰动影响的问题，提出基于拓扑数据分析的Topological Steering框架，通过激活空间的拓扑表示实现更鲁棒的模型行为控制，且在多模型家族及规模上均有效。

链接：https://arxiv.org/abs/2609.00597

机构：National University of Singapore (NUS)（新加坡国立大学）

作者：Benoît Guérand, Tan Minh Nguyen

英文摘要：With the rapid rise of large language models (LLMs), controlling undesirable model behaviors has become increasingly important. Existing behavioral control methods typically intervene directly in activation or feature space, but such approaches can be sensitive to outliers, distributional shifts, noise, and other local perturbations. Motivated by Topological Data Analysis (TDA), which captures global rather than purely local structure, we propose Topological Steering, a new framework for steering LLM behavior through the topological representation of activation spaces. Using persistence diagrams, our method connects activation-based steering with TDA and enables more robust behavioral control. We show that Topological Steering consistently modifies LLM behavior across multiple model families and model sizes.

AI 总结：针对多核k均值易受噪声边界样本影响、粒球与融合核几何不匹配的问题，提出DK-GBMKKM，通过核空间动态粒球交替优化提升聚类性能，在12个公开数据集上表现出色且代码开源。

链接：https://arxiv.org/abs/2609.00647

机构：Chongqing University of Posts and Telecommunications（重庆邮电大学）； Chongqing Open University（重庆开放大学）

作者：Xiaoyu Lian, Yuchao Zhang, Shuyin Xia, Siqi Zhong, Xuzhao Xiang

英文摘要：Multiple kernel $k$-means integrates complementary nonlinear similarities by learning a combination of base kernels. Its pointwise optimization, however, is sensitive to noisy and boundary samples and repeatedly operates on sample-scale kernel matrices. Granular-ball representations organize local sample groups into mesoscopic units, but granular balls generated once in the input space may be inconsistent with the fused-kernel geometry that evolves during multiple kernel learning. We propose dynamic kernel-space granular-ball multiple kernel $k$-means (DK-GBMKKM). The method generates granular balls in the current fused kernel space and alternates kernel-weight learning with granular-ball membership updates, allowing the representation to adapt to changes in the fused-kernel geometry. A sample-size-weighted granular-ball kernel is further constructed to preserve the contributions of balls of different sizes, and its positive semidefiniteness and related equivalence properties are established. Experiments on 12 public datasets demonstrate the strong overall clustering performance of DK-GBMKKM. The code has been open-sourced for reproducibility: this https URL.

AI 总结：该研究将脑电基础模型选择转化为实例级算法选择问题，提出EEG-AS框架，通过行为重构高效从七个脑电基础模型中选优，大幅缩小了最优单求解器与神谕上界的差距。

链接：https://arxiv.org/abs/2609.00653

机构：Duke Kunshan University（昆山杜克大学）； Ankara University（安卡拉大学）

作者：Yunzhen Zhang, Ruoxi Piao, Hasan Onur Keles, Mustafa Misir

英文摘要：Electroencephalography (EEG) is a non-invasive technique for measuring neural activity and has been widely used in neuroscience applications. Recent advances in EEG foundation models have enabled strong performance across diverse neural decoding tasks. However, no single foundation model consistently performs best across datasets or individual EEG instances, while instance-level model selection remains largely unexplored. To address this limitation, we formulate EEG foundation model selection as an instance-level Algorithm Selection (AS) problem. We propose \textbf{EEG-AS}, an instance-level algorithm selection framework that characterizes each EEG instance using inference-available latent EEG embeddings, handcrafted neurophysiological features, and an anchor foundation model. During training, EEG-AS learns to reconstruct unavailable foundation-model behaviors from privileged prediction tokens conditioned on an anchor foundation model, while during inference it estimates these behaviors without executing the entire model portfolio, enabling efficient selection from seven EEG foundation models. Experiments on seven public EEG benchmarks demonstrate that EEG-AS substantially narrows the gap between the Single Best Solver (SBS) and the oracle upper bound for each instance. These results highlight the effectiveness of instance-level AS for adaptive deployment of EEG foundation models.

AI 总结：针对振荡波场稀疏重建的欠定逆问题，提出HarmoCore模型，通过函数潜在扩散在核心空间采样，在1%--2%传感下的多类实验中取得显著性能提升。

链接：https://arxiv.org/abs/2609.00679

机构：College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与工程学院）

作者：Lihao Chen, Xinyu Zhang, Panqi Chen, Lei Cheng, Ting Zhang, Jianlong Li, Shikai Fang

英文摘要：Reconstructing oscillatory wave fields from scattered sensors is a severely underdetermined inverse problem. Beyond the challenges of general physical-field reconstruction, wave responses are complex-valued, frequency-sensitive, and highly oscillatory, while costly simulation and sensing often leave only extreme-sparse observations. Existing low-rank, operator, and diffusion approaches are largely designed for real-valued, smoother fields; dense pixel-space diffusion is particularly inefficient for oscillatory complex fields and difficult to scale to 3D. We propose HarmoCore, which places a generative prior in a compact, continuous, and structured wave-field latent. HarmoCore represents joint real--imaginary channels with Functional Tucker cores over shared continuous spatial bases, learns a frequency-conditioned core diffusion prior, and performs Diffusion Posterior Sampling directly in core space. At fixed sensor coordinates, the multilinear decoder induces an explicit likelihood guidance operator, avoiding dense pixel-space correction. Optional target-equation residual guidance further promotes physical consistency. Experiments on 2D Helmholtz, 2D synthetic wave fields, and 3D Helmholtz show substantial gains under 1%--2% sensing while remaining practical in three dimensions.

AI 总结：该研究针对局部学习方法特征学习弱的问题，提出边界优先推理方案并实例化为预测编码网络，在CIFAR-10上提升了准确率，验证了该方案的有效性。

链接：https://arxiv.org/abs/2609.00686

作者：Xueyuan Li, Danilo Vasconcellos Vargas

英文摘要：Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning in deep networks. We study whether the order of hidden-state optimization can address this limitation. We propose a boundary-first inference schedule that partitions a model into chunks, first coordinates hidden states at chunk boundaries, and then refines representations within each chunk. We instantiate this schedule in predictive coding networks (PCNs), a local-learning framework in which hidden activities and prediction errors are explicitly exposed during inference. On CIFAR-10, the resulting boundary-first predictive-coding instantiation improves accuracy over standard predictive coding by $9.77\%$ under a standard parametrization and by $5.51\%$ under a $\mu$-parametrization. Diagnostic analyses further show more non-trivial early-layer updates, lower initial-to-final CKA, and more diverse layerwise gradients, consistent with stronger feature learning. These results support boundary-first, chunk-based inference as a practical design principle for predictive-coding training and motivate its study in broader local-learning systems.

AI 总结：该研究针对VL微调导致LLM文本能力损失的问题，提出用Sink Strength诊断并预测退化，发现QK-RMSNorm及现成权重合并无法恢复能力，建议用Sink Strength筛选主干。

链接：https://arxiv.org/abs/2609.00746

机构：Korea University（高丽大学）； NAVER Cloud（NAVER云）； KAIST（韩国科学技术院）

作者：Minsik Choi, Geewook Kim, Young Geun Kim

英文摘要： Fine-tuning a pretrained LLM into a vision-language model (VLM) can erode the backbone's text capability, with the damage concentrated on tasks that require following exact output rules, such as instruction following, chain-of-thought reasoning graded on a strictly parsed final answer, and similar evaluations with strict graders. We trace this gap to attention-sink corruption: VL fine-tuning perturbs the early sink position that anchors a large fraction of attention probability, and how well the base LLM preserves its sink tracks how much of the affected capability survives adaptation. Building on this view, we introduce Sink Strength, a single scalar computed on the base LLM in a few seconds on a single GPU that predicts post-VL degradation without any VL training. It consistently tracks relative degradation across the six VLM-LLM pairs and multiple format-sensitive tasks. Complementing this diagnostic, we find that post-pretraining QK-RMSNorm injection fails to reproduce the protection of native QK-RMSNorm, while several off-the-shelf weight-merging settings fail to recover the lost capability after VL training. These negative results underscore the value of screening backbones with Sink Strength before VL training and narrow the intervention space toward head-selective training-time protection.

AI 总结：该研究通过反事实实验，在Qwen、Llama、OLMo模型上揭示语言模型的上下文与参数知识选择受任务依赖的权威方向影响，局部方向对源选择转变的重现效果优于跨任务方向。

链接：https://arxiv.org/abs/2609.00753

机构：Stanford University（斯坦福大学）； Perpetual Labs（永久实验室）

作者：Benjamin Shih, John Winnicki, Arianna Cao

英文摘要：When contextual information conflicts with the knowledge stored in model parameters, activation directions can be used to decode and steer which source the model follows. However, steering along a direction does not establish causality: whether the unedited model would naturally use that direction or whether the direction is reusable across tasks. We test these distinctions through counterfactual experiments in unambiguous settings. First, we estimate authority directions from agreement prompts, in which the context and parametric knowledge support the same answer. We then interchange naturally occurring coordinates along these directions between matched prompts that direct the model to prioritize either the supplied context or its parametric knowledge. Across Qwen, Llama, and OLMo models, this intervention reproduces 30-68% of the authority-induced shift in source choice, whereas matched controls reproduce almost none. To test cross-task reuse, we learn authority directions on two tasks separately and see that cross-task transferability closes only 9% of the authority gap while the local direction learned on the given task closes 57%. These results distinguish authority representation, causal use, and cross-task causal reuse, and suggest that authority computations may be task-dependent, rather than reusable across tasks.

AI 总结：HarnessEvolve是一种将执行与进化解耦的智能体自进化框架，通过参考轨迹克服信用分配失败，经质量与性能门控防止捷径学习和灾难性遗忘，在多基准上性能优于现有方法。

链接：https://arxiv.org/abs/2609.00829

机构：ICT AI Competence Center, Huawei Technologies（华为技术有限公司ICT AI能力中心）

作者：Wen Jiang, Mingmin Chu, Yimeng Tian, Qianxin Zhang, Haofei Yang, Rui Yang, Yang Liu, Tao Lv, Fangming Li

英文摘要：Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback. This paradigm, however, is hampered by three challenges: \textit{credit assignment failure}, where terminal success/failure feedback makes it ambiguous which step caused the error; \textit{shortcut learning}, where agents memorize task-specific patterns rather than acquire generalizable capabilities; and \textit{catastrophic forgetting}, where unguarded updates degrade previously acquired competence. In this paper, we introduce HarnessEvolve, a self-evolving framework that learns from reference trajectories to achieve reliable agent self-evolution. HarnessEvolve decouples the execution agent from the evolutionary pipeline, assigning execution, evaluation, optimization, and gating to independent agent modules, enabling generalizable and stable harness improvements. Specifically, HarnessEvolve overcomes credit assignment failure by generating reference trajectories (execution paths produced when given the ground-truth answers) and aligning failed executions against them to extract error signals, which are clustered to reveal systematic failure patterns. To prevent shortcut learning and catastrophic forgetting, candidate harness updates must pass two gates: a quality gate that filters data leakage and prompt bloat, and a performance gate that accepts each update if it improves on the current batch without degrading recent batches, with epoch-end validation on a held-out set selecting the best-performing accepted agent snapshot. We conduct extensive experiments on several benchmarks spanning open-domain and enterprise scenarios, using different models and agent frameworks. Results demonstrate that HarnessEvolve consistently outperforms state-of-the-art baselines across all benchmarks and settings, confirming reliability across task domains.

AI 总结：针对智能体压缩上下文训练引发的树状学习对象问题，提出LogitTree、4D注意力掩码及SDCC方法，在七个网络搜索基准上验证SDCC可缩小训练-rollout差距并提升奖励。

链接：https://arxiv.org/abs/2609.00865

机构：Token Foundry, Alibaba Group（Token Foundry，阿里巴巴集团）

作者：Zinco J, Xunjie Zhu, Shen Huang, Zhenyi Wang, Pengjun Xie, Jieping Ye

英文摘要：Production agent harnesses such as Claude Code and Qwen-Agent compress context during rollout, but training under compression creates a conditioning problem: every eviction branches the effective history, so the learning object is a tree rather than a sequence. Existing linearizations either retain the rightmost path, causing time-travel leakage, or replay a depth-first traversal, causing train-inference mismatch. We introduce two exact, gradient-equivalent corrections: LogitTree, a segmented K-forward traversal, and a packed 4D attention mask. LogitTree requires K+1 backward passes; the 4D mask requires a custom kernel and white-box eviction records. We also propose SDCC (Self-Distillation for Conditioning Consistency), a single-backward-pass variational relaxation. At each eviction, it minimizes forward KL between the compressed student and a stop-gradient teacher on the reconstructed pre-eviction prefix. A residual per-junction KL of epsilon_KL gives an O(sqrt(epsilon_KL)) bound on the train-deployment total-variation gap. SDCC also applies to black-box harnesses. On seven web-search benchmarks with TC-RAG, AgentFold, MemexRL, Claude Code, and OpenCode, naive training inflates the train-rollout log-probability gap, especially on eviction-heavy batches. The exact methods stay at the no-compression floor, and SDCC substantially closes the gap, with lower logit drift and higher rollout rewards.

AI 总结：本文针对现有泊松-伽马动力系统（PGDS）无法捕捉计数时间序列时变转移动力学的局限，提出TV-PGDS模型，构建三类狄利克雷马尔可夫链，开发高效吉布斯采样器，实验证实其预测性能优于相关模型。

链接：https://arxiv.org/abs/2609.00896

机构：University of Arizona（亚利桑那大学）； Great Bay University（大湾区大学）； Tsinghua University（清华大学）

作者：Jiahao Wang, Yijun Wang, Nan Fang, Sikun Yang

英文摘要：Bayesian methodologies for handling count-valued time series have gained prominence due to their ability to infer interpretable latent structures and to estimate uncertainties. Among these Bayesian models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still falls short in capturing the transition dynamics that are commonly observed in real-world count time series. To mitigate this limitation, a PGDS with time-varying transition kernel (TV-PGDS), is proposed to allow the underlying transition matrices to evolve over time. Three specifically-designed Dirichlet Markov chains (Dir-Dir, Dir-Gam-Dir, PR-Gam-Dir) are constructed to accommodate heterogeneous structural mutations within these dependencies. Leveraging Dirichlet-Multinomial-Beta data augmentation techniques, a fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed PGDS achieves improved predictive performance due to its capacity to learn time-varying dependency structure captured by the time-evolving transition matrices.

AI 总结：该研究针对生成建模中条件采样的挑战，提出基于偏好投票的精确MH采样器Pref-MH，利用成对比较反馈实现最优条件采样，在多模态生成任务中验证了其实用性。

链接：https://arxiv.org/abs/2609.00905

机构：Technion – Israel Institute of Technology（以色列理工学院）

作者：Ariel Smogorghevski, Nir Rosenfeld, Yaniv Romano

英文摘要：Sampling from distributions conditioned on desired semantic properties is an emerging challenge in modern generative modeling. Metropolis-Hastings (MH) provides a principled route to conditional sampling, but requires access to exact pointwise target-density evaluations, which are not available in generative settings. Meanwhile, pairwise comparisons by humans or model "judge" are highly accessible and have proved valuable across diverse applications. We introduce Pref-MH, a general exact MH sampler for judge-induced conditional distributions using only stochastic binary pairwise comparisons. Our key observation is that the MH unnormalized density ratio matches the preference odds of the Bradley-Terry (BT) choice model. The central challenge is that while MH requires precise ratio computation, BT judges provide only sampled binary feedback. To this end, we develop a valid accept/reject rule whose resulting Markov chain provably converges to the target distribution. We further show that, for a fixed proposal kernel and budget, Pref-MH is optimal in the Peskun-Tierney sense among this class of exact reversible acceptance rules. Experiments on text generation and molecular design with LLM judges, as well as image generation with VLM judges, demonstrate that Pref-MH provides a practical and flexible approach to conditional sampling when comparative feedback is relatively easy to obtain.

AI 总结：SAGE是两阶段生成增强框架，通过生成合成数据缓解虚假关联，在Waterbirds等三个数据集上的最差群体准确率优于无群体标签基线，提升最多7.7个百分点。

链接：https://arxiv.org/abs/2609.01051

机构：Harbin Institute of Technology（哈尔滨工业大学）； State Key Laboratory of Smart Farm Technologies and Systems（智慧农场技术与系统国家重点实验室）

作者：Yiming Luo, Rongqiang Zhao, Jie Liu

英文摘要：Spurious correlations pose a significant challenge to the robustness of modern machine learning. The inherent imbalance in dataset distributions often leads traditional Empirical Risk Minimization (ERM) models to rely on majority spurious attributes for classification, resulting in poor performance on minority groups. This problem becomes particularly challenging when the spurious attributes are unavailable. Existing group-label-free methods often upsample minority groups or misclassified real training examples; repeating the same instances can reduce effective diversity and encourage overfitting. To mitigate these spurious correlations from a data-centric perspective in the absence of prior knowledge, we introduce Subpopulation-Aware Generative Enhancement (SAGE), a two-stage generative augmentation framework. Using cluster-derived sub-labels and class labels, we fine-tune a conditional generative model and text encoder, generating targeted synthetic data to fill underrepresented regions in the training set and construct a balanced validation set for last-layer reweighting. We experimentally show that SAGE achieves 89.5%, 85.7%, and 79.1% worst-group accuracy on Waterbirds, CelebA, and MetaShift, respectively, outperforming the best group-label-free baselines by up to 7.7 percentage points.

AI 总结：该研究提出Modelpedia框架，用于从论文提取模型发现并聚合为可搜索目录，已在ICLR论文中提取超千条发现，助力AI元科学发展。

链接：https://arxiv.org/abs/2609.01090

机构：Centre for Credible AI（可信人工智能中心）； Warsaw University of Technology（华沙理工大学）； University College Cork（科克大学学院）； University of Technology Sydney（悉尼科技大学）； Human-Centered AI Lab（以人为中心的人工智能实验室）； University of Pisa（比萨大学）； ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）； Technical University of Berlin（柏林工业大学）； Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）； Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）； University of Warsaw（华沙大学）

作者：Franciszek Bernat (1 and 2), Dawid Płudowski (1 and 2), Michał Jan Włodarczyk (1 and 2), Luca Longo (3), Jianlong Zhou (4), Andreas Holzinger (5), Riccardo Guidotti (6 and 7), Wojciech Samek (8, 9 and 10), Przemysław Biecek (1, 2 and 11) ((1) Centre for Credible AI, (2) Warsaw University of Technology, (3) University College Cork, (4) University of Technology Sydney, (5) Human-Centered AI Lab, (6) University of Pisa, (7) ISTI-CNR, (8) Technical University of Berlin, (9) Fraunhofer Heinrich Hertz Institute, (10) Berlin Institute for the Foundations of Learning and Data, (11) University of Warsaw)

英文摘要：Scientific knowledge about AI models is produced faster than the community can organize it. Every few months a new foundation model reshapes the field and hundreds of papers, blogs, and technical reports document how each behaves or fails. Yet, these findings remain scattered and effectively unretrievable. To address this gap we present Modelpedia, an automated, LLM-assisted framework that extracts findings about models from published papers, links it to the model, dataset, method, and concept it concerns, and aggregates the result into a searchable public catalog. Applying the prototype to accepted ICLR 2024 and 2025 papers, we extract over a thousand findings and, treating the catalog itself as an object of study, run a meta-analysis of how the community investigates models. Now, we invite the community to explore, contribute to, and build on the open catalog, and to help establish model findings as a shared foundation for the meta-science of AI.

AI 总结：本文复现TRACE算法，发现其最优阈值与真值边际相关，单一全局阈值对滞后1边效果好、对高阶边差，基准滞后衰减会混淆算法极限，粒子数2时F1饱和，并提炼出五条从业者规则。

链接：https://arxiv.org/abs/2609.01108

机构：LotusFlare Inc.（莲花flare公司）

作者：Alex Chadyuk, Alicia Zhang, Roy Kucukates

英文摘要：TRACE (Math & Lienhart, arXiv:2602.01135 ) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-position conditional-mutual-information estimate at a fixed tau. We independently replicate its headline synthetic result: with tau selected on a validation split, mean per-sequence F1 against exact interventional truth reaches 0.90-0.91 at vocabulary size 1000 (paper: 0.91) and 0.86-0.91 from 100 to 2000. First, the optimal threshold is pinned to the truth margin, not to any constant: at every size the errors at tau* straddle the delta = 0.05 margin defining ground truth (missed true edges lie just above it, accepted false ones just below), and the blind optimum lands near delta/2 times the estimator's calibration, confirmed out of sample at 5000. Second, at a single global threshold TRACE mostly recovers a direct, adjacent-influence graph: lag-1 true edges are recalled at 0.97-0.99, while true edges at lag 2 or more read orders of magnitude lower---the reading-scale price of randomizing mediating positions, which an exact test of direct causal effect requires when the truth is unknown. A per-lag threshold family recovers a third to a half of lag-2 truth; on lag-uniform data one validated threshold recalls every lag at 0.40-0.87, 8-26 pp below an atomic-intervention control at lags 3-6. Third, the default lag decay of the paper's synthetic benchmark concentrates about 85% of interventional truth at lag 1 and pushes the rest below the estimator's noise floor, so headline F1 there certifies lag-1 recovery only and conflates the benchmark's skew with the algorithm's own limit; a flatter decay separates the two. Fourth, F1 saturates from N = 2 particles at the selected threshold---a property of the threshold's margin over the noise floor, not of the estimator, which converges as N^(-1/2). We distill five practitioner rules.

AI 总结：该研究发现Transformer注意力中存在缩放幂等性的代数规律，通过OV几何分解与值共享扩展，揭示了训练注意力头的稀疏方向特性及局部算子代数关系。

链接：https://arxiv.org/abs/2609.01129

机构：College of Computer Science, Beijing University of Technology（北京工业大学计算机学院）； School of Mathematics, Statistics and Mechanics, Beijing University of Technology（北京工业大学数学、统计与力学学院）

作者：Jiming Feng, Junliang Li

英文摘要：We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators $T=OV^\top$ nearly closes under composition, $T^2\approx\alpha T$. Across six pretrained endpoints spanning 2.8B--235B parameters, 3.98--8.00% of heads reach squared closure alignment $\mathcal{P}\geq0.9$, while no matched within-layer O/V mismatch does. An exact principal-coordinate factorization, $T=Q_OKQ_V^\top$ and $T^2=Q_O(KDK)Q_V^\top$, separates within-support transport from read--write return geometry. Across all 7,304 heads in nine MHA/GQA models, scrambling only the orientation of $K$ while preserving singular values, norms, factor spans, and principal angles reduces median closure from 0.336 to $1.04\times10^{-4}$; trained orientation wins for 98.64% of heads and in every layer. Constructive searches show that high closure is feasible in every surveyed layer, but usually not attained. Retrospective trajectories in three independently trained lineages further separate broadly available capacity from the orientations attained by final strong heads. Under exact value sharing, headwise closure extends to a right-action algebra, $T_iT_j=\alpha_jT_i$. Seven-model experiments verify the approximate law and reveal distinct oblique projections with a shared value-defined kernel. These results characterize scaled idempotence as a sparse trained orientation within broadly available geometric capacity and show how value sharing extends a headwise relation into a local operator algebra.

AI 总结：提出叠加式潜在自编码器（SLAE），通过学习叠加共享存储，在相同内存预算下改善重构-内存权衡，降低重构误差，还提升下游分类性能，为表示压缩提供新原则。

链接： https://arxiv.org/abs/2609.01158

机构：University of California San Diego（加利福尼亚大学圣迭戈分校）； Georgia Institute of Technology（佐治亚理工学院）； University of California Riverside（加利福尼亚大学河滨分校）； San Diego State University（圣迭戈州立大学）

作者：Quanling Zhao, Jiaying Yang, Tianqi Zhang, Ziyang Hao, Fatemeh Asgarinejad, Flavio Ponzina, Tajana Rosing

英文摘要：Autoencoders typically meet tight latent-memory budgets by making each latent representation smaller, sacrificing representational capacity. We ask a different question: can multiple wider latents be stored together instead? We introduce the Superposed Latent Autoencoder (SLAE), which preserves high-capacity latent representations while sharing storage through learned superposition. SLAE transforms latents into storage-friendly codes, binds them with randomized keys, superposes multiple codes into a single memory tensor, and learns to recover each latent before decoding. Under the same storage budget, SLAE replaces irreversible dimensional bottlenecks with structured interference that can be suppressed. Across CIFAR-10/100, SVHN, STL-10, Tiny ImageNet, and a wide range of memory budgets, SLAE substantially improves the reconstruction--memory tradeoff, reducing reconstruction error by up to 56% over conventional autoencoders at matched storage. Further analysis shows that SLAE's advantage comes from making wider representations usable under the same storage budget. These gains also extend beyond reconstruction: the information preserved by SLAE improves downstream classification by up to 16.79 percentage points under the same memory budget. Our results suggest a new principle for representation compression: instead of making every latent smaller, keep representations wide and let them share memory.

AI 总结：该研究追踪Pythia-410M模型训练中模块化任务分区的形成过程，发现其模块化图谱预雕刻、分区通过梯度相对剥夺锁定且偏差随学习领域出现，预注册了28亿参数实验的规模阈值假设。

链接：https://arxiv.org/abs/2609.01170

机构：Zaozhuang University（枣庄学院）

作者：Guangqi Li, Yongxin Li

英文摘要：Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organization forms during training is unknown: prior work has characterized finished models, not the formation process. We track formation step by step: we train a Pythia-410M model from scratch (two trajectories, bf16 and fp32) and run attribution patching at every step, alongside probes for gradient norms, effective updates, weight norms, and first-order loss decomposition across 14 tasks in four cognitive domains. Three findings. First, the modular map is pre-carved: before any learning, the dominant task pair already overlaps at ~3.6x the attribution substrate (a task-independent baseline), and its layer-0 concentration is an architecture-level constant on this model family. Second, the partition locks in through two sharp jumps whose amplitudes do not track the learning-rate schedule (the second reaching 20.4 sigma quiet-window / 6.2 sigma global), accompanied by gradient-level relative deprivation--winners receive 2.25->2.73x the loser's gradient supply, 9.5-11.5 standard deviations below a random control--that does not propagate to updates or weights. Third, deviation from the substrate appears only in the domain being learned, consistent with the hypothesis that modularity tracks learning. We close by separating the feature-level account we can defend from the mechanistic questions we cannot, and we pre-register the scale-threshold hypothesis behind our ongoing 2.8B experiments.

AI 总结：该研究以荷兰居民生育预测为对象，借助含147名研究者的数据挑战，发现高级模型未优于经典模型，估算出生育预测上限，揭示生殖偶然性对个体人生预测的显著限制。

链接：https://arxiv.org/abs/2609.01194

作者：Elizaveta Sivak, Emily M. Cantrell, Thomas Emery, Javier Garcia-Bernardo, Flavio Hafner, Kasia Karpinska, Malte Lüken, Adrienne Mendrik, Joris Mulder, Hanzhang Ren, Varun Satish, Mark Verhagen, Angelica M. Maineri, Paulina Pankowska, Jasmin Abdel Ghany, Bruno Arpino, Giovanni Cassani, Julia Hellstrand, Katya Ivanova, Sanni Kuikka, Ana Macanovic, Charles Rahal, Felix C. Tropf, Roland J. Veen, Nicole Walasek, Daniël van Wijk, Kelsey Q. Wright, Emilio Zagheni, Henry Abbink, Emanuele Aliverti, Matteo Amestoy, Tilbe Atav, Nicola Barban, Sunnee Billingsley, Goan J. Booij, Louis Boucherie, Yael Broos, Li Ya Chang, Jamie C. Chiu, Chiara Ludovica Comolli, Boris Cule, Qixiang Fang, Dennis M. Feehan, Rachel Ganly, Erwin Gielens, Rolando M. Gonzales Martinez, Andrea Gradassi, Rosember Guerra-Urzola, Mario Guerra-Urzola, Stéphane Guerrier, Enamul Hassan, Vincent A. Haverhoek, Andrew T. Hendrickson, Amber Howard, Yuxuan Jin, Sayash Kapoor, Erik-Jan van Kesteren, Iris ten Klooster, Marie Labussiere, Lydia T. Liu, Tiffany Liu, Adam Maghout, Simone Meneghello, Lasse Mohr, Clara H. Mulder, Saul J. Newman, Jessica Nisén, Janis Norden, Mikkel Odgaard, Riccardo Omenti, Ozancan Ozdemir, Christina Pao, Paige Park, Gaia Penta, Juan C. Perdomo, Tanzir Pial, Alessio Piraccini, Federica Querin, Ziwei Rao, Christian Rellama, Adrien Remund, Frederieke Richert, Arnout van de Rijt, Mojtaba Rostami Kandroodi, Stijn J. Rotman, Lucas Sage, Germans Savcisens, Katrin Schwanitz, Steven Skiena, Alessandro Spata, Yannick Stadtfeld, Benedikt Stroebl, Gaetano Tedesco, Mathilde Theelen, Gianluca Tori, Abigail Tun-Mendicuti, Rishabh Tyagi, Keyon Vafa, Luiz Felipe Vecchietti, Linda Vecgaile

英文摘要：Major life events have proven difficult to predict. Does this reflect limits of theory, data, and algorithms, or the large role of chance? We examine one outcome - having a child within three years - through a near-ideal setting for prediction: a data challenge where 147 researchers predicted births for Dutch residents aged 18-45, using survey data and full-population registers. Methods ranged from logistic regression to a large language model and transformers. Predictions were moderately accurate (best F1: register 0.59, survey 0.76); advanced models did not outperform classical ones; and the larger registers did not beat the survey. Simulating the stochastic biology of conception and pregnancy, we estimated a predictive ceiling (survey F1 ~ 0.86-0.94, register 0.88-0.96). Observed performance falls short of this ceiling, implicating imperfect data, methods, and unmodelled chance, while the ceiling itself shows that chance in reproduction alone sets a non-trivial limit on predicting individual lives.

AI 总结：REFACTOR-VLA 是用于学习可复用技能的醒/睡系统，在 LIBERO 数据集上，其改进的训练目标提升了聚类性能，生成了首个 real-LIBERO 任务-语言库，性能优于现有基线。

链接：https://arxiv.org/abs/2609.01215

机构：Apple（苹果公司）

作者：Riyaaz Shaik, Chandru Venkataraman

英文摘要：Most vision-language-action (VLA) models -- OpenVLA, $\pi_0$, RT-2, RDT-1B -- are monolithic: they emit raw motor commands or short action chunks without organizing behavior into reusable abstractions, so they degrade on long-horizon tasks and resist interpretation. Existing skill-discovery methods sidestep the core question of when two action sequences are behaviorally equivalent, either clustering contrastive embeddings or delegating the judgment to a language model uncalibrated to the robot's dynamics. We introduce REFACTOR-VLA, a wake/sleep system for learning reusable skills. Its sleep phase clusters motor-program fragments under a Behavioral-Equivalence Kernel (BEK) computed from rollouts of a learned latent world model $M_\phi$; its wake phase emits typed lambda terms over a Hindley--Milner-inspired vocabulary, consumed by a library-conditioned rectified-flow action decoder. Abstractions are admitted only if they pass Minimum Description Length and return-preservation gates. On LIBERO we report two findings. First, enlarging the world model from 188M to 430M parameters worsened performance on 4 of 4 suites, so capacity alone does not help. Second, the training objective matters far more: adding an auxiliary supervised contrastive (InfoNCE) loss during world-model warmup substantially improves sleep-phase clustering, giving Normalized Mutual Information at $n=3$ seeds of $0.462 \pm 0.021$ (object), $0.867 \pm 0.025$ (spatial), $0.915 \pm 0.013$ (goal) and $0.754 \pm 0.010$ (LIBERO-10), and beating the strongest published baseline on all 4 suites by a mean $\Delta = +0.184$. Across providers ($n=12$) the 95% bootstrap confidence interval for mean pairwise NMI is $[0.683, 0.729]$ (mean $0.705$). The sleep phase also yields the first real-LIBERO task-language library: the decoder uses 2 of 3 admitted abstractions and rewrites all 256 sampled demonstrations.

AI 总结：本文针对合成数据隐私属性的认知偏差，经实证分析发现其隐私保证隐含难验证，主张将隐私视为明确的证据型科学声明，建议ML venues制定相关规范。

链接：https://arxiv.org/abs/2609.01273

机构：University of Notre Dame（圣母大学）

作者：Jiachen Zhao, Antonia Januszewicz, Taeho Jung

英文摘要：Synthetic data has become a common component of machine learning research. While widely adopted, its use in privacy-sensitive contexts has quietly shifted from a claim of residual inference risk under stated assumptions to an appearance-based property inferred from data generation itself. In this position paper, we argue that this shift reflects an implicit change in community standards for what counts as sufficient privacy evidence, rather than a misunderstanding of well-established privacy principles. Drawing on an empirical analysis of recent publications across major ML venues, we show that synthetic data is frequently used in privacy-sensitive settings without explicit articulation of threat models, inference risks, or falsifiable privacy claims. As a result, privacy assurance often remains implicit, difficult to verify, and unevenly distributed, with heightened exposure for rare and minority records. We argue for treating privacy as an explicit, evidence-based scientific claim and recommend that ML venues adopt norms requiring privacy-relevant assertions to be clearly scoped, testable, and contestable.

AI 总结：该研究指出前沿AI模型的宪法供给无法覆盖人类需求，提出预算多元主义三难困境，发现精简的宪法菜单可显著降低遗憾，为AI治理提供了关键洞见。

链接：https://arxiv.org/abs/2609.01275

机构：Kera Health Platforms（Kera健康平台）

作者：Natalija Mitic, Soona Sedahmed A. O., Mamadou Selly Ly, Moustapha Cisse

英文摘要：Frontier AI systems function as \emph{constitutional institutions}: each deployed model encodes an implicit ranking among safety, helpfulness, honesty, autonomy, and equity. We ask whether the supply of frontier constitutional types covers human demand. Combining a paraphrase-controlled audit of the as-shipped default constitutions of $23$ frontier LLM archetypes with a pairwise-tradeoff study of $1{,}649$ US participants on the same instrument, we report three facts. \emph{Demand is broad}: it spans all five values, with the largest constituency under one-third. \emph{Supply is narrow and drifting}: the $23$-archetype hull occupies ${\sim}2\%$ of the demand hull under conservative noise-matched estimation ($0.10\%$ at full audit precision), no archetype puts helpfulness or autonomy first ($37\%$ of users are constitutionally homeless), and across six model families autonomy decreases in $5/6$, equity increases in $5/6$, and safety increases in $4/6$, with monotone within-family version trends (order-permutation $p = 0.013$) and the autonomy decline concentrated in scenarios where safety is not at stake. The drift's importance is directional: \emph{away} from a value already undercovered, mechanically worsening the welfare floor for the least-served users. \emph{The fix is sparse}: a $2$-vertex menu $\{e_{\mathrm{HON}}, e_{\mathrm{AUT}}\}$ beats the full $23$-archetype frontier by $47\%$ on mean regret (CI $[43\%, 52\%]$); three vertex additions cut mean/worst-group regret by up to $81\%$/$64\%$. We formalize these findings as a budgeted-pluralism trilemma, show the binding regime is empirically realized, and verify the conclusions are robust to distance-based welfare and to degraded routing. The instrument and audit harness are described in full in the appendices.

AI 总结：该研究将单层Transformer与最近邻分类器的等价性从二分类扩展至多分类，证明带argmax头的单层Transformer等价于多分类单最近邻，填补了前期研究的空白。

链接：https://arxiv.org/abs/2609.01311

机构：James B. Conant High School（詹姆斯·B·柯南特高中）； Illinois Institute of Technology（伊利诺伊理工大学）

作者：Skanda Athreya, Yutong Wang

英文摘要：We extend recent work establishing an equivalence between one-layer transformers and nearest-neighbor classifiers in the binary setting to the multiclass case. By leveraging the simplex encoding, we show that one-layer transformers with an argmax classification head behave identically to a one-nearest-neighbor classifier in the multiclass setting. This closes a gap left by prior work, whose multiclass result relied on a non-standard rounding-based approach rather than the typical argmax head used in practice.

AI 总结：该研究针对多模态拆分学习的上行链路带宽分配问题，提出ModalShare分配器，利用Shapley贡献分数设置各模态保留率，在5倍压缩下显著提升了CREMA-D和MVSA数据集的准确率，且适配多种压缩器、数据集和预算。

链接：https://arxiv.org/abs/2609.01406

机构：Yale University（耶鲁大学）

作者：Iason Ofeidis, Leandros Tassiulas

英文摘要：Multimodal models are increasingly the default option for perception at the network edge, yet they are trained almost entirely in the datacenter, because a client holding several sensor streams cannot host an encoder per modality. Split Learning makes such training feasible by keeping only the first layers on the device, at the cost of an uplink that must carry smashed activations for every modality at every step. Existing compression schemes give each modality the same keep-ratio, so the shared budget is divided in proportion to smashed-activation dimension, a quantity unrelated to how much each modality contributes to the fused prediction. We make that division an explicit decision and call it inter-modality allocation: under a fixed uplink budget, every policy transmits the same expected payload and differs only in how that payload is split across modalities. Our allocator, ModalShare, sets each modality's keep-ratio from a Shapley contribution score that the server computes over coalitions of activations it has already received. Measuring this score adds no uplink traffic and no client-side computation, and needs no prior knowledge of which stream is which. ModalShare improves accuracy over equal keep-ratios by 15.4 and 12.4 percentage points on CREMA-D and MVSA at matched payload in 5x compression, with strong performance across three compressors, three datasets, and four budgets. We show that existing compressors underperform in multimodal settings, with ModalShare recovering what gains are left behind.

AI 总结：本研究针对ReAct范式LLM智能体的效率问题，提出TRIAGE三级路由框架，通过复用历史轨迹实现三级查询处理，在安全监控和跨域实验中显著减少token消耗，形成效率提升的正反馈循环。

链接：https://arxiv.org/abs/2609.01428

机构：China Telecom Cloud（中国电信云）

作者：Ruocan Wei

英文摘要：Large Language Model (LLM) agents based on the ReAct paradigm have demonstrated remarkable capabilities in tool use and task execution. However, ReAct suffers from a fundamental efficiency problem: every query triggers a complete reasoning loop from scratch, and similar queries repeat identical steps without leveraging historical experience. We propose TRIAGE,a three-level routing framework that reduces token consumption by reusing historical execution trajectories. Its core innovation is TaaS (Trajectory-as-a-Skill), which abstracts historical execution trajectories into reusable skills, realizing 'experience as a service'. TRIAGE classifies queries into three levels: (1) Direct Reuse-identical queries, 0 tokens; (2) Skill Substitution-similar queries, 0 tokens via deterministic parameter substitution; (3) Full ReAct-novel queries, automatically stored for future reuse. In large-scale experiments on 1,007 security monitoring queries, TRIAGE achieves 62.3% token savings, with 56.0% of queries at Level 2 and 5.5% at Level 1, both executing at zero cost. Cross-domain validation on ToolBench (15 domains, 345 queries) achieves 76.3% token reduction, confirming the generalizability of semantic routing. An online learning experiment demonstrates cold-start-to-mature evolution: the L2 hit rate rises from 0% to 57% within the first 100 queries, and the average token cost drops from 198 to 74.7. We also propose an automatic Skill extraction mechanism that distills high-frequency trajectory patterns into deterministic Skills, creating a positive feedback loop of 'the more you use it, the more efficient it becomes'.

AI 总结：该研究提出基于TTVAE的TREVIS方法，将决策树映射至潜在空间实现梯度优化，所获决策树兼具与近优算法相当的预测性能及更优结构稀疏性。

链接：https://arxiv.org/abs/2609.01430

机构：University of Pisa（比萨大学）； ISTI-CNR

作者：Giacomo Fidone, Alessio Cascione, Riccardo Guidotti

英文摘要：Decision trees are among the most widely used models in machine learning, largely due to their transparent decision logic, making them well-suited for high-stakes decision-making contexts. However, most existing learning algorithms focus on predictive performance, overlooking the joint optimization of other desirable properties, such as structural sparsity. In this work we propose TREVIS, an approach for learning decision trees with respect to complex objectives, based on the exploration of the latent space of a Tree Transformer Variational Auto-Encoder (TTVAE). By mapping decision trees onto latent representations, TREVIS replaces the discrete search space with a continuous one, enabling gradient-based optimization via a differentiable surrogate model. We experiment with TREVIS for learning decision trees that jointly optimize predictive performance and sparsity. Results show that TREVIS discovers decision trees matching the predictive performance of existing near-optimal algorithms while improving their structural sparsity.

AI 总结：LatentPress将上下文压缩为连续记忆令牌，仅训练小型适配器，在多个长上下文任务中压缩后性能优于文本摘要和OCR，且读写速度更快，证实其作为机器面向上下文接口的实用性。

链接：https://arxiv.org/abs/2609.01507

机构：Cornell University（康奈尔大学）； Arizona State University（亚利桑那州立大学）

作者：Zhengze Zhou, Hejian Sang

英文摘要：Compressed context is usually carried as human-readable text or as rendered images that must be decoded, even when its consumer is a language model. We introduce LatentPress, which writes conversational histories and long documents into a third representation: continuous memory tokens that a frozen decoder reads directly through its input-embedding interface, with no text reconstruction at inference. A small reader-matched writer compresses $4$-$16\times$ while training only an adapter (4.2M-26.2M parameters, $\sim\!0.1\%$ of the decoder). On LongMemEval, LatentPress reaches $0.504$ accuracy at $7.70\times$ compression versus $0.490$ for uncompressed evidence, outperforming text summaries (0.184) and OCR-based compression (0.426 to 0.312). On LongBench-QA, in-domain writers match or exceed raw-context reading at $4$-$8\times$ compression, while $16\times$ trails raw. Writing takes 43ms per conversation, roughly an order of magnitude faster than text summarization or OCR reconstruction, and reading is $5$-$9\times$ faster than raw context or cached OCR. We validate the interface under two transfer settings, zero-shot from UltraChat to LongMemEval memory QA and from LongMemEval-derived QA to unseen LongBench document domains, establishing direct soft tokens as a practical machine-facing context interface beyond text and vision. The implementation of the experiments could be found at: this https URL.

AI 总结：本研究首次将量子机器学习应用于认知诊断的Q矩阵估计，提出量子稀疏自编码器，经60个模拟及9个真实测评数据集测试，其相比经典自编码器更稳定、在多数真实数据集上表现更优。

链接：https://arxiv.org/abs/2609.01537

机构：School of Computer and Cyber Sciences, Augusta University（奥古斯塔大学计算机与网络科学学院）； School of Computing, University of Georgia（佐治亚大学计算学院）； Department of Graduate Psychology, James Madison University（詹姆斯麦迪逊大学研究生心理学系）； Department of Computer Science and Engineering, University of Tennessee at Chattanooga（田纳西大学查塔努加分校计算机科学与工程系）； Department of Radiology, Massachusetts General Hospital, Harvard Medical School（哈佛医学院麻省总医院放射科）

作者：Arif Hassan Zidan, Yi Pan, Bowen Guo, Xiang Li, Yu Bao, Yingfeng Wang, Tianming Liu, Wei Zhang

英文摘要：Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires. Data-driven Q-matrix estimation remains challenging when assessments involve many correlated skills and when real response patterns depart from idealized generative assumptions. We introduce a novel quantum sparse autoencoder (QSAE) for Q-matrix estimation, which, to the best of our knowledge, is the first application of quantum machine learning (QML) to cognitive diagnosis. Overall, the QSAE embeds each student's binary response vector into a quantum circuit using an encoder, compresses it into a sparse latent representation, and maps that representation to the Q-matrix. We benchmark the QSAE against a classical autoencoder (CAE) across 60 simulated datasets and 9 real-world assessment datasets. The results reveal complementary strengths. Although the CAE partially achieves higher average accuracy under several simulation conditions, the QSAE is substantially more stable across replications, exhibiting lower variance in 49 of the 60 conditions. Moreover, on real assessment data, the QSAE outperforms the CAE on 6 of the 9 datasets. These findings suggest that the principal advancement of QML in this setting is not universal accuracy improvement, but enhanced robustness and capability to explore latent-structure complexity in real datasets.

AI 总结：该研究在数学和智能体轨迹领域发现嵌入检索存在表面形式偏差，LLM重排序器可部分缓解此偏差，而词汇重排序器的效果随领域变化，下游实验显示求解器准确率存在瓶颈。

链接：https://arxiv.org/abs/2609.01556

机构：MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）； Mantis（曼蒂斯（机构名））

作者：Nabira Rashid, Manolis Kellis

英文摘要： We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not wording, in two unrelated domains under one protocol, competition mathematics (MathNet-Retrieve; 500 queries, 117,088-item corpus) and embodied-agent trajectories (ALFWorld-derived; 118 queries, 336 trajectories). In mathematics the failure is complete: strict Hit@1 at the heaviest disguise tier is 0.0% for both production embedders (bootstrap 95% CI [0.0, 0.0]) while the correct item sits in the top 10 nearly always, and in 95.2 to 99.8% of misses the winner is more lexically similar to the query than the correct answer. In trajectories, where surface variation is incidental, the same models land at or near hypergeometric chance when gold must involve a different object, and below chance for all three embedders once gold must differ in object and receptacle: retrieval anchors on literal tokens, not task structure. A lexical reranker control hurts in mathematics and helps in trajectories (closing 26 to 36% of the gap, CIs excluding zero); its sign reveals whether a benchmark's surface variation is adversarial or incidental. An LLM reranker recovers 5 to 63% of the gap in mathematics and 43 to 76% in trajectories; direction replicates across three judges (all 21 cells positive), but effect sizes, tier profiles, and the outlier judge change with domain (paired differences excluding zero everywhere). Mathematics gains concentrate on well-known competitions (+19.8 points, CI [+6.7, +33.2], one of six cells), so part of the recovery is memorization. In a paired downstream experiment (210 queries, graders at 96 to 99% agreement), oracle retrieval was indistinguishable from adversarially bad retrieval (McNemar p = 0.678); the solver's 69.5% zero-shot accuracy is largely a truncation proxy (97 to 100% on finished answers), leaving no headroom.

AI 总结：本研究通过因果混合精度干预探究LLM量化损伤的结构，发现精度恢复多为分散式，全局分配精度预算比局部修复关键层性能更优，需用因果干预验证量化损伤的定位。

链接：https://arxiv.org/abs/2609.01587

机构：PayPal AI（PayPal人工智能部门）

作者：Jundong Hu, Shekar Ramachandran

英文摘要：Post-training quantization (PTQ) is widely used to reduce the cost of serving large language models (LLMs), but its accuracy cost is uneven and is often tuned per model. We study where quantization damage occurs and how to allocate a small additional precision budget. Using causal mixed-precision intervention as ground truth (raise each layer to 8-bit in turn and measure the accuracy it recovers) across 9 open-weight models in 4 architecture families, we test 3 intuitive hypotheses: that quantization damage lives in task circuits, where the model computes, or in weight statistics. None of them predicts which layers benefit from restored precision. Recovery is instead diffuse: for 8 of 9 models, recovering 75% of the gap takes roughly half the layers; the lone exception, Qwen3-8B, is sharply concentrated. At a matched precision budget, spending it globally on finer quantization granularity beats locally repairing the most recoverable layers for all 8 group-128-compatible models (all but OpenLLaMA, whose width rules out group-128), by 21-52 points, including the concentrated Qwen3-8B. We report 2 secondary findings: the residual is budget-limited (8-bit is near-lossless in our evaluation across RTN, GPTQ, and AWQ), and the location of peak recovery correlates with architecture within a family, though not across families. Within this budget setting, global granularity is a better default than selectively protecting critical layers. More broadly, cheap signals that correlate with quantization damage do not necessarily identify where restoring precision improves accuracy; this must be tested with causal intervention.