机器学习学术速递[11.9]

AI 总结：本文针对实验高能物理中粒子Transformer（ParT）可解释性不足的问题，提出基于Kolmogorov-Arnold网络（KAN）的分量归因方法，探究多头注意力（MHA）等机制能否学习喷注的物理判别特征。

链接：https://arxiv.org/abs/2611.08656

机构：Imperial College London（伦敦帝国学院）； Institute for Theoretical Physics (ITP), Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院理论物理研究所）； Institute for Quantum Materials and Technologies (IQMT), Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院量子材料与技术研究所）； Institute of Experimental Particle Physics (ETP), Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院实验粒子物理研究所）

作者：Lauri Laatu, Aritra Bal, Benedikt Maier, Markus Klute, Michael Spannowsky

英文摘要：Experimental High Energy Physics (HEP) has adopted the transformer architecture for identification of jets, particularly the state-of-the-art Particle Transformer (ParT) which injects explicit information about particle correlations into the attention mechanism. While able to achieve state-of-the-art results in accuracy, interpretability to its effectiveness has been limited. In this paper we propose component attribution methods using Kolmogorov-Arnold Networks (KANs) that directly tie back to the physical descriptors of jets, to probe whether mechanisms such as Multi-Head Attention (MHA), or the ParT architecture, are able to learn these as discriminating features.

AI 总结：该研究提出RF+MLP集成模型，利用地理空间嵌入分析38591个现有太阳能电站，在13国验证中ROC-AUC达0.90，较MCDA策略提升0.06-0.30，可高效开展全球太阳能选址。

链接：https://arxiv.org/abs/2611.08831

机构：University of Oxford（牛津大学）； European Space Agency（欧洲空间局）

作者：Abdullah Rehman, Quentin Paletta, Rui Song

英文摘要：Global solar photovoltaic (PV) capacity is rapidly growing, helping decrease our emissions and dependence on fossil fuels. However, optimally siting a solar plant remains challenging, requiring anticipation of geographical, urban, and infrastructure needs. Current methods rely on multi-criteria decision analysis (MCDA) using hand-picked geophysical layers and solar-resource products, however these strategies are not geographically transferable and do not capture the practical requirements of solar sites. We use geospatial embeddings, dense vectors representing geophysical properties of a location, to analyse 38,591 existing solar sites and the land they were built on to learn the latent solar suitability signal. We assess a set of linear and non-linear models and select a soft-voting ensemble of a random forest and a multilayer perceptron (RF+MLP ensemble), chosen for accuracy and large scale deployability. Validated against future installations in thirteen countries, the ensemble separates existing solar sites from random land with a median ROC-AUC of 0.90. Compared with published MCDA strategies, the ensemble increases ROC-AUC by 0.06-0.30 in every country. The ranking also concentrates real deployment: the most-suitable 20% of land holds 84% of estimated generation (annual energy yield) and 67% of installed capacity (potential power output). After applying standard siting constraints, 5.6% of global land (9.8% if cropland is permitted) remains highly suited to solar. The global 10 m resolution solar suitability dataset and code can be found here: this https URL.

AI 总结：本文提出SSF-Net，通过双分支SSF块结合多分辨率编解码器，在PDE基准上以更少参数实现更低预测误差，同时保持近线性复杂度。

链接：https://arxiv.org/abs/2611.08912

机构：University of New South Wales（新南威尔士大学）

作者：Siqi Zhao, Flora D. Salim

英文摘要： Machine learning methods for solving partial differential equations (PDEs) significantly improve computational efficiency over traditional numerical solvers such as finite element method (FEM). However, PDE dynamics inherently span both local and global dynamics: disturbances propagate and decay gradually through the domain, while global coupling effects can influence the whole system simultaneously. Capturing both types of dynamics with a low complexity model remains a key challenge. To address this, we propose the Spatial-Spectral Fusion Network (SSF-Net), built around a dual-branch Spatial-Spectral Fusion (SSF) block comprising a spatial branch and a spectral branch. The spatial branch employs a multi-directional Mamba, which mitigates its inherent causal, single-direction scanning bias and capture local interactions with reduced directional bias at linear complexity. The spectral branch leverages a Fourier transform with a block-diagonal MLP to efficiently capture global spectral features with reduced parameter count and complexity. The SSF block is embedded in a multiresolution convolutional encoder-decoder, which extracts multi-scale features. We evaluate SSF-Net on a comprehensive PDE benchmark spanning multiple task types and assess its long-horizon stability. Compared with attention-based and convolution-based baselines, SSF-Net achieves lower prediction error with fewer parameters while retaining near-linear asymptotic complexity in the number of spatial tokens.

AI 总结：该研究针对循环模型缺乏状态估计形式化保证的问题，将RNN建模为Neural ODE的离散化形式，通过施加收缩条件实现可调观测器，在移动机器人任务上验证了其性能优于普通GRU。

链接：https://arxiv.org/abs/2611.09217

作者：Vincent Andrieu (LAGEPP, CNRS), Pauline Bernard (CAS), Lucas Brivadis (L2S), Laurent Praly, Christian Wolf

英文摘要：Estimating the state of a dynamical system from observations is a crucial task in robotics and control. Despite their empirical success, recurrent models often lack formal guarantees on convergence and robustness. We bridge this gap by analyzing these architectures from the perspective of nonlinear observer theory. By framing RNNs as a time-discretization of continuous latent dynamical systems (Neural ODEs), we demonstrate that enforcing a contraction condition on the latent flow guarantees the existence of a smooth, injective map of the true physical state into the latent space. We prove that this architecture acts as a tunable observer: by increasing a single scalar gain that scales the latent vector field, the estimation error can be driven to an arbitrarily small neighborhood of zero at an exponentially fast rate. We further establish quantitative bounds on the MLP complexity required to decode this latent state, and extend our formal guarantees to the discrete-time residual RNN implementation. We validate the theory on a real mobile robotic task, where a provably contracting model outperforms a vanilla GRU with substantially more stable training. We also report that unconstrained GRUs converge to contracting dynamics on this task, suggesting that contraction is an emergent property of well-trained sequence models.

AI 总结：该研究将MoE负载平衡视为反馈控制问题，提出PID-Balancer控制器，采用纯积分项的PID（I），在混合分布切换和持续预训练场景中，相比现有方法能更紧密地恢复负载平衡且困惑度相当。

链接：https://arxiv.org/abs/2611.09252

机构：Umeå University（于默奥大学）

作者：Yikun Hou, Alp Yurtsever

英文摘要：Mixture-of-Experts (MoE) training is often not stationary: the data mixture changes at curriculum boundaries, when a model is continually pretrained into a new domain, or when the corpus is refreshed. Routing is learned against the current mixture, so each such change disrupts the per-expert load the router had converged to, and existing balancing methods have only been evaluated on stationary data. We rethink load balancing as a feedback control problem, in which the deviation of each expert's load from its fair share is the control error and the per-expert routing bias is the control input, and define a family of controllers, the PID-Balancer, from the proportional, integral, and derivative terms of classical PID control. Two widely used methods belong to this family: the auxiliary balancing loss behaves like a proportional controller, and the loss-free bias update is an integral controller acting on the sign of the error. Reading the router as a static map with a one-step delay, we show that the integral term is the only one that both removes persistent imbalance and averages out the step-to-step fluctuation of the measured load, whereas the proportional and derivative terms pass or amplify that fluctuation into the routing bias. We therefore adopt PID (I), the pure-integral member of the family with a single gain. Two settings are evaluated: (i) training an OLMoE backbone from scratch with 16 to 64 experts per layer, through a mid-run mixture switch, and (ii) continual pretraining of the released OLMoE-1B-7B on a new corpus. PID (I) holds balance before the shift and restores it more tightly afterwards than either the auxiliary loss or loss-free balancing, at comparable perplexity.

AI 总结：针对大模型训练内存受限问题，提出基于初始正向传播信息的近似激活重新计算方法，可仅重计算重要层组件，在Llama-488M模型上仅增少量困惑度即可减少计算量。

链接：https://arxiv.org/abs/2611.09614

作者：Danyal Ahmed (MLIA), Edouard Oyallon (MLIA)

英文摘要：Large Language Model training is increasingly constrained by memory capacity. Activation Checkpointing reduces activation memory by avoiding storing selected activations during the forward pass and rematerializing them during backpropagation, thereby trading memory savings for additional computation. Although this technique is essential for scaling model training, rematerialization can be prohibitively expensive, particularly for Transformer linear layers. Approximate computation could reduce this overhead, but conventional approaches either introduce errors that accumulate over the backward pass or fail to exploit information available from the initial forward pass. We introduce a novel approximate rematerialization method that can yield unbiased gradient estimates: using information collected during the initial forward pass, the method selectively recomputes only the most important layer components, either through greedy selection or randomized sketching. Ablation studies show that the resulting gradients closely match the exact gradients. When applied to feed-forward layers, attention layers, or both, our method can recompute only two-thirds of the layer components in a Llama-488M model, while increasing perplexity by just 1.7%, 1.2%, and 2.5%, respectively.

AI 总结：本研究针对近邻分类中全局度量无法适配区域特征差异的问题，提出EAML框架，通过遗传算法优化局部度量参数，在部分数据集上性能优于全局度量，明确了其适用条件与局限。

链接：https://arxiv.org/abs/2611.08549

机构：University of Maroua（马鲁阿大学）

作者：Isaac Touza

英文摘要： Nearest neighbour classifiers inherit the geometry of their distance function. Fixed distances and globally learned metrics apply the same geometry throughout the input space, although relevant feature directions may vary across regions. We propose EAML (Evolutionary Adaptive Metric Learning), a framework that learns instance-dependent positive-definite metrics through a low-dimensional parameterization. Each local metric combines an input-dependent diagonal scaling, generated by softmax interpolation between anchor points, with a global low-rank correlation component. A real-coded elitist genetic algorithm optimizes the parameters using a scalar objective combining leave-one-out prediction error, robustness, metric smoothness, and regularization. We establish positive definiteness, metric equivalence, existence of an optimal solution, and Lipschitz continuity of the metric field. We further investigate prediction stability, generalization bounds, and evolutionary convergence under explicit assumptions. Experiments on synthetic data with region-dependent feature relevance show that EAML can recover local metric variations and outperform global metrics. Evaluation on thirteen public datasets using nested 5-fold cross-validation reveals a more nuanced picture: EAML improves performance on selected datasets but does not significantly outperform global metric baselines overall. Additional experiments show that global diagonal metrics can be preferable under nuisance features and test-time noise. These findings identify the conditions under which evolutionary local metric learning is beneficial and highlight its practical limitations.

AI 总结：该研究针对稀疏自编码器（SAE）训练的激活缓存压缩，通过冻结SAE测试和重新训练测试分析压缩效果，提出校准方法，发现标准化通道可提升int4量化的特征保留率。

链接：https://arxiv.org/abs/2611.08551

机构：Stanford University（斯坦福大学）

作者：Abraham Yeung

英文摘要：To train a sparse autoencoder (SAE), you need a massive cache of model activations. We look into the effects that compression has on an SAE in two ways: we keep the original fp32-trained SAE and pass the compressed cache into the same SAE to see how many feature activations stay the same (the frozen-SAE test), and we retrain an SAE on the compressed cache and see how many of the original features still exist (the retraining test). We found that in the retraining test, there is no clear scale for retained features. On a GPT-2 cache, rounding everything to fp16 keeps 60.6% of features, but changing one value in a million by the smallest step fp32 allows (a change eight orders of magnitude smaller) keeps only 70.5%. Meanwhile, changing the random seed keeps 23.0%. For the frozen-SAE test, the frozen SAE's correlation with the original increases in order of how precise the codecs are, but plain $L_2$ distance gives nearly the same ordering. We also see the same frozen reading correspond to different percentages retained at different sites. This leaves the question of the right measurement. We build one by calibrating: retraining on identical bytes sets the ceiling, and a reseed sets the floor. We then measure the effect of each compressed codec against its own site's floor. With TopK SAEs on GPT-2 small and Pythia-1.4B at research-scale budgets, naïve per-token int4 loses more features than a reseed everywhere we tested, as do PCA and random projection on GPT-2. Standardizing each channel before quantizing brings int4 back above the floor in terms of retained features, at the same raw file size. At our smallest budget, a bf16 forward pass, which some pipelines use to save memory, loses slightly more features than rotated 8-bit storage. Calibrating a site costs four training runs and two evaluation passes.

AI 总结：该研究探讨交易策略是否需了解标的，基于微观结构不变性提出执行策略零样本迁移方法，通过纳斯达克等数据实验验证其泛化能力与成本表现。

链接：https://arxiv.org/abs/2611.08701

机构：University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）； University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）

作者：Hieu Tran, Hong Yu

英文摘要：Execution algorithms are calibrated asset by asset, because the queues, trade rates and bid-ask spreads they face differ by orders of magnitude across assets. For reinforcement learning this is zero-shot generalisation across contexts of very different scales, and microstructure invariance proposes a normalisation fixed by theory: measured in each asset's own units of time, size and price, markets look alike. In an exact order-by-order replay of public Nasdaq data, we train policies once, on 954 stocks in 2019, to choose between waiting in the queue and crossing the spread, and evaluate them unchanged on 1,964 unseen stocks in 2020-21, 2,629 stocks in 2025-26, crypto pairs and a second exchange. First, a policy that sees a stock only through its recent trade rate, trade size, spread and price increment (tick) costs within 0.015 spreads per share (a fifth of what learning saves) of a policy whose training data included the stock, and the stock's own history does not help it; it comes within a similar margin of policies trained on the second exchange when every episode counts equally, and within a wider one on crypto. Second, in mean cost before fees, invariant units beat raw units, z-scores and asset descriptors, but by under a basis point: most of their advantage is information and a common cost scale that a learner can also take as plain inputs, and none of the representations tested extrapolates to unseen spread regimes. Third, a near-zero transfer gap to a pooled comparator is weak evidence that a representation is right: we show that such a comparator detects only a small share of what a poor representation loses, and confirm it in synthetic markets and on pendulums.

AI 总结：该研究针对电商支付欺诈检测的删失训练问题，提出双流大语言模型引导奖励设计方法，在不增加推理成本的情况下，显著提升了欺诈检测的美元加权精度。

链接：https://arxiv.org/abs/2611.08706

机构：eBay（亿贝（eBay））

作者：Bo Qu, Zhurong Wang, Frank Zahradnik, Ming Ouyang

英文摘要： Production fraud-detection models learn from a censored slice of their own traffic: transactions a legacy system blocked never receive fraud labels, so models train on a biased, approved-only distribution. We extend LLM-guided reward design, the framework of Qu et al. (2025) in which an LLM evolves the reward of a two-step REINFORCE fraud-blocking policy, to attack this reject-inference problem inside the reward. A single LLM designs a dual-stream reward: stream 1 applies the standard dollar-weighted precision objective to labeled transactions; stream 2 scores legacy-blocked, unlabeled transactions by contrasting the newest gradient-boosted risk signal against the legacy scores that drove the original block. Rather than prescribe which signals matter, we expose a superset of evidence and let the LLM decide for itself which to use, guided by evaluation feedback alone; because it writes the reward as code, that choice is directly auditable. On a held-out four-month out-of-time test, the dual-stream agent beats the prior labeled-only agent at every target recall, by +4.7, +2.4 and +3.0 points of dollar-weighted precision at 80%, 85% and 90% recall, and the production baseline by +6.8 points on average. The resulting policy is architecturally identical to that of Qu et al. (2025) and adds no inference cost.

AI 总结：本研究针对无监督环境设计（UED），发现自适应课程下智能体存在训练相关病理，提出稳定学习者的干预方法，可提升长时性能与零样本泛化，确立学习者可训练性为UED的互补设计原则。

链接：https://arxiv.org/abs/2611.08787

机构：Mila – Québec AI Institute（米拉-魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； Google DeepMind（谷歌DeepMind）

作者：Johan Obando-Ceron, Walter Mayor, Michael Dennis, Aaron Courville, Pablo Samuel Castro

英文摘要：Unsupervised Environment Design (UED) approaches train reinforcement learning (RL) agents on diverse curricula that may evolve with their capabilities. While prior work has largely focused on how these curricula are constructed, we study whether their students remain trainable under the resulting distributions. Across multiple UED mechanisms, environment complexities, and extended training horizons, we identify recurring learner-side pathologies, including parameter growth, degraded value--outcome ordering, and loss of representational diversity, that accompany stagnation and performance degradation. These findings connect limitations in UED to optimization failures previously identified in conventional deep RL, while showing how adaptive curricula couple the learner's optimization state to its future training distribution. Controlled interventions show that mitigating selected pathologies improves learning. Stabilizing the learner improves long-horizon performance and zero-shot generalization without changing the curriculum rule or increasing environment interaction. Our results establish learner trainability as a complementary design principle for UED. Effective curricula require students that remain capable of learning from the distributions they produce.

AI 总结：该研究针对预算约束下的平台推广定向问题，提出DR-CATE-CBwK以行动为中心的因果多臂老虎机，结合双重鲁棒学习器与原始对偶控制器，在半合成基准上较最强奖励基线降约20%遗憾且预算合规。

链接：https://arxiv.org/abs/2611.08990

机构：LinkedIn Corporation（领英公司）

作者：Yifan Lin, Kaixu Yang, Di Mo

英文摘要：Web platforms select among costly interventions for each user to maximize incremental outcomes under a global budget. We formulate this problem as a budget-constrained contextual bandit with heterogeneous treatment effects. Although an action-independent outcome baseline cancels from treatment comparisons, modeling a nonlinear baseline can increase statistical complexity. We propose DR-CATE-CBwK, an action-centered causal bandit that directly learns treatment contrasts. Its online update remains valid under baseline-model misspecification without inverse-propensity weighting. It combines an offline doubly robust learner to warm-start treatment-effect estimates, an online action-centered estimator for sequential contrast learning, and a primal-dual controller with an affordable-action rule to enforce the effective-cost budget pathwise. For linear conditional average treatment effects (CATEs) in a stationary i.i.d. setting, we prove a high-probability (\widetilde{O}(Kd\sqrt{T})) regret bound, where K is the number of priced actions, d the context dimension, and T the horizon. We benchmark against the fluid linear program (LP) under the coverage-guaranteed action rule. We further show that the action-centered estimating moment remains unbiased under any predictable baseline estimate, whereas a specified separate-arm reward regression can exhibit asymptotic contrast bias under action-dependent logging and shared-baseline misspecification. On a semi-synthetic job-marketplace benchmark with real logged features and simulated outcomes, our practical Thompson-restricted variant achieves the lowest regret among evaluated budget-feasible methods in the operating regime. It reduces regret by approximately 20% versus the strongest reward-based baseline, outperforming raw-reward contextual bandits, BwK baselines, and a static offline policy, while never exceeding the effective-cost budget.

AI 总结：本文研究强化学习做市中损失函数的影响，发现对库存和现金管理的惩罚可提升策略韧性，强调算法交易中利润与风险平衡的重要性。

链接：https://arxiv.org/abs/2611.09012

作者：Siddharth Nand, Bora Guney

英文摘要：Market makers play a vital role in ensuring efficient trade within financial markets. Recent literature has delved into training market-making systems using reinforcement learning. This paper delves into the impact of various loss function formulations on risk management behavior within reinforcement-based market making. Through empirical evaluation, we contrast profit-maximizing strategies with risk-averse approaches, finding that penalties for inventory and cash management foster more resilient and adaptable market-making strategies. Our results underscore the significance of striking a balance between profit maximization and risk management in algorithmic trading, providing actionable insights for refining strategies in practical settings.

AI 总结：针对自动竞价策略的缺陷，提出TUGB框架，结合生成式序列建模与RL，经实验其在京东广告部署中表现优异，泛化能力强。

链接：https://arxiv.org/abs/2611.09091

作者：Luzhan Yuan, Chao Mi, Xiahao Shi, Yi Mao, Shengsheng Niu, Xin Zhu, Jie He, Zhangang Lin, Ching Law

英文摘要： Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance on unseen traffic. To address these challenges, we propose the Two-stage Uncertainty-aware Generative Auto-Bidding (TUGB) framework. TUGB integrates generative sequence modeling with Reinforcement Learning (RL). It employs a two-stage pipeline where a pre-trained Generative Bidding Model is fine-tuned via an ensemble-based Uncertainty-aware Environment Model. This approach quantifies epistemic uncertainty to penalize high-risk trajectories and evolves the policy from RTG-conditioning to direct bidding optimization. Extensive experiments demonstrate that TUGB significantly outperforms SOTA baselines. Notably, full-scale deployment on JD Search Ad achieved a 2.32\% increase in cost and 3.57\% in target cost, validating its industrial efficacy, while its successful adaptation to subsequent mechanism upgrades and JD Food Delivery Ad further validates TUGB's superior generalization capability.

AI 总结：提出SIFR方法，用有向优势替代奖励权重并约束速度漂移以稳定流模型训练，在SD3.5 Medium等模型上验证，性能优于现有方法且长期训练更稳定。

链接：https://arxiv.org/abs/2611.09175

作者：Runlong Liao, Xingqian Xu, Lizhang Chen, Baiyu Su, Yufan Huang, Zhonghao Wang, Akash Gokul, Ming-Yu Liu, Qiang Liu, Yogesh Balaji

英文摘要：Reward-based fine-tuning of flow models requires effectively promoting high-reward and suppressing low-reward samples, while maintaining training stability over many rounds of iterative updates. Iterative reward fine-tuning provides a simple starting point, but the positive reward weights give no explicit unfitting signal, and repeated reweighting concentrates the distribution and causes collapse. We propose Stable Signed Flow Reinforcement (SIFR), which replaces the reward weights by signed advantages to supply the missing unfitting signal, and constrains the velocity drift from a reference model to stabilize the updates, with a Lagrange multiplier that adapts the regularization strength to a prescribed drift budget. We further show that existing flow RL methods fall within this framework: they implicitly minimize the signed loss, differing in their regularization choices. We validate SIFR on SD3.5 Medium (2.5B) and FLUX.2 Klein (9B) and scale it to Cosmos 3 Super Text2Image (64B): across all 12 backbone--reward pairs with preference and rule-based rewards, it matches or exceeds existing methods, reaches their peak rewards much faster, and keeps improving over long training where they plateau or collapse.

AI 总结：本文针对安全强化学习的耦合控制问题，提出双时间尺度Q学习算法，结合风险敏感控制与平均代价控制，在GridWorld和CarGoal任务中验证了其安全最优控制的有效性。

链接：https://arxiv.org/abs/2611.09290

机构：Iowa State University（爱荷华州立大学）； Indian Institute of Technology, Bombay（印度理工学院孟买分校）

作者：Jiabin Lin, Shana Moothedath, Vivek S. Borkar

英文摘要：This paper investigates the coupled control problem within safety-focused reinforcement learning, addressing the essential challenge of achieving optimal performance while ensuring safety in systems operating within complex environments. We define safety as the requirement to prevent the system from reaching undesirable or hazardous states. We propose a coupled control approach that prioritizes safety by employing effective methods to prevent the system from entering unsafe states while optimizing the performance metric, defined as the average cost. We propose a novel problem transformation that reformulates it into a risk-sensitive problem combined with an average reward criterion. We present a two-timescale Q-learning algorithm where in the faster timescale, the algorithm solves a risk-sensitive control problem to ensure safety, while on a slower timescale, the algorithm focuses on average cost control. We provide theoretical guarantees for the convergence of our algorithms, establishing their significance in ensuring safe, optimal control in dynamic environments. We validated the performance of our approach using GridWorld and CarGoal task in Safety Gymnasium.

AI 总结：提出Dejavu方法，实现受限马尔可夫决策过程中强化学习策略的大概率安全仿真到真实迁移，经三个基准验证，其终身有效性由可求和失败概率保证。

链接：https://arxiv.org/abs/2611.09344

机构：University of Oxford（牛津大学）

作者：Rohan Tangri, Jan-Peter Calliess

英文摘要：We present Dejavu, a method that makes sim-to-real transfer of reinforcement learning policies in constrained Markov decision processes probably safe over an unbounded sequence of policy updates. An anytime valid test using per-decision importance sampling and a betting confidence sequence certifies each candidate trained in simulation before deployment using only trajectories collected by a safe baseline policy operating in production. Simulation quality does not affect the safety guarantee, only the production sample efficiency of the method. Finally, a summable per-test failure probability yields the lifetime valid property. Empirical results across three sim-to-real benchmarks support the theoretical work.

AI 总结：该研究针对演员-评论家方法忽略未来内生特征的问题，提出未来感知价值函数与对应算法，在噪声稀疏奖励环境中性能优于标准算法。

链接：https://arxiv.org/abs/2611.09417

机构：University of Liège（列日大学）； McGill University（麦吉尔大学）； Mila（米拉研究所）； École Polytechnique（巴黎综合理工学院）

作者：Samy Mokeddem, Gaspard Lambrechts, Adrien Bolland, Damien Ernst

英文摘要： Actor-critic methods optimize a parametrized policy using a critic to estimate their policy gradient. Recent work has shown that conditioning the critic on features of future states, actions, or rewards can improve sample efficiency and even final return. However, existing methods are restricted to exogenous features (independent of actions), overlooking endogenous features (dependent on actions) that may be crucial for credit assignment. We introduce the future-informed value function, which can be conditioned on both exogenous and endogenous features of future states, actions, and rewards. Then, we express the policy gradient using this value function, yielding the future-informed policy gradient. Building on that, we propose the future-informed actor-critic algorithm. Empirical results show that this algorithm leveraging endogenous features of the future outperforms standard actor-critic algorithms in environments with noisy and sparse rewards.

AI 总结：本研究针对带可验证奖励的强化学习（RLVR）提出基于奖励的熵分配（RCEA）框架，发现全局熵无法稳定反映推理性能，验证器失败轨迹的 token 熵更高，局部协方差可预测熵变化方向，为熵崩溃诊断提供了新方法。

链接：https://arxiv.org/abs/2611.09448

机构：School of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）

作者：Song Yu, Li Li, Zhenming Wu

英文摘要：Policy entropy is widely used to diagnose exploration and collapse in reinforcement learning with verifiable rewards (RLVR), yet its magnitude does not consistently track reasoning performance across optimization objectives. We argue that this ambiguity arises because global token entropy conflates uncertainty in successful and failed trajectories, diversity across correct solution strategies, and variation among realizations of the same strategy. We introduce \textbf{Reward-Conditioned Entropy Allocation (RCEA)}, a hierarchical diagnostic framework that separates complete-trajectory entropy from average token entropy, conditions uncertainty on verifier outcome and process validity, measures correct-solution-mode retention, and connects these population-level quantities to local covariance-driven updates. In controlled sweeps over six RLVR objectives at two model scales, entropy trajectories do not induce a stable ordering of reasoning accuracy. Token entropy is higher for verifier-failed than successful trajectories under both broad separately aggregated estimates and a common-question paired analysis, whose confidence intervals exclude equality at 10 of 12 displayed endpoints. A local covariance approximation predicts the direction of adjacent-checkpoint entropy change in 95.5\% of nonfailed transitions; a reward-stratified endpoint proxy further shows that positive chosen-token covariance is more tail-concentrated within failed prefixes. Every reportable trained endpoint exhibits some contraction in independently audited correct-solution-mode breadth, whose positive association with large-\(k\) coverage remains exploratory. These results show that entropy collapse should be diagnosed by which uncertainty is removed, rather than by global entropy alone.

AI 总结：本研究提出TT-MBRL方法，通过测试时梯度下降将回合观测记忆编码到世界模型参数，在Memory Maze基准达最优，且在非记忆基准仍保持性能，解决MBRL长期记忆难题。

链接：https://arxiv.org/abs/2611.09625

机构：University of Würzburg（维尔茨堡大学）

作者：Maxime Burchi, Fayaz Ali Dharejo, Radu Timofte

英文摘要：Model-based reinforcement learning (MBRL) approaches have demonstrated strong performance across diverse domains in recent years, learning accurate world models from agent trajectories. However, despite this progress, current approaches still struggle to surpass human performance on tasks that require long-term memory and planning. In this work, we address the problem of long-term memory in MBRL by moving beyond the commonly studied paradigm of architecture design. We introduce Test-Time Model-Based Reinforcement Learning (TT-MBRL), using gradient descent at test time to encode the memory of episode observations into world model parameters. This enables the agent to learn a distinct world model for each episode, improving memory capabilities compared to traditional approaches that solely rely on contextual memory. We first establish a proof of concept on a simplified two-dimensional variant of the Memory Maze environment, which we refer to as Memory Maze 2D, showing consistent improvements across different world model architectures. We then demonstrate the effectiveness of TT-MBRL in the 3D domain, achieving new state-of-the-art results on the Memory Maze benchmark. Finally, we show that TT-MBRL maintains strong performance on non-memory benchmarks such as DeepMind Control and Atari 100k.

AI 总结：本文针对ρ-可解码POMDP提出拟多项式时间近似规划算法，证明可解码性是弱于可观测性的统一假设，且最优可解码常数可多项式时间计算，为POMDP规划提供新的可行假设。

链接：https://arxiv.org/abs/2611.09778

机构：University of Cambridge（剑桥大学）； University of British Columbia（不列颠哥伦比亚大学）

作者：Oliver Dobson, Varun Jog, Chun Hei Michael Shiu

英文摘要：We study planning for finite-horizon partially observable Markov decision processes (POMDPs) with finite state, action, and observation spaces. Both exact and approximate planning are known to be computationally hard in this setting, so prior work has explored natural assumptions that make planning easier. Recent work [Golowich et al., 2022] gave quasipolynomial-time approximate planning algorithms for observable POMDPs. These are POMDPs whose observation channels satisfy an $\ell_1$-observability condition, but notably, no assumptions are required on the transition dynamics. In a similar vein, for every fixed $\rho>0$, we give quasipolynomial-time approximate planning algorithms for $\rho$-decodable POMDPs. We show that decodability is implied by both $\ell_1$- and $\ell_2$-observability and is strictly weaker than observability. Moreover, we show that the optimal decodability constant can be computed in polynomial time, whereas computing the optimal $\ell_1$-observability constant is NP-hard in the worst case. We also show that the fast filter-forgetting guarantee underlying the approach of [Golowich et al., 2022] does not extend directly from $\ell_1$-observability to constant $\ell_2$-observability. Thus, decodability is an easy-to-check, unifying assumption under which quasipolynomial-time approximate planning for POMDPs is possible.

AI 总结：本研究针对强化学习中的奖励黑客行为，引入三个Qwen3-4B的真实黑客环境，分析监控器的规避问题，提出改进监控器的方法，可降低奖励黑客率。

链接：https://arxiv.org/abs/2611.09828

机构：MATS； Google DeepMind（谷歌DeepMind）

作者：Aria Wong, Joshua Engels, Neel Nanda

英文摘要：Reinforcement learning (RL) rewards are notoriously difficult to design and control, often leading to the model learning unintended behaviors such as reward hacking. One potential solution is to monitor for reward hacking and penalize it when detected; however, training against a monitor could lead to evasive behavior, and our general understanding of how to apply monitors effectively during training is limited. To study how best to use monitors to mitigate reward hacking, we introduce and open source three realistic environments where Qwen3-4B reward hacks: a coding environment hackable via test overwriting, a medical chat environment hackable via sycophancy, and a biography generation environment hackable via hallucination. We first focus on the coding environment, where we find that: (1) models can learn to evade highly accurate monitors by exploiting systemic flaws in probes and LLM judges; (2) monitors that leak more learning signal during RL suppress reward hacking but are more often evaded; and (3) including easier problems in training can decrease reward hacking. We apply our findings to build better reward hacking monitors for the medical chat and biography generation environments that improve upon naive baselines to reduce reward hacking rates across seeds to before-training levels in some interventions. Our results demonstrate that our takeaways translate to new settings and that better monitor intervention designs are possible.

AI 总结：本研究针对安全关键数字孪生的缺失传感器重建问题，为HTTF开发稀疏传感器重建框架，评估多种模型，发现时空生成建模可有效提升重建性能，区域上下文DM在跨实验重建中表现最优。

链接：https://arxiv.org/abs/2611.08499

机构：University of Michigan（密歇根大学）； Idaho National Laboratory（爱达荷国家实验室）

作者：Umme Mahbuba Nabila, Linyu Lin, Majdi I. Radaideh

英文摘要：Accurate reconstruction of incomplete sensor fields is critical for state awareness in safety-critical digital twins (DTs). Thermocouples in high-temperature and radiation environments may drift, fail, or become intermittently unavailable, causing partial observability. This study develops a sparse-sensor reconstruction framework for Oregon State University's High Temperature Test Facility (HTTF) and evaluates six methods under intra- and inter-experiment protocols: three conditional generative models (i.e., a diffusion model [DM], variational autoencoder [VAE], and generative adversarial network [GAN]), two deterministic recurrent neural-network models, and ridge regression. For intra-experiment reconstruction within the PG{-}29 depressurized conduction cooldown (DCC) test, the models combine graph-based spatial encoding with gated recurrent units. The graph neural network (GNN)--gated recurrent unit (GRU) VAE achieves the lowest error, with a mean absolute error (MAE) of $11.73,^\circ$C, a root mean square error (RMSE) of $20.54,^\circ$C, and an $R^2$ of 0.98. The deterministic GNN--GRU and plain GRU obtain RMSE values of $25.26,^\circ$C and $35.22,^\circ$C, respectively, demonstrating the benefit of spatial modeling. All three generative models reduce RMSE by more than half compared with ridge regression. The DM maintains an $R^2$ of 0.94 when known sensors decrease from 91 to 45. For inter-experiment reconstruction, models trained on PG{-}27 pressurized conduction cooldown (PCC) are evaluated on PG{-}29 using section-context conditioning. The section-context DM achieves the best transfer performance, with an RMSE of $42.84,^\circ$C and an $R^2$ of 0.91. These results demonstrate the value of spatiotemporal generative modeling for missing-sensor reconstruction in safety-critical DT applications.

AI 总结：针对隐式图生成模型性能落后于离散模型的问题，提出与模型无关的隐变量重要性重加权（LIR）方法，通过解码器雅可比计算隐变量维度的重要性并加权，在基准数据集上提升性能并加快收敛。

链接：https://arxiv.org/abs/2611.08788

机构：University of Texas at Arlington（德克萨斯大学阿灵顿分校）； Michigan State University（密歇根州立大学）

作者：Biraaj Rout, Jay Revolinsky, Han Liu, Harry Shomer

英文摘要：Graph generation has shown tremendous effectiveness in modeling complex scientific tasks ranging from molecule generation to optimized circuit design. Most recent advancements have developed models that learn to denoise noisy graphs using either discrete diffusion or flow matching. However, discrete graph diffusion scales quadratically with the number of nodes, making it difficult to use such models on larger graphs. On the other hand, latent graph generation instead seeks to denoise noisy graph latents, which scale better to more nodes due to their lower dimension. However, in practice, latent graph generation models lag behind their discrete counterparts in performance. We study this problem, finding that it is caused by the unequal distribution of that different latent dimensions have on graph reconstruction. the impact. We observe that the vast majority of impact is contained in only a smaller number of latent dimensions. Since equal emphasis is placed on reconstructing the entire latent in the loss function, existing models are optimized to reconstruct information irrelevant to the downstream task. To tackle this problem, we propose Latent Importance Reweighting ({\bf LIR)} which weights each latent dimensions via it's importance to final graph reconstruction. Importance is calculated as the relative influence of a single latent unit on graph reconstruction, which is represented via the Jacobian of the decoder relative to the latent. Our method is model-agnostic and requires no additional model parameters or hyperparameters. Experiments show that LIR can boost performance and lead to faster training convergence when applied to two different autoencoders on various benchmark datasets. Code: this https URL

AI 总结：该研究推出DTCD工具库，可生成带真实因果结构的多变量时间序列，支持可控属性调整，构建基准揭示因果发现与处理效应估计方法的失败模式，为相关研究提供支撑

链接：https://arxiv.org/abs/2611.08918

机构：University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）

作者：Muhammad Hasan Ferdous, Md Osman Gani

英文摘要： Real-world multivariate time series rarely come with verified ground-truth causal structure, so research on time-series causal discovery and treatment-effect estimation depends on synthetic data. Existing tools are either fixed datasets that cannot be modified after release or script-based generators in which each script fixes one combination of mechanism, confounding, and missingness. Neither supports controlled experiments that vary a single property, such as sparsity, noise distribution, or missingness mechanism, while holding the others fixed. Counterfactual evaluation has the same gap, since existing simulators are built per paper with hardcoded mechanisms or produce observational data only. We introduce DTCD (Datasets and Toolkit for Causal Discovery), a data generation library that produces multivariate time series with ground-truth contemporaneous and lagged adjacency matrices. Topology, mechanism, noise, observational mask, and intervention policy are independent components that compose through configuration alone. Paired counterfactual twins, produced by caching the stochastic realization during the factual rollout and re-injecting it during the interventional rollout, recover individual treatment effects to numerical precision. A reference benchmark of eight discovery algorithms on eighty-one configurations and four treatment-effect estimators on eighteen configurations exposes failure modes that aggregate metrics hide. These include the inability of standard discovery methods to handle missing values, regardless of whether the missingness mechanism is informative, and a marginal-variance shortcut (varsortability) that we measure and remove by standardization. Code and data: this https URL

AI 总结：提出基于能量的推理器（EBRs），将循环更新转化为能量梯度下降，经探索式训练优化，在四个算法推理基准上优于现有模型，极端数独准确率达99.9%且推理计算量仅为次优模型的1/345，多解基准覆盖更优。

链接：https://arxiv.org/abs/2611.08977

机构：Duke University（杜克大学）； UIUC（伊利诺伊大学厄巴纳-香槟分校）； Harvard University（哈佛大学）

作者：William Xingxu Chen, Alexi Gladstone, Zeyu Michael Li, Heng Ji, Yilun Du

英文摘要：Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherently guided by an explicit measure of progress, making it difficult to determine when to stop looping and how to improve upon the current state. To enable this, we introduce Energy-Based Reasoners (EBRs), which learn an energy function over latent reasoning states and formulate looped updates as gradient descent on this energy. The energy scores latent states, while its gradient guides refinement and provides a signal for stopping. To train EBRs effectively, we further introduce exploration-based training to discover additional modes and to better shape the energy landscape over a broader set of states. Across four algorithmic reasoning benchmarks, EBRs match or outperform prior recurrent reasoning models, achieving 99.9% accuracy on Sudoku-Extreme while using 345$\times$ less inference compute than the next-best model and maintaining comparable training compute. On all multi-solution benchmarks, EBRs achieve state-of-the-art coverage of distinct valid solutions while maintaining near-100% single-sample accuracy. These results suggest that energy-based models are a promising approach for strong reasoning performance.

AI 总结：提出SensDiff框架，将符号规则集成到扩散模型中，通过序列约束引导3D分子生成，提升化学有效性且符合物理化学规则。

链接：https://arxiv.org/abs/2611.09142

机构：The Hong Kong Polytechnic University（香港理工大学）

作者：Zhuoran Li, Xu Sun, Chang Wen Chen, Wanyu Lin

英文摘要：Diffusion models have recently emerged as a powerful paradigm for generating 3D molecules. Despite showing remarkable promise, they learn atomic distributions implicitly from data, without explicitly encoding physicochemical rules into their generative dynamics. Consequently, generated samples can be statistically plausible yet chemically invalid. To address this problem, we propose Sequential Neuro-Symbolic Constrained Diffusion (SensDiff), a framework that integrates symbolic rules into generative modeling, enabling the model to internalize scientific priors during training. Central to SensDiff is the observation that the diffusion trajectory of 3D molecule generation exhibits a coarse-to-fine evolution: valid molecules arise by first mitigating macroscopic geometric conflicts and then refining structures toward microscopic chemical consistency through iterative denoising. Accordingly, SensDiff mirrors this dynamic by sequentially enforcing constraints with adaptive weighting during training, progressively steering generation toward valid molecular geometries. Moreover, SensDiff translates domain knowledge into interpretable generative controls, grounding opaque neural denoising in scientific principles. Experiments on molecular benchmarks and real-world constrained generation tasks confirm that SensDiff consistently improves chemical validity while adhering to physicochemical rules and user-specified targets. The code is publicly available at this https URL.

AI 总结：该研究针对图高斯过程的异构网络建模问题，提出方差耦合高斯过程（VCGPs），通过学习耦合指数调节图交互，在多类数据集上验证了其预测与不确定性估计的竞争力。

链接：https://arxiv.org/abs/2611.09247

机构：Brevan Howard Centre for Financial Analysis（布赖文·霍华德金融分析中心）； Imperial Business School（帝国理工商学院）； School of Informatics（信息学院）； University of Edinburgh（爱丁堡大学）

作者：K. S. Sesh Kumar, Viacheslav Borovitskiy

英文摘要： Gaussian processes on graphs provide a principled framework for prediction and uncertainty estimation, but modelling heterogeneous networks often requires balancing flexibility against parameter complexity. Variability at a node may reflect useful signal that should propagate through the network, unreliable measurements whose influence should be suppressed, or a mixture of both. We introduce Variance-Coupled Gaussian Processes (VCGPs), which use a positive auxiliary signal to modulate graph interactions through a single learned coupling exponent. The exponent controls how strongly high-variability nodes propagate or attenuate information, while a cluster-wise extension accommodates different regimes within the same graph. Under stated structural assumptions, we characterize the unique stationary-rescaling point of the basic family, where correlations match those of a stationary graph kernel while node-dependent variances remain. Experiments on traffic, air-quality and weather datasets show competitive prediction and uncertainty estimation relative to stationary and per-node non-stationary baselines, with the largest gains on networks requiring multiple coupling regimes. Stationary correlations after variance rescaling remain sufficient on some data, and performance depends on the auxiliary signal and model selection.

AI 总结：本研究提出DiffusionRef-IMU两阶段跨位置平移框架，通过引导锚定残差扩散细化目标信号差异，在多组实验中优于基线模型，实现了质量与计算效率的良好权衡，同时明确了零样本外部迁移的局限性。

链接：https://arxiv.org/abs/2611.09323

机构：American International University-Bangladesh (AIUB)（孟加拉国美国国际大学）； Mälardalen University（梅拉达伦大学）

作者：M. M. Golam Hafiz, Safia Akter Simi, Md. Rakibul Islam, M. F. Mridha

英文摘要：Cross-location variation in wearable inertial measurement unit (IMU) signals complicates learning when measurements from a desired target body location are unavailable. This study proposes DiffusionRef-IMU, a two-stage cross-location translation framework in which a deterministic Direct network first estimates the target signal and a guide-anchored residual diffusion model refines only the remaining target discrepancy. The evaluation comprises five subject-disjoint activity-location composition-held-out folds, capacity-matched deterministic and flow-based residual baselines, source-only activity conditioning, computational ablation, and true zero-shot evaluation on two independent datasets. DiffusionRef-IMU with 16-step deterministic DDIM achieved a mean nRMSE of 0.087538 +/- 0.004922, compared with 0.090262 for Direct, 0.088847 for deterministic residual refinement, and 0.088417 for eight-step CompFlow, and outperformed each baseline in all five folds. Four-step DDIM retained a mean nRMSE of 0.087820 at 47.62 ms per window, providing a favourable quality-computation trade-off. Replacing ground-truth activity conditioning with a source-only activity predictor (macro-F1 0.8473) increased 16-step DiffusionRef nRMSE only to 0.088190. True zero-shot evaluation produced mixed results: DiffusionRef was marginally favourable on Grouvel2025 but remained worse than Direct on Saldaña2025. Overall, guide-anchored residual diffusion improves controlled cross-location reconstruction while revealing clear limits in zero-shot external transfer.

AI 总结：该研究针对跨不完整队列的临床数据，提出因果图融合与表格基础模型的因果引导方法，在缺失数据处理、分布偏移下的判别性能及临床预测上均取得优于基线的结果。

链接：https://arxiv.org/abs/2611.09400

机构：ETH Zürich（苏黎世联邦理工学院）； Swiss Paraplegic Research（瑞士截瘫研究中心）； Università degli Studi di Milano-Bicocca（米兰比可卡大学）； Swiss Paraplegic Center（瑞士截瘫中心）； Balgrist University Hospital（巴尔格里斯特大学医院）； Tohoku University（东北大学）

作者：Yanke Li, Dhiyaa Al Jorf, Ayoube Ighissou, Anke Scheel-Sailer, Robert Riener, Diego Paez-Granados

英文摘要：Clinical data are split across incomplete cohorts with partially overlapping variables. Causal discovery under missing data and multi-source integration have developed separately, and tabular foundation models cannot take a causal graph without retraining. We make two contributions. First, causal graph fusion learns a partial ancestral graph on the shared variables, fuses it into each cohort's graph under temporal background knowledge and lets Markov blankets guide re-imputation, so missing data are handled inside discovery. Second, causal attention steering compiles the learned graph into the attention of a frozen tabular foundation model at inference. Against known ground truth, fusion dominates pooled and per-cohort baselines in every missingness and heterogeneity condition tested (p<0.001), and steering improves discrimination under distribution shift (p<10^{-5}), a gain that a random graph does not produce. In two spinal cord injury cohorts, fusion orients age, albumin and hemoglobin as ancestors of length of stay, a set no single cohort orients in full, and yields compact, temporally ordered predictor sets that match or exceed automatic feature selection on four of five outcomes.

AI 总结：本文提出DISCO方法，规避时间相关分数场需求，仅估计单个分数，可精确采样任意条件，样本质量与扩散模型相当，且表示更忠实，优于启发式采样器。

链接：https://arxiv.org/abs/2611.09758

机构：TU Graz（格拉茨工业大学）； Graz Center for Machine Learning (GraML)（格拉茨机器学习中心（GraML））

作者：Thomas Wedenig, Robert Peharz

英文摘要：The success of modern score-based generative models is largely driven by diffusion-based training, which learns a collection of time-indexed score fields corresponding to progressively noisier versions of the data distribution. While such models achieve impressive sample quality, leveraging them for sound probabilistic inference---particularly sampling from arbitrary conditionals of the model---remains challenging. This difficulty arises because conditioning information is only available for clean data and not for the higher noise levels required to generate exact conditional samples. In this paper, we introduce DIffusion-free SCOre matching (DISCO), a principled approach that sidesteps the need for time-dependent score fields altogether. Our method is based on an objective that, while reminiscent of diffusion-based training, estimates only a single score of the (slightly perturbed) data distribution, for which the exact conditional score is readily obtained. In experiments, DISCO is competitive with state-of-the-art diffusion models in terms of sample quality. More importantly, DISCO yields a more faithful representation of the underlying data distribution and---crucially---enables accurate sampling from arbitrary conditionals, outperforming standard heuristic samplers. This capability opens the door to principled and flexible probabilistic reasoning with score-based models.

AI 总结：该研究揭示十亿参数神经网络的优化轨迹受低维拓扑约束，提出拓扑自适应优化算法，使ImageNet训练时间减少14.1%，验证于80多种架构。

链接：https://arxiv.org/abs/2611.08502

机构：Imaginary Space Laboratory, IMSLAB（Imaginary Space实验室，IMSLAB）

作者：Dongqing Cao

英文摘要：The remarkable generalization of modern over-parameterized neural networks defies classical statistical learning bounds. Here we establish that optimization trajectories in billion-parameter models do not sample the ambient dimension $\mathbb{R}^N$ homogeneously; instead, they are dynamically constrained to a low-dimensional execution submanifold $\mathcal{M}_{\text{exec}}$ (with empirically observed effective dimension $d_{\text{eff}} \le 12$). By equipping the parameter space with a regularized Hessian metric $g_{ij} = \nabla_i \nabla_j L + \epsilon \delta_{ij}$ and analyzing stochastic Langevin diffusion on loss sublevel sets, we derive a rigorous Topological Generalization Bound grounded in projected subspace persistent homology. Furthermore, by linking Morse index transitions to Betti number annihilation ($\beta_1 \to 0$), we formulate an exact mathematical mechanism for exponential escape from strict saddles under anisotropic noise. We validate our framework across 80+ architectures (ResNets, Vision Transformers, and 7B LLMs). To bridge theoretical topology with computational feasibility, we resolve the curse of dimensionality by computing projected persistent homology proxies via randomized Lanczos iterations restricted strictly within active Hessian subspaces. Building upon this mathematical foundation, we introduce Topological-Adaptive Optimization (Top-SGD and Top-AdamW)---a family of wrapper algorithms that dynamically modulate learning rates using active curvature signatures. Extensive benchmarks demonstrate a 14.1\% reduction in total wall-clock training time on ImageNet with all computational and memory overheads fully accounted for. Code is publicly available at this https URL.

AI 总结：本论文提出一种新型退化高斯后验分布及两种高效算法，解决贝叶斯方法的计算权衡问题，实现大型模型的最优置信度校准与分布外检测，还为过参数化模型学习提供理论支撑。

链接：https://arxiv.org/abs/2611.08997

机构：Technical University of Denmark（丹麦技术大学）； Riken Institute（理化学研究所）； Amazon AWS（亚马逊云科技）； New York University（纽约大学）； University of Technology Nuremberg（纽伦堡工业大学）

作者：Marco Miani

英文摘要：A primary limitation of modern deep learning is the miscalibration of model confidence; traditional architectures fundamentally lack a mechanism to quantify their own uncertainty. Larger models and larger datasets mitigate this issue, but they do not resolve the underlying structural deficiency. Bayesian methods offer a principled uncertainty-aware learning framework through stochastic parameters. Yet, despite the established benefits, the inherent computational overhead often compromises either scalability or quality. This trade-off currently prevents the widespread adoption of Bayesian methods. This Thesis bridges the gap between high-quality and low-complexity by introducing a novel distribution on parameter space: a degenerate Gaussian whose covariance is a projection matrix aligned with the null space of the Fisher information matrix. We demonstrate the scalability of this Bayesian posterior through two numerically efficient algorithms: one for posterior sampling and another for the direct computation of predictive confidence. Empirically, we show State-Of-The-Art confidence calibration and out-of-distribution detection for large models. We provide theoretical grounding for this approach. We study the degeneracies inherent in Amari's information geometry and highlight its most relevant component: the split of parameter's perturbations into two orthogonal subspaces. From this perspective, our posterior naturally emerges as the simplest choice that captures this split, assigning unitary variance to one subspace and zero variance to the other. Moreover, through the tools of differential geometry, we utilize this split to identify and rectify a critical misalignment issue of the non-linearized Laplace Approximation. Finally, with a focus on PAC-Bayes generalization bounds, we pave the way for a deeper understanding of the learning capabilities of overparametrized models.

AI 总结：本综述从统计物理视角，整合平均场理论等概念与方法，阐释宽网络分析等深度学习进展，构建统一物理框架，桥接梯度优化的确定性与随机 regime，以深化对深度学习理论的理解。

链接：https://arxiv.org/abs/2611.09138

机构：RIKEN Center for Advanced Intelligence Project (AIP)（理化学研究所先进智能中心）； The Institute of Statistical Mathematics（统计数学研究所）； University of Science and Technology of China（中国科学技术大学）

作者：Wei Huang, Youjin Deng

英文摘要：The recent success of foundation models and deep learning has far outpaced our theoretical understanding of how large-scale neural networks learn and generalize. Statistical physics provides a natural language for describing such high-dimensional, nonlinear, and strongly coupled systems, offering concepts such as mean-field theory, phase transitions, energy landscapes, and stochastic dynamics. In this topical review, we adopt a statistical-physics way of thinking -- from concepts including phases and criticality, and free-energy viewpoints, to methods such as kernel and Gaussian-process limits, mean-field and dynamical mean-field theories, random-matrix tools, and Fokker-Planck formalisms, and to a mindset emphasizing universality, scaling, and tractable limits with explicit validity regimes. We survey recent progress on understanding modern deep learning through this lens, including mean-field analyses of wide networks, spectral and geometric perspectives on loss landscapes, stochastic-gradient-based training viewed as a dynamical process, and phase-transition analogies that organize phenomena such as overparameterization, generalization, and representation change. Our goal is to synthesize these threads into a coherent framework that clarifies what each approximation explains, when it is expected to hold, and how apparently competing narratives relate or diverge. Together, these perspectives form a unified physical framework that views representation learning as a collective phenomenon in high-dimensional systems, bridging deterministic and stochastic regimes of gradient-based optimization.

AI 总结：本文针对衰落信道下的语义通信问题，提出TOFS特征选择框架，通过接收端分类损失提供监督，在CIFAR-10仿真中较SOTA方法提升了分类精度。

链接：https://arxiv.org/abs/2611.09173

机构：Graduate School of System Informatics, Kobe University（神户大学系统 informatics 研究生院）； Information Technology Center, Nara Women’s University（奈良女子大学信息技术中心）

作者：Zhiyi Zhu, Eiji Takimoto, Patrick Finnerty, Chikara Ohta

英文摘要： Task-oriented semantic communication transmits task-relevant features to support receiver inference under limited communication resources and adverse channel conditions. For image classification, the usefulness of a feature depends on the other transmitted features and the distortion introduced by the wireless channel. Effective feature prioritization should therefore account for classification performance after transmission of the selected features. This paper proposes a Task-Oriented Feature Selection (\textit{TOFS}) framework and method, which evaluates feature replacements using receiver classification loss. Loss differences confirmed under independent transmission samples provide pairwise ranking supervision for a selector network. The trained selector predicts priorities in a single forward pass. CIFAR-10 simulations demonstrate improved classification accuracy over an importance-based feature selection baseline at the same transmitted feature count and average transmit power. The proposed \textit{TOFS} framework shows 84\% accuracy performance under Rayleigh fading and Gaussian noise, compared with the 68\% performance of a SOTA method.

AI 总结：该研究在边际非均匀学习框架下，通过提出非中心DS规避维数，刻画了多分类问题最优学习率的三分法，其分布耗尽引理或具独立研究价值。

链接：https://arxiv.org/abs/2611.09543

机构：Apple（苹果公司）； Purdue University（普渡大学）； University of Tübingen（蒂宾根大学）； Tübingen AI Center（蒂宾根人工智能中心）； Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）

作者：Nataly Brukhim, Steve Hanneke, Amirreza Shaeiri, Maximilian Thiessen

英文摘要：We study the problem of multiclass classification within the framework of marginal-nonuniform learning, where the constants in the learning rate may depend on the unknown marginal distribution generating the unlabeled data, but not on the target concept. This notion naturally lies between classical PAC learning, where the constants are independent of both the marginal distribution and the target concept, and more recent universal learning, where the constants may depend on both. We give a complete characterization of the optimal marginal-nonuniform learning rates, establishing a fundamental trichotomy: exponential, linear, and arbitrarily slow rates. This characterization is witnessed by a new combinatorial dimension, termed the uncentered DS-eluder dimension. A key ingredient in the upper-bound proofs is a set of new distributional exhaustion lemmas that exploit the sequential nature of this dimension and may be of independent interest.

AI 总结：本文针对双隐藏层的多尺度单索引模型，分析在线球形SGD的MSE动力学，证明其可从随机初始化出发，经特定样本量实现弱、强恢复，为分层特征学习提供了可处理的研究场景。

链接：https://arxiv.org/abs/2611.09682

机构：New York University（纽约大学）

作者：Gordon Dai, Joan Bruna

英文摘要：We consider the Multiscale Single-Index Model (MSIM), first introduced by Oymak and Soltanolkotabi (2021), as a stylized model for hierarchical feature learning with scale separation. Each layer extracts a shared single-index feature at one physical scale and passes it to the next, giving a tractable setting in which to study how deep architectures learn local multiscale representations. Under non-degeneracy and delocalization assumptions on the link function and planted features respectively, for the two hidden-layer case ($K=2$), we analyze joint online spherical SGD under MSE loss, which is a canonical regression objective, in discrete time and show that it achieves weak recovery from random initialization in $O(d\log^2 d)$ samples, followed by strong recovery to accuracy $\varepsilon$ in $O(d\log(1/\varepsilon))$ additional samples. The main technical challenge arises from the non-Gaussian learned features observed by the second layer. We address this challenge through a quantitative Gaussian comparison using delocalization, combined with sharp trajectory-level control of the coupled SGD dynamics. This work is a companion to Bruna (2026, arXiv:2607.03347 ), which studies recovery under a correlation objective for general $K$.

AI 总结：该研究提出一种不动点加速方法，将概率测度表示为参考分布经神经网络映射的推前，利用黎曼Anderson混合加速自然梯度迭代，在多类机器学习任务上提升了参数化Wasserstein方法的训练效率。

链接：https://arxiv.org/abs/2611.09723

机构：Weierstrass Institute for Applied Analysis and Stochastics (WIAS)（魏尔斯特拉斯应用分析与随机学研究所）； Georgia Institute of Technology（佐治亚理工学院）

作者：Vitalii Aksenov, Sebastian Gutierrez Hernandez

英文摘要：We propose a fixed-point acceleration method for optimization over probability measures, applicable to a variety of machine learning problems. We represent probability measures as pushforwards of a reference distribution through a neural network map and equip the parameter space with the induced pullback Wasserstein metric. This geometric structure allows natural gradient descent to be interpreted as a fixed-point iteration on a Riemannian manifold. We accelerate this iteration using Riemannian Anderson mixing method, which exploits historical residuals to capture approximate second-order information without forming Hessians. In the present parametric setting, the manifold is represented by Euclidean coordinates endowed with a point-dependent metric, simplifying retraction and vector transport. We evaluate the method on multimodal sampling, PDE-based inverse problems, aggregation dynamics, Bayesian logistic regression, and generative modeling. Across the tested tasks, Anderson mixing reduces the number of natural-gradient iterations and achieves competitive performance relative to SGD and Adam in terms of both loss-gradient evaluations and wall-clock time. These results suggest that fixed-point acceleration is an efficient tool for improving the computational efficiency of training on parametric Wasserstein methods.

AI 总结：本文将算法无关的PAC界扩展至动力系统，通过建立神谕不等式推导线性与双线性系统参数估计的有限样本界，并分析其速率与经典渐近结果的对比。

链接：https://arxiv.org/abs/2611.09767

机构：Aalborg University（奥尔堡大学）； Institute for Computer Science and Control, HUN-REN SZTAKI（HUN-REN SZTAKI计算机科学与控制研究所）

作者： Mihaly Petreczky, John Leth, Emma Lukacs, Balint Daroczy

英文摘要：Probably Approximately Correct (PAC) bounds on the generalization error (the difference between the empirical prediction error computed on the training data and its expectation) are an established tool in statistical machine learning, and there have been several extensions of these bounds to dynamical systems. In parallel, in recent years, there has been growing interest in finite-sample bounds for parameter estimation error in system identification. The latter bounds tend to be algorithm-specific, relying on reformulating the identification algorithm as a least-squares regression problem. This is in contrast to classical PAC bounds, which are algorithm-agnostic and can be applied to any identification algorithm based on minimizing a cost function involving the empirical loss. In this paper, we show how oracle bounds derived from PAC bounds can be used to derive finite-sample bounds for dynamical systems. As an illustration of this approach, we present finite-sample parameter-estimation bounds for linear and bilinear systems with bounded inputs and noise. These bounds apply to identification algorithms based on minimizing a regularized empirical loss function. The key ingredient is to establish an oracle inequality, i.e., an inequality between the true prediction error of the learned model and the minimum achievable true prediction error, and then use either the convexity of the true loss or system-theoretic properties of the loss function to derive bounds on the parameter estimation error. We also analyze the rates of the obtained bounds and compare them with those of classical asymptotic results.

AI 总结：本文提出新框架MEDALLION，通过知识蒸馏和神经特征归因解释低维嵌入，经MNIST实验和单细胞转录组学应用验证，其特征归因可提供额外见解，性能优于部分现有方法。

链接：https://arxiv.org/abs/2611.08767

机构：Columbia University（哥伦比亚大学）； University of Florida（佛罗里达大学）

作者：Vicky Jung, Claire M. He, Irene Chang, Genevera I. Allen

英文摘要：Dimensionality reduction is widely used to visualize high-dimensional data and guide scientific discovery, yet interpreting which original features contribute to low-dimensional representations remains challenging, particularly for black-box methods such as t-SNE and UMAP. We introduce \textbf{MEDALLION} (Manifold Embedding Distillation and Attributions for Low-dimensional Latent InterpretatiON), a novel framework for interpreting low-dimensional embeddings through knowledge distillation and neural feature attribution. MEDALLION distills any given embedding with a neural encoder which we explain via a broad range of existing neural feature attribution methods. Through experiments on MNIST and applications in single-cell transcriptomics, we show MEDALLION provides informative feature attributions that cast additional insights into the underlying embedding and compare its performance with existing interpretability approaches.

AI 总结：针对低秩内存高效优化器在量化感知训练（QAT）中性能下降的问题，提出ResQAdam优化器，通过保留BF16动量、仅对主子空间坐标应用Adam并添加残差符号更新，在大幅减少内存占用的同时保持接近AdamW的性能，吞吐量损失极小。

链接：https://arxiv.org/abs/2611.08924

机构：Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）； King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）； Advanced Micro Devices, Inc. (AMD)（超威半导体公司）； Carnegie Mellon University (CMU)（卡内基梅隆大学）

作者：Liqun Ma, Shengkun Tang, Liangyu Wang, Lin Zhao, Wei Luo, Xinjun Niu, Spandan Tiwari, Ashish Sirasao, Kun Zhang, Zhiqiang Shen

英文摘要：Quantization-aware training (QAT) is the most reliable way to obtain accurate low-bit large language models (LLMs), but training with AdamW keeps two dense FP32 states for every weight matrix. We find that low-rank memory-efficient optimizers such as GaLore and LDAdam degrade substantially in QAT. A considerable part of the QAT momentum lies outside its top-r singular subspace, and projection-based methods discard this part at every step. We further observe that this residual remains useful when only its sign is kept. Based on these observations, we propose ResQAdam. It keeps a single BF16 momentum, applies Adam only to the r x r coordinates of the principal subspace, and adds a normalized sign update computed from the residual. We evaluate ResQAdam with two from-scratch QAT methods and three QAT fine-tuning pipelines, with weights quantized down to 2 bits. It reduces optimizer-state memory by 71% to 74% relative to AdamW, stays close to AdamW in most settings, and lowers training throughput by less than 2%.

AI 总结：本文提出将多层感知机的知识蒸馏至可微逻辑网络，通过四种变体在20个表格分类任务上提升了DLN的平衡类精度，最高达15%，且保留其原有优势。

链接：https://arxiv.org/abs/2611.09024

机构：Princeton University（普林斯顿大学）

作者：Hee Yun Suh, Niraj K. Jha

英文摘要：Differentiable logic networks (DLNs) are interpretable, edge-friendly classifiers that learn both their logic operators and their connections through gradient descent, achieving accuracy competitive with multi-layer perceptrons at orders-of-magnitude lower inference cost. Their accuracy, however, is bounded by the problems of vanishing gradients, scalability, and lack of an ecosystem, leaving a gap relative to conventional neural networks on several datasets. We introduce knowledge distillation for DLNs to narrow this gap. We distill from a trained multi-layer perceptron teacher into a DLN student, integrating the distillation objective into a two-phase training loop without altering the architecture or the inference procedure. The teacher is discarded after training. Hence, the distilled model retains the interpretability, sparsity, and inference cost of a conventionally trained DLN. We investigate this approach through four variants: a joint hyperparameter search that optimizes the distillation weight and temperature alongside the architecture, a grid search over these two hyperparameters with the architecture fixed, and two single-phase variants that employ distillation during only the neuron-function or only the connection phase. On 20 public tabular classification tasks, distillation improves balanced-class accuracy at negligible cost to gate-level operation counts and model size, though the benefit varies by dataset. Performance improvements of up to 15% are observed, in some cases surpassing the teacher itself.

AI 总结：本文针对大语言模型资源需求高难以部署到边缘设备的问题，综述了助力其部署的最新软件优化与专用硬件技术，明确了边缘部署的优势，为从业者提供相关部署技术参考。

链接：https://arxiv.org/abs/2611.09075

机构：meta

作者：Rahul Maliakkal, Yashasvi Makin, Plawan Rath, Rohit Jain, Ankur Sadhoo

英文摘要：Large Language Models (LLMs) have transformed many areas of artificial intelligence (AI), but their substantial resource requirements limit their deployment on mobile and edge devices. Although LLMs have demonstrated impressive capabilities in various applications, the next challenge is deploying these models on resource-limited edge devices. Recent innovations in software optimizations and specialized hardware have made it feasible to deploy LLMs on edge devices. Edge deployment offers benefits including local data processing, cost savings, reduced latency, and personalized responses. This paper reviews the latest techniques that make the deployment of LLMs on edge devices feasible.

AI 总结：MINE是一种无损熵编码方法，通过核心方案dtANS-LLM适配LLM推理，集成到vLLM作为插件，在两款GPU上针对特定Llama模型实现了显著推理加速。

链接：https://arxiv.org/abs/2611.09424

机构：ETH Zurich（苏黎世联邦理工学院）

作者：Emil Schätzle, Markus Püschel

英文摘要：We present MINE (Memory-efficient INference Engine), a lossless entropy coding approach that accelerates single-stream inference of Large Language Models (LLMs), where existing lossless compression methods yield speedups only for specific data types such as \texttt{BF16} and under additional assumptions. Single-stream decoding is strongly memory-bound, since every weight must be streamed from memory once per generated token and requests cannot be batched in local or low-latency deployments. At the core of MINE is dtANS-LLM, a GPU entropy coding scheme adapted from the prior dtANS to the needs of LLM inference. It exploits the non-uniform distribution of weights, which persists even after quantization, and exposes hyper-parameters that trade compression ratio against decoding cost. We auto-tune these parameters for each tensor and GPU to obtain the Pareto front between model size and decoding latency. MINE integrates into vLLM as a plugin and selects the best kernel configuration for a given memory budget. On Llama~3.1~8B~Instruct with a 2.1-bit EntQuant checkpoint, MINE achieves speedups of 2.52$\times$ and 1.48$\times$ over the fastest baseline on an RTX~4060~Ti and an RTX~5090, at effective bitrates of 2.24 and 3.43~bits per weight. MINE is available as open source.

AI 总结：提出Transformer-FSQ，用有限标量量化瓶颈替换KV缓存的标准键值投影，在12×至97.5×极端压缩比下，于长上下文检索任务中较基线更准确，解码吞吐量接近原生SDPA注意力，可扩展固定设备的上下文容纳量。

链接：https://arxiv.org/abs/2611.09598

作者：Andras Szecsenyi, Thomas L. Lee, Vaisakh Shaj, Elliot J. Crowley, Amos Storkey

英文摘要：Private, personalised language models must run on local consumer devices, where large, frontier models cannot fit, and retaining long contexts is non-trivial. Sequential memory---the key-value (KV) cache---grows linearly with context length, quickly dwarfing the model itself: for Qwen3-1.7B-Base, 200,000 retained entries require 21 GiB, 6.6 times more than the model weights. Yet the KV-cache compression methods we measured fail beyond moderate compression ratios. We introduce Transformer-FSQ, addressing extreme KV-cache compression by replacing standard key and value projections with a finite scalar quantisation bottleneck. Our cache stores a packed vector of discrete integer codes per token, with no per-token quantisation metadata. Converting a pretrained transformer trains only these projections on 0.25 tokens per original parameter. We evaluate Transformer-FSQ against five baseline families on models from 0.6B to 8B parameters. On long-context retrieval (RULER), from 12$\times$ to 97.5$\times$ Transformer-FSQ is the most accurate method we evaluate, across scales. A fused Triton kernel decodes directly from the integer codes; with baselines given their authors' kernels where available, it decodes at $1.01\times$ (95% interval $0.98$--$1.05$) the throughput of native SDPA attention on the uncompressed Qwen3-8B-Base at $32\times$ and $1.54\times$ at $97.5\times$. Extreme KV-cache compression is therefore a practical way to extend how much context a fixed device can hold.

AI 总结：本研究提出首个无约束线性回归的持续差分隐私机制ContinualAdaSSP，给出盒约束线性回归的差分隐私下界，实验显示其精度优于现有机制。

链接：https://arxiv.org/abs/2611.08737

机构：Institute of Science and Technology Austria (ISTA)（奥地利科学技术研究所）

作者：Bardiya Aryanfard, Monika Henzinger, Farhood Rostamkhani

英文摘要： We study the classic least-squares linear regression problem under differential privacy (DP) in the batch and the continual observation setting. In the latter setting, the mechanism receives a stream of $n$ data points $(x_i,y_i)$ ($x_i\in\mathbb{R}^d$ and $y_i\in\mathbb{R}$) and must output an estimate of the optimal parameters at each time step $i$. Although differentially private linear regression has been extensively studied in the batch setting, the problem remains underexplored for the continual setting, with prior work being restricted to constrained linear regression and update time polynomial in $n$. In this work, we introduce ContinualAdaSSP, the first mechanism for unconstrained linear regression under continual differential privacy. Our mechanism's suboptimality gap is proportional to $\sqrt{d}\operatorname{polylog}(n)$. It requires $O(d^2\log{n})$ space and $O(d^2\log{n}+d^{\omega})$ update time, where $d$ is the dimension of the input space. We also study fundamental limits of differentially private linear regression by showing the first lower bounds for the box-constrained least-squares linear regression problem. Our lower bounds are proportional to $\min(n,\frac{\sqrt{d}}{\log^{1.5}d})$ for $(1,O(\frac{1}{n}))$-DP, and $\min(n,\frac{d}{\epsilon})$ for $\epsilon$-DP, and are derived using a reduction from a fingerprinting code problem from [Peter et al., 2024], providing new insights into the inherent hardness of this canonical task. Our experimental evaluation on real-world datasets shows that the accuracy of our continual observation mechanism clearly outperforms any other known differentially private mechanism for this problem such as rerunning the batch algorithm at each time step.

AI 总结：该研究针对联邦学习的通信开销问题，提出以多样性为导向的客户端选择策略，可在非IID数据下实现通信节省并提升模型泛化性能，使通信效率与模型质量互补。

链接：https://arxiv.org/abs/2611.09278

机构：RISE Research Institutes of Sweden（瑞典RISE研究院）； KTH Royal Institute of Technology（瑞典皇家理工学院）； Scaleout Systems（Scaleout Systems公司）； Zenseact（Zenseact公司）； Uppsala University（乌普萨拉大学）

作者：Max Halleryd, Sima Sinaei, Viktor Valadi, Mina Alibeigi, Henrik Abrahamsson, Salman Toor

英文摘要：Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it attractive for privacy-sensitive and bandwidth-constrained applications. A practical challenge in deploying FL is reducing communication overhead while maintaining model performance under heterogeneous, non-IID data distributions. Selecting which subset of clients participates in each training round offers a principled way to address both challenges simultaneously, yet its impact on data diversity and representativeness remains underexplored. In this paper, we investigate three client selection strategies, Power-of-Choice, Fisher information, and Centered Kernel Alignment, evaluating them not only by accuracy and convergence, but through the lens of participation diversity using the Gini coefficient and KL divergence. Under non-IID conditions, restricting participation to 15% of clients per round achieves significant communication savings, and when selection promotes diverse and balanced contributions, it also improves generalization over biased alternatives. This work provides a systematic and reproducible analysis demonstrating that diversity-focused client selection renders communication efficiency and model quality complementary rather than competing objectives.

AI 总结：提出DW-FedADMM联邦优化框架，结合原对偶协调与客户端动态加权，在三个安卓恶意软件基准上实验，较FedADMM等方法提升准确率、降低误报率，在多数配置中表现最优。

链接：https://arxiv.org/abs/2611.09470

机构：University of Tehran（德黑兰大学）； Sejong University（世宗大学）

作者：Mohammad Mashreghi, Mohammad Hossein Badiei, Md. Jalil Piran

英文摘要：Smartphones, smart-home hubs, and wearables are increasingly exposed to sophisticated Android malware, while centralized threat-detection pipelines raise privacy and scalability concerns. Federated learning (FL) enables collaborative model training without collecting raw client data, but partial participation and variation in local model quality can destabilize global optimization. In this article, we propose DW-FedADMM, a federated optimization framework that combines primal-dual coordination with performance-dependent client-side weighting. The dynamic coefficient modulates each participating client's local state before the augmented-Lagrangian update, while the dual variables regulate disagreement between local and global model states. We evaluate DW-FedADMM on three Android malware benchmarks, namely Drebin, Malgenome, and TUANDROMD, with 5, 10, and 15 clients holding IID data shards, partial client participation, and communication budgets of 5 and 10 rounds. Each configuration is repeated with ten random seeds. DW-FedADMM obtains the highest seed-averaged accuracy on Drebin (97.64% +/- 0.20%) and the best mean accuracy in 9 of the 18 dataset-client-round configurations, including 7 of the 9 configurations with a 10-round budget. Pooled over all configurations, it reaches 95.42% accuracy, 94.62% F1-score, 96.06% precision, and 99.45% AUC, compared with 95.32%, 94.51%, 95.56%, and 99.41% for FedADMM, while also giving the lowest mean false-positive rate and the smallest client update norm among the six compared methods. Both primal-dual methods are well ahead of the averaging- and proximal-based baselines on Malgenome and TUANDROMD, where the latter often remain at the majority-class solution when clients are fragmented. The gain of dynamic weighting over FedADMM is most pronounced on Drebin and with the longer communication budget, where it also reduces the variation across seeds.

AI 总结：该研究揭示带归一化层的深度神经网络的两种Lipschitz常数会随深度指数级增长，导致训练稳定机制产生局部不可见的不稳定性，实验在三类数据集验证秩创建扰动会引发更严重的性能下降。

链接：https://arxiv.org/abs/2611.08775

机构：Massachusetts Institute of Technology（麻省理工学院）； The University of Texas at Dallas（德克萨斯大学达拉斯分校）； University of Virginia（弗吉尼亚大学）

作者：Ashkan Soleymani, Reyhaneh Hosseinpourkhoshkbari, Hadi Daneshmand, Patrick Jaillet

英文摘要： Can a network look stable at every layer and still be exponentially unstable as a whole? The Lipschitz constant of a neural network is a basic stability quantity appearing in optimization guarantees, generalization bounds, and robustness certificates. Deep networks naturally admit two such notions, input Lipschitzness, measuring sensitivity to data perturbations, and parameter Lipschitzness, measuring sensitivity to weight perturbations. We prove that, for deep networks with normalization layers, with batch normalization as the canonical example, both Lipschitz constants can grow exponentially with depth and hence with parameter dimension, even under strong per-layer norm control such as $\|W_\ell\|_2\le 1$, and already for linear activations. Thus, a mechanism widely used to stabilize training can create severe worst-case instabilities that are invisible locally, i.e., from layerwise norm bounds alone. Parameter-Lipschitz explosion turns Lipschitz-dependent nonsmooth optimization guarantees into exponential-in-dimension bounds for deep normalized networks, while input-Lipschitz explosion makes worst-case Lipschitz-based generalization and robustness certificates vacuous. The latter also yields a concrete rank-separation mechanism for adversarial vulnerability. The theory predicts that perturbations introducing new singular directions should be amplified much more strongly than perturbations at the same noise level that remain within the input's original singular subspace. Experiments on MNIST, Fashion-MNIST, and CIFAR-10 support this prediction, showing that rank-creating perturbations cause substantially sharper drops in accuracy, confidence, and margins than same-subspace perturbations.

AI 总结：本文将预训练模型的事后对称化方法从紧致群扩展到非紧致群，通过三种替代方法实现，在分布外场景等特定情况有改进，但未始终优于直接训练对称模型。

链接：https://arxiv.org/abs/2611.08992

机构：Johns Hopkins University（约翰斯·霍普金斯大学）； New York University（纽约大学）； Max-Planck-Institut für Astronomie（马克斯·普朗克天文研究所）； Flatiron Institute（弗拉蒂伦研究所）； Mathematical Institute for Data Science, Johns Hopkins University（约翰斯·霍普金斯大学数据科学数学研究所）

作者：Wenjie Zhou, Valentino F. Foit, David W. Hogg, Soledad Villar

英文摘要：Post-hoc group averaging (or test-time augmentation) is a simple way to impose symmetry on a trained predictor without changing its architecture or retraining it. For finite and compact groups, averaging over a normalized Haar measure on the group gives the Reynolds operator: a canonical projection onto invariant or equivariant predictors with known non-increasing risk guarantees under certain assumptions. This paper provides numerical experiments on physics emulation models that demonstrate the effectiveness of the approach in this setting. We then extend this framework to non-compact group symmetries. For non-compact groups, the Haar measure cannot be normalized, so group averaging cannot be defined in the same way. We replace it with three alternatives: the Weyl unitary trick (which requires complexifying the space and extending the predictor), a data-dependent orthogonal projection (which involves a non-trivial optimization on the space of invariant or equivariant functions), and a frame averaging approach (which involves mapping each point to a set of orbit representatives). We illustrate the constructions theoretically and empirically on the unit-rescaling group and the Lorentz group. Our results show that in the non-compact case, the Weyl trick and frame averaging do not provide a consistent improvement over the baseline, except where the test data is out-of-distribution (an orders-of-magnitude improvement in this case) and, for the Weyl trick, in low-data regimes. The orthogonal projection can provide improvements in-distribution and out-of-distribution. We also observe that models trained directly on invariant features matched or beat the projection of an unconstrained one. We conclude that post-hoc symmetrization extends to non-compact groups, but it does not consistently outperform training a symmetric model.

AI 总结：提出几何感知的Augmentron流水线，生成多视图一致的增强数据，替换部分真实数据集后，在三个物理操纵任务中提升了机器人策略的泛化性能，且优于其他增强技术。

链接：https://arxiv.org/abs/2611.09145

机构：University of Pennsylvania（宾夕法尼亚大学）； Scale AI； University of California, Berkeley（加州大学伯克利分校）； Scale AI, Inc.（Scale AI公司）

作者：Tanay Tandon, Aseem Doriwala, Jade Choghari, Catherine Weaver, Pragna Mannam

英文摘要：Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that are unrelated to the task. Existing generative augmentation methods can introduce visual diversity, but processing every frame and camera view independently is computationally expensive and may produce inconsistent observations across cameras and timestamps. We introduce Augmentron, a geometry-aware pipeline that generates reusable scene representations and renders them through recorded camera poses. This produces temporally and multi-view consistent environ- ment and workspace variations while preserving the robot, task objects, actions, and annotations. Across three physical manipulation tasks, replacing half of the real world training dataset with Augmentron data improves model success across three tasks for both in out-of-distribution distractor objects, and out-of-distribution workspace variation evaluations. In a separate comparison against alternate augmentation techniques, Augmentron achieves the highest pooled success in all three conditions. The results show that introducing augmented data to a data training recipe can help policies generalize to dynamic real-world settings.

AI 总结：该研究提出S-JEPA，将JEPA的辅助变量z改为随机隐变量，在不损失表示质量的前提下提升性能，还能生成空间结构化不确定性图和多样补全。

链接：https://arxiv.org/abs/2611.09302

机构：Imperial College London（伦敦帝国学院）； Information Technologies Institute, CERTH（CERTH信息技术研究所）

作者：Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki

英文摘要：Joint-Embedding Predictive Architectures (JEPAs) predict the latent embedding of a target signal from a context signal, with an auxiliary variable z conditioning the predictor. Despite its prominent role in the original JEPA blueprint, the content of z has been carried by a fixed deterministic token in every prior instantiation, collapsing the genuinely multi-modal distribution over plausible completions to a point estimate. We present S-JEPA, which realises z as a proper stochastic latent variable for masked image prediction: a learned posterior infers z from context and target during training, while a learned context-conditioned prior approximates the distribution of plausible completions at inference, with no decoders and no reconstruction. In its deterministic limit the objective reduces to the I-JEPA loss in functional form, generalising that objective rather than strictly containing the I-JEPA model. Our central finding is that stochasticity adds capabilities, error-correlated predictive uncertainty and diverse completions, at no cost to representation quality: under matched architectures and schedules S-JEPA improves over the deterministic I-JEPA baseline and exceeds LeJEPA at matched architecture, while additionally producing spatially structured uncertainty maps and semantically diverse completions, neither of which the deterministic predictor produces.

AI 总结：本研究在22个TDC ADMET数据集上比较11种校准不确定性量化方法，发现LightGBM与集成MC dropout为互补基线，需通过多化学划分的统计分析验证比较结论。

链接： https://arxiv.org/abs/2611.09373

机构：Department of Applied Mathematics and Computer Science（应用数学与计算机科学系）； Technical University of Denmark（丹麦技术大学）

作者：Laurits Fredsgaard, Michael Riis Andersen, Mikkel N. Schmidt

英文摘要：Absorption, distribution, metabolism, excretion, and toxicity (ADMET) models often rely on small, heterogeneous datasets, yet their predictions may determine which compounds proceed to experimental testing. Useful evaluations must therefore assess both predictive performance and the quality of reported probabilities or intervals. We ask which common uncertainty-quantification methods perform best on the 22 Therapeutics Data Commons (TDC) ADMET datasets and what this benchmark can resolve. We compare eleven calibrated pipelines using nested five-fold cross-validation across ten chemical partitions and five model seeds. Ensemble Monte Carlo (MC) dropout has the best average rank for TDC performance, Brier score, and 90% interval score. For TDC performance, however, it is not separated from the other ensemble pipelines; for Brier and interval score, LightGBM is also not ruled out as best. LightGBM wins more individual datasets than any other method for TDC performance and Brier score, but performs poorly on several endpoints. Smaller evaluations can identify a different leader and often fail to recover the broader comparison. These results make LightGBM and an ensemble neural model complementary baselines. Comparative claims should be checked across multiple chemical partitions using statistical analyses matched to the question being asked.

AI 总结：针对数据标注成本高且存在子群体分布偏移的问题，提出利用数据采集元数据作为有噪代理的主动学习策略，提升分类器在各子群体上的准确率。

链接：https://arxiv.org/abs/2611.09520

机构：Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； HEC Montréal（蒙特利尔高等商学院）

作者：Mizu Nishikawa-Toomey, Andreas Kirsch, Laurent Charlin, Dhanya Sridhar

英文摘要：In many domains from species identification to cancer diagnosis, labelling data to train predictive models remains costly. In these settings, it is advantageous to intelligently select data points to label to achieve the maximum information gain, this is the motivation behind the study of active learning. In addition to the high costs of acquiring data in such domains, there is the added complexity of data distribution shifts that can occur between training and deployment. For example, the features of cancerous skin cells taken in one country may be different in another region of the world. These two challenges - efficient labelling of data, and learning models robust to distribution shifts have been studied separately but not together, even though these challenges often co-occur in real-life settings. We identify failure modes of standard active learning approaches when the distribution of data at deployment is different from the distribution in which the data is sampled for labelling. We propose a new strategy for efficiently learning classifiers that generalise under specific forms of distribution shift, namely subpopulation shift. Drawing on work in learning from heterogeneous data, we aim to train models that perform well across subpopulations of the data, through active learning. To handle this challenging setting, we exploit the fact that many datasets include metadata about data collection that can serve as a noisy proxy for each sample's underlying subpopulation. We demonstrate how to leverage these noisy labels during active learning selection, and demonstrate empirically that our approach improves classifier accuracy across subpopulations.

AI 总结：该研究针对图变换器的残差聚合约束，提出节点自适应深度聚合方法AttnRes，在GPS、GRIT模型的5项ECHO任务上，相比原主干降低了平均绝对误差，验证了方法的有效性。

链接：https://arxiv.org/abs/2611.08500

作者：Yifeng Lu, Zhen Wang

英文摘要：Graph Transformers improve long-range node-to-node communication through global or structure-aware interactions. However, improving cross-node communication does not determine how computations produced at different depths should be combined. Standard residual streams accumulate successive computations with fixed unit coefficients shared across nodes. This fixed aggregation is a residual-interface constraint: once intermediate contributions have been produced, the interface cannot explicitly reweight them by node. We hypothesize that this constraint can create a depth-wise aggregation mismatch when the relative utility of these intermediate contributions varies across nodes and structural contexts. To study this hypothesis, we formalize Graph Transformer residual computation as a causal node-wise history of graph-propagation and feed-forward network (FFN) contributions, making depth aggregation an explicit interface choice. We realize node-adaptive aggregation over this history with Attention Residuals (AttnRes) while preserving the backbone's graph-propagation and auxiliary-state machinery. Block AttnRes reduces the routing cost of long histories relative to Full AttnRes by pooling consecutive contributions. We instantiate the interface in GPS and GRIT and evaluate it on all five ECHO tasks. Both variants achieve lower mean absolute error (MAE) than their independently tuned backbones on every task, and at least one obtains the lowest mean among all compared methods in each task. Routing-only donor-swap interventions support the mismatch hypothesis, while additional ablations examine the key design choices. Together, these results support node-adaptive depth aggregation as a useful complement to cross-node communication in long-range graph reasoning.

AI 总结：StreamTab是基于表格基础模型的无训练时序链接预测框架，通过regime conditioning设计优化负例采样，在13个数据集上对比21个基线方法，多数场景下取得最优或接近最优的平均精度。

链接：https://arxiv.org/abs/2611.09052

机构：South China University of Technology（华南理工大学）

作者：Mingqi Yang, Renqi Wu

英文摘要： Temporal link prediction uses past interactions to predict whether two nodes will interact in the future. Temporal graph neural networks achieve strong results on this task, but they are trained separately for each graph. How a model should use interaction history also depends on the candidates it is compared with. A past interaction can distinguish a recurring link from a random pair that has never interacted, but when the negative candidates have also interacted before, other signals are needed. We propose StreamTab, a training-free framework built on a frozen tabular foundation model pretrained only on synthetic tables. StreamTab describes each candidate pair by statistics of its past interactions and shows the model recent observed interactions and sampled negative pairs as labeled examples, from which the model scores new candidates. Its central design, regime conditioning, samples the negative examples according to how the candidates are sampled, so the examples show the distinction the model must make. As new interactions arrive, StreamTab updates the statistics and refreshes the examples while the model parameters stay fixed. On thirteen datasets against 21 temporal graph baselines, StreamTab achieves the highest average precision on twelve datasets under historical sampling and eleven under inductive sampling, and ranks first or stays within one point of the best on seven datasets under random sampling. With the same features and model, regime conditioning raises average precision over examples with random negatives by a median of 12.6 points under historical sampling.

AI 总结：本研究提出可扩展的基于GNN的框架FiLSim，结合顺序图编辑策略构建大规模数据集，在基准与新数据集上验证其在超15万节点图上的准确性与高效性，解决现有GNN方法图相似度学习的可扩展性问题。

链接：https://arxiv.org/abs/2611.09805

机构：Norwegian University of Science and Technology（挪威科技大学）

作者：Ahmet Tüzen, Helge Langseth, Kjetil Nørvåg

英文摘要：Graph similarity computation is an important task in graph mining with many real-world applications, such as chemical compound analysis, program dependence comparison, and social network analysis. The problem is computationally challenging: Graph Edit Distance (GED) and Maximum Common Subgraph (MCS), which quantify the distance between graphs and identify their largest shared subgraph, respectively, are NP-hard to compute exactly. To address these computational challenges, Graph Neural Networks (GNNs) have been applied to this problem. However, existing GNN-based approaches have primarily focused on small-scale graph datasets, while scalability to larger scales remains underexplored. In this work, we propose FiLSim, a scalable GNN-based framework, and investigate whether a simplified GNN pipeline can maintain competitive performance on standard benchmarks while scaling to large graphs. We additionally propose a sequential graph-editing strategy to construct large-scale graph datasets with reliable GED labels to evaluate scalability. The proposed framework is evaluated on four benchmark datasets and four newly created large-scale datasets, demonstrating its effectiveness and scalability. FiLSim remains accurate on graphs with more than 150{,}000 nodes, where the baseline methods run out of memory or fail to learn, and scores all test pairs within seconds on a single GPU.

AI 总结：本研究发现LLM评判器与持续学习者会将新闻复制品误判为独立确认，提出的检测方法可有效减少其接受的复制谎言，同时明确了防御手段的局限性与未解决问题。

链接：https://arxiv.org/abs/2611.09203

机构：caaise GmbH（caaise有限公司）； Djilali Liabes University of Sidi Bel Abbes（西迪贝勒阿巴斯吉利·利亚贝斯大学）

作者：Abdelkader Metales, Miriam Grabenheinrich, Aicha Metales

英文摘要：Many news reports of a claim are copies of one source: wire stories, content shared within a media group, syndicated features and press releases. We ask whether LLM judges and continual learners treat such copies as independent confirmations. In 200,000 English CC-News articles, a MinHash detector links 18.9% to a near-copy from another outlet (precision 0.97 once boilerplate is removed); it links 92% of edited reprints to their originals but none of the LLM rewrites by phi4, Llama 3.2 or Gemini 2.5 Flash. Shown three identical reprints of a claim about an unknown person instead of one report, Llama 3.2 3B and phi4 14B raised the share of lies they accepted from 0.06 to 0.71 and from 0.21 to 0.90 and ignored a note that the reports came from one source; Gemini 2.5 Flash already believed a single report, and Gemini 2.5 Pro followed provenance notes and tables. In a simulated continual-learning stream, showing the judge one report per detected chain cut the copied lies it accepted by 0.10-0.24 across four judges, at a mean cost of no more than 4.2 percentage points of accepted truths. Against reworded copies, a test of how many of a report's named entities are absent from an earlier look-alike separates LLM rewrites from 100 labelled independent reports of the same event with AUC 0.98-0.99 and wrongly flags one; entity overlap alone does as well, TF-IDF and a current embedding model come close, and the test catches few natural same-source derivatives. With the miss patterns of generated rewrite networks, it cut the reworded-copy lies accepted from 0.67 to 0.20 (0.40 when the rewriter invents details). Counting reports or chains alone is not a reliable defence, the effect of provenance information depends on the judge, and colluding sources remain the open problem. Code and labels: this https URL

AI 总结：本研究提出从LoRA适配器及冻结基础模型恢复技能文档的任务，提出Executing Writer等方法，在ALFWorld等基准上取得显著效果，可提升Llama-3.1-8B性能。

链接：https://arxiv.org/abs/2611.09454

机构：QpiAI

作者：Saranya Dintakurthy Swadha, Pavan C Shekar, Arpit Jain, Aswanth Krishnan

英文摘要： Agent skills are short documents that teach a language model how to handle a class of tasks. To save context, these documents are increasingly compiled into low-rank adapters (LoRA), which keep the behaviour but lose the text: an adapter is hard to read, edit, audit or move to another model. We ask whether the skill document can be written back from the adapter and its frozen base model, and we score each recovered document by the share of the original's key instructions it states and by the tasks it solves. Reading the weights alone recovered little with the methods we tried; a learned map from weights to text passed on about one bit of the document. Running the adapter worked much better. The Executing Writer, a small writer trained on top of the adapted model, recovers 39-44% of the key instructions of held-out skills, against 1.3-1.5% with another skill's adapter, and on adapters fitted to 41 external skills its documents restore 85-91% of the original's task gain. These strongest results are on adapters whose training stored the document; adapters trained on behaviour alone are much harder for trained writers (1-2% of instructions). For these adapters we test an agent that runs the base and adapted models and writes a skill from where they differ. On ALFWorld its skills recover 58-71% of a LoRA's gain and carry over to models that cannot load the LoRA, lifting Llama-3.1-8B from 5% to 55%. Whether such a skill comes from the adapter depends on what the adapter learned: when its behaviour cannot be guessed, the adapter is the source; when it can, a reward loop without the adapter does as well.

AI 总结：本研究探究LLM智能体在低成本分子优化基准中的学习机制，量化在线优化、可检索信息等的贡献，提出两种低成本合理性检查方法。

链接：https://arxiv.org/abs/2611.08522

机构：University at Buffalo（布法罗大学）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

作者：Jiayu Qin, Zhengquan Luo, Changyou Chen, Zhiqiang Xu

英文摘要：Recent work reports large gains for LLM agents on low-budget molecular optimization. We measure the contributions of online optimization, retrievable task information, and permissive oracle landscapes. On PMO at 50 oracle calls, a GPT-4o mini agent's sum AUC falls from 14.44 to 4.85 after task names and curated reference compounds are hidden. An identity-blinded condition that states only the oracle form (e.g., similarity to a hidden reference) scores 5.39, while a deterministic retrieval-only baseline with no LLM reaches 12.16 (84% of the full agent). A full 23-task 2x2 ablation and a three-seed replication on eight tasks support this interpretation. On a protein-targeted benchmark with an AutoDock Vina composite oracle, a single-edit random walk is a strong lower bound; across three seeds it obtains composite 0.636 +/- 0.008 and docking improvement -1.11 +/- 0.04 kcal/mol. As a positive control, a retrieval-free population agent exceeds REINVENT at a matched 50-call AUC budget, with its strongest result at 100 calls. These results motivate two inexpensive sanity checks: retrieval-safe PMO prompts and a random-walk floor for docking-based optimization.

AI 总结：本文针对涌现对齐偏差现有评估的局限，提出分解基准EMERGE，经8个模型和13个数据集验证，可捕捉单一分数无法体现的不同模型对齐偏差行为特征，推动该领域研究发展。

链接：https://arxiv.org/abs/2611.08569

机构：ETH Zürich（苏黎世联邦理工学院）

作者：Afonso Domingues, Mubashara Akhtar, Bhada Yun, Xin Chen, Lukas Fluri, Anna Hedström

英文摘要：Emergent misalignment (EM), in which fine-tuning on a narrow task induces misaligned behaviour on unrelated prompts, has been demonstrated across a wide range of datasets, model families, and training setups. Yet, most studies continue to rely on the evaluation approach introduced in the original EM paper, producing rates that are sensitive to the small set of evaluation questions used, the choice of judge, and the thresholds applied. These evaluations can also conflate misalignment with capability loss and offer little insight into the specific ways misalignment manifests. Differences in datasets, models, and fine-tuning configurations further make findings difficult to compare across studies. We introduce EMERGE, a decomposed benchmark that tracks changes in eight distinct misaligned behaviours from base to fine-tuned models. It evaluates these behaviours on out-of-domain prompts against matched benign controls and tracks capability, coherence, and refusal to account for potential confounders. Applying EMERGE to 8 open-weight models and 13 fine-tuning datasets, we find that models with similar broad misalignment rates can exhibit very different behavioural profiles that a single score cannot capture. We hope EMERGE can help establish a shared and robust standard for measuring EM, making findings more comparable and helping move research from detecting the phenomenon towards understanding it.

AI 总结：本研究针对天体物理中混沌三体动力学的ML方法开展基准测试，设计稳定性与轨迹预测任务，对比ML方法与天体物理准则，发现长时程轨迹预测仍具挑战。

链接：https://arxiv.org/abs/2611.08634

机构：École Polytechnique, IP Paris（巴黎综合理工学院, 巴黎IP大学）； CITA, University of Toronto（多伦多大学CITA研究中心）； Google DeepMind（谷歌DeepMind）； LIX, CNRS, École Polytechnique, IP Paris（法国国家科学研究中心LIX实验室, 巴黎综合理工学院, 巴黎IP大学）

作者：Sheng Wan, Pavan Vynatheya, Duo Xu, Li Kevin Wenliang, Ye Zhu

英文摘要：Machine learning (ML) and generative AI have recently made impressive progress in understanding physics. We explore a hierarchy of prediction problems stemming from chaotic three-body systems and benchmark existing ML approaches, including general-purpose prediction algorithms and those that build on top of foundational physics models. We first simulate the trajectories of triple systems near the critical boundary of stable/unstable initial conditions. We then design a hierarchy of learning tasks, focusing mainly on two broad problems: stability prediction and trajectory prediction. The former classifies whether a given triple system has diverged or not up to a specific horizon, while the latter predicts the exact trajectory, both given suitable input features. We benchmark a range of ML approaches, from simple regression methods to state-of-the-art foundational physics models, across these tasks, and compare them against astrophysical methods such as the Mardling-Aarseth stability criterion. Our experiments reveal a clear order of task difficulties in chaotic three-body dynamics: early dynamics enable strong stability prediction, while precise long-horizon trajectory forecasting remains difficult. Code and dataset are publicly available at this https URL.

AI 总结：MotionBench-XAI基准通过合成与真实时空数据集、多种归因方法及架构，揭示时空机器学习中Shapley解释的关键影响因素，为相关研究提供实用见解与开源工具。

链接：https://arxiv.org/abs/2611.08797

机构：University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）

作者：Mathilde Papillon, Louisa Cornelis, Nina Miolane

英文摘要：Predicting outcomes from spatiotemporal data, such as assessing Parkinson's severity from human motion, often requires explainability in addition to accuracy. Practitioners need to know what drove the prediction, whether it be spatial (a body joint), temporal (a specific window), or both. Shapley values are attributions computed by treating input features as players in a cooperative game and measuring how the model output changes as coalitions of players are removed. Computing them involves choosing what counts as players, how absent players are imputed, and how the game is evaluated. How these choices affect explanation quality is poorly understood for spatiotemporal data, and real data carries no ground-truth attributions to check against. We present MotionBench-XAI, a benchmark built on i) five synthetic spatiotemporal datasets with exact ground-truth Shapley values, ii) three real datasets across clinical gait, electrocardiogram, and audio, iii) ten attribution methods across three player sets, and iv) three trained architectures. We show that grouping features into players, across time, space, or both, matters more than the choice of imputer. Generative imputers improve explanations only when their conditional models are accurate. On real data, the standard proxy metrics select contradictory best methods. We distill these findings into practical insights and provide an open-source pipeline.

AI 总结：针对视觉-语言模型少样本适配的梯度噪声问题，提出两种无状态优化器SignSparseSGD与DynSignSparseSGD，在多数据集、骨干及样本数设置下性能优于或相当基线，且对长训练计划更鲁棒。

链接：https://arxiv.org/abs/2611.08800

作者：Nairouz Mrabah, Ismail Ben Ayed, Mahdi S. Hosseini, Eric Granger

英文摘要：The limited supervision available for the few-shot adaptation of vision-language models makes gradient estimation particularly noisy. We find that the gradient magnitudes are severely miscalibrated, while the signs of a small top-magnitude subset remain informative. This motivates SignSparseSGD and DynSignSparseSGD, two state-free optimizers that use gradient magnitudes only to select where to update and fixed-magnitude signs to decide how to update. The static variant fixes the support after the first minibatch. The dynamic variant refreshes it at every step. Across 11 datasets, three CLIP backbones, and five shot levels, the proposed methods are competitive with or outperform parameter-efficient and optimization-based baselines on average, while exhibiting markedly lower sensitivity to long training schedules. They introduce no task-specific modules, maintain no first- or second-moment optimizer states, and use one shared configuration across datasets, backbones, and shot levels. Our code is included in the supplementary materials and will be released upon publication.

AI 总结：该研究针对机器学习招聘工具公开基准测试的法律难题，构建分类学驱动的合成HR数据集与基准，审计发现嵌入模型在HR场景的性能及公平性与通用基准存在差异，需定制评估识别帕累托最优模型。

链接：https://arxiv.org/abs/2611.09178

机构：Malt（马尔特公司）

作者：Warren Jouanneau, Morgane Hoffmann, Emma Jouffroy, Marc Palyart

英文摘要：While machine learning hiring tools are ubiquitous, the need for privacy regulations and commercial sensitivity makes public benchmarking legally complex. We address this challenge by introducing a taxonomy-driven, fully synthetic HR dataset and benchmark to simultaneously evaluate retrieval effectiveness and algorithmic fairness. Grounded in 660K real freelancer profiles, our multilingual corpus features candidate profiles, project briefs, and counterfactual demographic twins. Auditing state-of-the-art embedding models reveals performance divergence from general MTEB scores, alongside fairness disparities in grammatically gendered languages. This demonstrates that general benchmarks are insufficient for HR, requiring tailored evaluations to identify Pareto-optimal models that balance semantic accuracy and fairness.

AI 总结：本研究提出FondueQA基准，用于评估多跳问答中参数补偿，发现模型对流行实体的事实补偿更成功，桥接证据比答案文档更有用，竞争实体可使精确匹配降15个百分点。

链接：https://arxiv.org/abs/2611.09274

机构：University of Technology Nuremberg（纽伦堡工业大学）； Department of Computer Science & Artificial Intelligence（计算机科学与人工智能系）

作者：Laurin Schmid, Suman Navaratnarajah, Koel Dutta Chowdhury, Steffen Eger, Josif Grabocka, Christian Frey

英文摘要：Large Language Models (LLMs) show remarkable performance based on parametric knowledge, i.e., their ability to recall facts and associations internalized in a model's weights. However, studying this capability on established multi-hop benchmarks may be complicated by benchmark contamination, as many of these benchmarks have been publicly available long enough to plausibly appear in modern pretraining corpora. As a result, correct answers under missing evidence may reflect either general parametric knowledge or memorization of benchmark-specific instances. To study how models use internal knowledge when retrieval evidence is incomplete, we introduce FondueQA, in which every required multi-hop fact is uniquely localized to a designated evidence document. This enables controlled document-level evidence ablations to study parametric compensation under incomplete retrieval. Our empirical evaluation reveals that parametric compensation strongly depends on both entity popularity and the structural role of missing evidence. Generally, models compensate more successfully for facts involving popular entities. On FondueQA, we show that bridging evidence can be more useful than the answer-bearing document itself. Moreover, models may recall a missing fact in isolation but fail to use it under partial evidence, particularly when the context contains plausible competing entities, which can reduce Exact Match by up to 15 percentage points.

AI 总结： 本研究针对不确定知识结构下的学习路径推荐问题，提出先修感知框架，经MOOCCubeX和Junyi数据集验证，发现即时预测准确率、先修结构可靠性与长时路径质量为互补评估维度。

链接：https://arxiv.org/abs/2611.09345

机构：American International University-Bangladesh (AIUB)（孟加拉国美国国际大学（AIUB））； Mälardalen University（梅拉达伦大学）

作者：M. M. Golam Hafiz, A.K.M. Shahriar Emtiaz, Safia Akter Simi, Md. Rakibul Islam, M. F. Mridha

英文摘要：Learning-path recommendation often depends on knowledge and prerequisite structures whose reliability is uncertain, while high accuracy in predicting the next resource does not necessarily establish reliable long-horizon path behaviour. This study develops a reliability-oriented prerequisite-aware framework that jointly examines immediate next-resource ranking, uncertain prerequisite structures, hard, soft and hybrid constraint semantics, graph robustness, and autoregressive path generation under course-level confirmatory evaluation and independent cross-dataset validation. Development used 3,187 MOOCCubeX courses, followed by a frozen confirmatory evaluation on 541 held-out courses and 37,747 transitions. The primary MOOCCubeX task is structural and course-prefix-conditioned rather than learner-personalised. Junyi provides independent structure-/hierarchy-aware external validation, uses hierarchy metadata rather than an explicit prerequisite graph and is not a zero-shot transfer setting. On the frozen MOOCCubeX evaluation, XGBoost pairwise was the strongest observed immediate ranker, with mean reciprocal rank (MRR) of 0.9048, whereas the proposed prerequisite-aware graph model achieved 0.7707. In the controlled graph-variant development ablation, the no-graph condition produced the strongest immediate ranking result, and immediate prediction showed strong dependence on permitted title/path-similarity information. Autoregressive evaluation exposed path properties not captured by one-step ranking. On Junyi, Markov achieved the strongest observed MRR of 0.4453, compared with 0.3954 for the proposed graph model, with metric-specific differences across ranking measures. Overall, immediate predictive accuracy, prerequisite-structure reliability, and long-horizon path quality should be treated as complementary rather than interchangeable evaluation dimensions in educational recommendation.

AI 总结：本研究针对离线模仿学习中安全与性能难以兼顾的问题，提出DexDICE方法，结合双专家演示与DICE式学习，在DSRL基准及移动机器人任务中验证其性能与鲁棒性。

链接：https://arxiv.org/abs/2611.09433

机构：Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）； Korea Advanced Institute of Science and Technology (KAIST)（韩国高等科学技术院）； Hyundai Motor Company（现代汽车公司）； Yonsei University（延世大学）； Korea Institute for Advanced Study (KIAS)（韩国高等研究院）

作者：Seokin Seo, Sung Kuk Shyn, Minji Seo, Yisoo Lee, Jongmin Lee, Hongseok Yang, Kee-Eung Kim

英文摘要：Ensuring high returns while providing strong safety guarantees in offline imitation learning (IL) is a fundamental challenge: existing approaches either rely on explicitly specified cost functions, which are difficult to design for complex real-world safety constraints, or require expert demonstrations that are both safe and high-performing, which are often too costly to collect. We introduce dual-expert imitation learning, which leverages two complementary data sources: (i) safety-compliant demonstrations that faithfully follow safety guidelines but may be suboptimal, and (ii) performance-oriented demonstrations that achieve high returns but may violate safety guidelines. To address this problem, we propose DexDICE (Dual-expert offline imitation learning via stationary DIstribution Correction Estimation). Instead of conventional distribution constraints, DexDICE combines DICE-style offline learning with safe support constraints, enabling agents to exploit high-return behaviors while remaining within safety-compliant regions. We prove that the ideal solution satisfying this constraint exactly has zero unsafe-region visitation with high probability. We evaluate DexDICE on a re-curated DSRL benchmark and validate it on a real-world mobile-robot navigation task trained directly from human teleoperation demonstrations, where it substantially outperforms baselines and remains robust to data scarcity and quality degradation.

AI 总结：本研究提出基于Transformer的ICare-DT数字孪生模型，利用14万余条eICU-CRD数据训练，可每小时更新患者状态提升预测，构建基准测试治疗反应预测，证实常规记录支持改进型预测。

链接：https://arxiv.org/abs/2611.09712

机构：ETH Zurich（苏黎世联邦理工学院）； Swiss Paraplegic Research（瑞士截瘫研究机构）； University of Toronto（多伦多大学）

作者：Yanke Li, Yahang Qi, Yumi Kim, Diego Paez-Granados

英文摘要：Digital twins of intensive care patients should update forecasts from new data and predict treatment responses, but few studies test whether routine records support either. We propose ICare-DT, a Transformer-based twin that updates a latent patient state hourly from new measurements without retraining. We trained it on 140,473 eICU-CRD stays to forecast vital signs crossing their training-set means. On test data, later forecasts beat the twin's own hour-6 forecasts of the same windows in all 12 settings (+0.073 to +0.153 AUROC). On validation data, controls that withheld or swapped the new hours traced the gain to the patient's own measurements. Without refitting, the model kept its gain on a second database (8 of 9 settings, +0.025 to +0.114 AUROC) in a prespecified evaluation of the previously analyzed MIMIC-IV test split. Refitted within MIMIC-IV, a twin state fine-tuned on clinical endpoints gave gradient boosting a significant gain for acute kidney injury (+0.0035 AUROC; hypotension +0.0010, not significant). To test response prediction, we built a benchmark that replaces the treatments in real records with simulated doses and injects responses of known size, visible only at measurement times. Ridge models supervised with injected effects recovered them from real records only through frequently measured variables (heart rate) read at their measurement times. We asked standard learners to predict these effects for a dosing regime no patient had received. No standard learner outperformed predicting zero effect at an out-of-support query. When told how the simulated responses were generated, a separate learner recovered the effects from the same records without seeing their true values (R2 0.30 to 0.40 at one effect size). Routine records support forecasts that improve with each patient's new data, and our benchmark is a testbed for models that learn how responses are generated.

AI 总结：该研究针对LLM在数据科学任务中的可靠性评估问题，构建DS-QA基准与三层评估框架，采用含100次重复运行的蒙特卡洛协议，发现LLM在部分任务中响应变异性显著，且词冗长度比与标记冗长度比存在关联。

链接：https://arxiv.org/abs/2611.09729

机构：University of Edinburgh（爱丁堡大学）

作者：Wenqi Ni, Ozan Evkaya, Miguel de Carvalho

英文摘要：Large language models (LLMs) have shown promise for automating data science workflows. Benchmarks such as DataSciBench (2026) and StatQA (2024) have advanced the evaluation of their capabilities across data science and statistical tasks. Assessing their reliability requires examining both the quality of their responses and their consistency across repeated runs, task types, and difficulty levels. With this aim, we introduce DS-QA, a benchmark comprising 100 data science and statistics questions drawn from UK university courses, spanning 16 datasets and three difficulty levels. We develop a three-layer evaluation framework that combines general response properties (runtime, verbosity and text similarity), coarse-grained metrics (accuracy, code executability and completeness), and task-specific metrics. We evaluate OpenAI models using a Monte Carlo protocol with 100 repeated runs. The results reveal substantial variability in responses to data visualisation and supervised learning tasks, particularly at medium and hard difficulty levels, highlighting the importance of evaluating consistency alongside response quality. We also find that an increase of 0.1 in the word verbosity ratio corresponds to an increase of about 0.013 in the token verbosity ratio.

AI 总结：研究发现UCR时间序列分类档案的部分数据集任务偏离TSC目标，存在缺陷，呼吁谨慎解读其分数并关注部署相关评估。

链接：https://arxiv.org/abs/2611.09843

机构：University of Freiburg（弗莱堡大学）； Prior Labs（Prior实验室）； ELLIS Institute Tübingen（图宾根ELLIS研究所）

作者：Omar Swelam, Jaris Küken, Shi Bin Hoo, Frank Hutter, Lennart Purucker

英文摘要：The pigs were bleeding. That was the point of the experiment: could airway pressure reveal hemorrhage before it became critical? In the UCR Time Series Classification Archive, the de facto benchmark for Time Series Classification (TSC), the same recordings ask a different question: "which of 52 pigs produced this trace?". The dataset PigAirwayPressure is not an outlier. Although the archive is the standard benchmark, whether its tasks resemble the problems TSC is meant to solve has rarely been examined. We find that several datasets are repurposed from their original task, built from toy setups, or have flawed test splits. We further question how representative the archive's ordered non-temporal sequences (e.g. spectra, shape outlines) are of real TSC, and the potential downsides from the decomposition of multivariate problems. Our findings call for more careful interpretation of archive-wide scores and greater attention to deployment-relevant evaluation. The audit is at this https URL.

AI 总结：本研究针对物理信息神经网络（PINN）现有基准孤立考察组件的问题，提出将四个组件视为集成系统的综合评估协议，发布含18种方法和9个基准问题的PINNpipe包，所得结果挑战了常见假设。

链接：https://arxiv.org/abs/2611.08559

机构：Osnabrück University（奥斯纳布吕克大学）； Joint Lab Artificial Intelligence and Data Science（人工智能与数据科学联合实验室）

作者：Kevin von Bargen, Hamid Ebrahimy, Tim Römer

英文摘要：The Physics-Informed Neural Network (PINN) literature has produced a rapidly expanding catalogue of methods. We divide a PINN training pipeline systematically into four components and observe that many existing benchmarks study these components in isolation. These components are domain-importance adaptation, loss balancing, neural network architecture, and optimization scheme. Moreover, the studies set the surrounding and not considered components of the pipeline to a minimal default that is no longer representative of current best practice approaches. Conclusions drawn under such conditions may not transfer to competitive pipelines. In this work, we propose a new evaluation protocol that (1) treats the four components as an integrated system; (2) crucially requires competitive implementations of the components not under investigation; (3) specifies the metrics and reporting format; and (4) is accompanied by structured documentation that ensures the traceability of evaluations across studies. Based on this comprehensive protocol, we release PINNpipe, an innovative JAX package containing 18 different methods from the current literature as well as nine efficiently implemented benchmark problems. Using PINNpipe, we illustrate our evaluation protocol in relation to established benchmark studies and report results that challenge common assumptions.

AI 总结：本研究提出时序条件框架When2What，通过预测心跳时序并锐化事件、条件生成波形，在心血管波形长时序预测中性能优于现有方法，可零样本迁移且适配多类波形。

链接：https://arxiv.org/abs/2611.08993

机构：Indiana University Bloomington（印第安纳大学布鲁明顿分校）； Indiana University School of Medicine（印第安纳大学医学院）； Fuwai Hospital, National Centre for Cardiovascular Diseases, Chinese Academy of Medical Sciences & Peking Union Medical College（中国医学科学院阜外医院（国家心血管病中心、北京协和医学院））； Tianjin Chest Hospital, Tianjin University（天津大学附属天津胸科医院）； Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University（南京大学医学院附属南京鼓楼医院）； Xiangya Hospital, Central South University（中南大学湘雅医院）； University of California Davis School of Medicine（加州大学戴维斯分校医学院）； Microsoft（微软公司）

作者：Chaoqi Zhang, Shujie Yan, Zhao Zhang, Yanhua Sun, Yu Wang, Li Li, Lingzhong Meng, Xiaoyi Chen, Haixu Tang

英文摘要： Long-horizon forecasting of quasi-periodic cardiovascular waveforms, such as the electrocardiogram (ECG), arterial blood pressure (ABP), and photoplethysmogram (PPG), requires predicting both when future cardiac events will occur (beat timing) and what the local structural pattern looks like around each event (beat morphology). However, standard sequence forecasters trained with pointwise mean squared error (MSE) average across uncertain future heartbeat phases, flattening sharp R peaks and pulse upstrokes into featureless baselines. Our analysis of intraoperative ECG reveals a clear temporal asymmetry: beat-time predictability from history decays within seconds due to stochastic heart-rate variability, whereas local beat morphology aligned at true beat times remains stable over several minutes. Guided by this insight, we introduce When2What, a timing-conditioned framework comprising three stages: Predict, Commit, and Generate. Given a 120-s history, When2What predicts a dense 60-s timing map, selects and sharpens discrete beat events into unit-height Gaussian impulses, and conditions a neural waveform generator on both these committed events and the observed history. Across intraoperative ECG, When2What substantially outperforms existing time-series and physiological forecasters, achieving a near-term waveform event skill of 0.644 and reproducing 95.62% of its predicted heartbeats in the generated waveform where direct long-horizon forecasters collapse into flat baselines. Furthermore, When2What transfers zero-shot to external hospital and atrial fibrillation cohorts, extends effectively to ABP and PPG pulse waveforms, and is supported by ablations and synthetic analyses that establish explicit timing conditioning as an effective paradigm for quasi-periodic long-horizon waveform forecasting.

AI 总结：本文提出函数空间验证框架，将区间边界传播（IBP）与CROWN扩展至函数空间，可全域验证神经算子，实验显示其能为含5.725亿参数的球形傅里叶神经算子等生成紧致保证，为可信算子学习奠基。

链接：https://arxiv.org/abs/2611.09038

机构：National Taiwan University（台湾大学）； California Institute of Technology（加州理工学院）

作者：Ryan Hsiang, Robert Joseph George, Anima Anandkumar

英文摘要：Certifying the robustness and physical consistency of scientific machine-learning models ensures that their predictions remain reliable beyond the test set. For neural operators, which learn PDE solution operators by mapping infinite-dimensional function spaces, certification means establishing rigorous, domain-wide guarantees for their output functions. However, standard neural network (NN) verification methods are fundamentally designed for vector-to-vector mappings, and they can only certify neural operators at fixed grid resolutions and provide no guarantees over the entire domain or across another resolution. We close this gap by introducing a function-space certification framework that verifies neural operators across the entire continuous domain. We formulate interval bound propagation (IBP) and CROWN in function space, propagating upper and lower bound functions through each layer using rigorous numerical integration. In addition, we extend bound propagation to higher-order derivatives to certify PDE residuals and solution error bounds. Experiments across several neural operator architectures and scientific problems, including the 572.5-million-parameter spherical Fourier neural operator for global weather forecasting, show that our method produces tight, domain-wide guarantees efficiently, providing a foundation for trustworthy operator learning.

AI 总结：本研究针对大语言模型分子生成表示纠缠的问题，提出可解释性驱动的SpaRE框架，通过超完备稀疏特征空间实现分子生成的局部与全局可控，实验验证其能生成符合要求的分子并提供结构-性质分析见解。

链接：https://arxiv.org/abs/2611.09235

机构：The Hong Kong Polytechnic University（香港理工大学）

作者：Zhuoran Li, Xu Sun, Chang Wen Chen, Wanyu Lin

英文摘要：Controllable molecule generation is crucial for diverse scientific applications, such as drug discovery and materials design. While large language models (LLMs) show great promise, their dense and entangled representations impede precise control over the generation of molecules with bespoke substructures or properties. To address this, we propose Sparse Representation Editing (SpaRE), an interpretability-driven framework for fine-grained and precise control in LLM-based molecule generation. The crux of SpaRE is to learn an overcomplete sparse feature space that disentangles LLM representations into a compact set of latent features corresponding to chemically meaningful concepts. Within this space, we can directly manipulate these concept-aligned latent features to achieve (1) local control, by generating target atoms and functional groups at specified positions; and (2) global control, by customizing the overall structural and physicochemical properties within defined ranges. In this way, our framework advances interpretability from post-hoc analysis to actionable generative control. Experiments show that SpaRE can generate chemically desirable molecules under complex constraints in real-world scenarios, while offering mechanistic insights for quantitative structure-property analysis. The code and demo are available at this https URL.

AI 总结：本文针对部分观测动力系统模拟的稳定性问题，提出受迫耗散随机插值器框架，通过结构约束保证稳定性，在Lorenz-96系统上验证了其长期稳定性与预测精度。

链接：https://arxiv.org/abs/2611.09317

机构：École polytechnique, Institut polytechnique de Paris（巴黎综合理工学院、巴黎理工学院）； Courant Institute, New York University（纽约大学柯朗数学科学研究所）； LMD, ISPL, ENS, Université PSL（巴黎高等师范学院、巴黎文理研究大学）

作者：Mario Massy, Sara Shamekh, Fabrizio Falasca, Matthieu Blanke

英文摘要：Predicting the long-term behavior of partially observed dynamical systems such as the coupled atmosphere-ocean system is central to societal decision-making. Motivated by the success of deep learning emulators in weather forecasting, data-driven climate models represent a promising approach. However, climate emulation poses distinct challenges: models must account for unresolved fast variables introduced by unavoidable coarse-graining, reproduce long-term statistics, and remain stable over arbitrarily long rollouts and under external perturbations. These requirements motivate stochastic data-driven emulators, but modern generative models lack stability guarantees. We introduce forced-dissipative stochastic interpolants, a generative framework for learning stochastic reduced dynamics. Its architecture uses structural constraints inspired by turbulent dynamics, which provide stability by design while retaining the flexibility of stochastic interpolants to represent complex probabilistic dynamics. Building on the theory of Markov-chain stability, we establish a Foster--Lyapunov drift condition and prove geometric ergodicity for our emulator, together with stability under steady external forcing. We evaluate the framework on the two-timescale Lorenz-96 system, a prototype of partially observed multiscale turbulence. The resulting emulator remains stable over long integrations and under finite-amplitude forcing, with accurate prediction of forced responses of both the mean and variance.

AI 总结：本研究提出BiLoGo模拟器，结合局部节点-元素消息传递与Transformer神经算子，在板材成形模拟中降低局部响应平滑效应，较现有模型误差更低且内存占用更少。

链接：https://arxiv.org/abs/2611.09621

机构：Dyson School of Design Engineering, Imperial College London（帝国理工学院戴森设计工程学院）； Prometheus, UK（英国普罗米修斯机构）

作者：Yingxue Zhao, Haoran Li, Haosu Zhou, Tobias Pfaff, Nan Li

英文摘要：Trial-and-error FE simulation of sheet forming could be computationally expensive, neural-network-based learned simulators are used to accelerate design. These simulators should accurately capture localised responses, such as thinning around sharp radii or near ribs, which determine formability. Transformer-based neural operators propagate information efficiently across the mesh but tend to smooth such localised responses. This study develops BiLoGo, a Bipartite Local-Global learned simulator with an FE-guided design that connects local node-element message passing with a Transformer-based neural operator for long-range information exchange. BiLoGo has three modules: a bidirectional node-element GraphSAGE model that learns nodal-elemental coupling on a bipartite graph and predicts each quantity on its native FE entity without interpolation; a dual-stream Transformer-based neural operator that processes blank deformation and tool contact with separate token sets, preventing localised contact information from being averaged with the whole-blank state; and a fusion and element update module that combines global and local features via gated residual fusion and updates element features conditioned on element-node kinematics. Evaluated on a dome-shaped cold forming case and two corner-shaped hot stamping cases (one with ribs), BiLoGo achieves the lowest positional and threshold-based thinning errors on all three cases compared with single-level and hierarchical graph-based models and Transformer-based neural operators. Near the ribs, the smoothing index of predicted thinning increases from 0.41-0.56 for Transformer-based neural operators to 0.94 for BiLoGo-U. Compared with the hierarchical graph network CAtt-BiUGNN, BiLoGo-T reduces mean positional error by 15.5% on the Corner case and BiLoGo-U by 8.3% on the Corner+Rib case, with 66-69% less training memory.

AI 总结：该研究针对英国风电预测不确定性区间覆盖不足问题，将共形预测应用于原生区间，通过按风况校准提升覆盖精度，大幅降低大风天气下的日前区间外体积并收窄区间。

链接：https://arxiv.org/abs/2611.09815

机构：University College London（伦敦大学学院）

作者：Carl Somers

英文摘要：Uncertainty bands on wind forecasts help inform reserve sizing and commitments, but often fail to deliver their stated coverage. We apply conformal prediction to native bands to see what it adds and what it costs, comparing six forecasters, from ARIMA to a tabular foundation model, at two wind farms in Great Britain (GB) under operational conditions. We show that calibration repairs empirical marginal coverage with little or no Winkler Score penalty, but this apparent success conceals under-coverage in high winds. Calibrating by forecast wind regime turns marginal coverage into regime-level coverage, cutting day-ahead out-of-band volume in high winds by over 40% relative to pooled calibration while narrowing bands overall.

AI 总结：FasterRW是一种用于热分析的高效先验辅助随机游走求解器，通过提出延续值框架及相关恒等式，实现了最高28倍的加速且保持精度，代码已开源。

链接：https://arxiv.org/abs/2611.08490

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； The Chinese University of Hong Kong（香港中文大学）

作者：Zixiao Wang, Tianshu Hou, Chenghan Wang, Zhen Zhuang, Leilei Jin, Tsung-Yi Ho, Farzan Farnia, Bei Yu

英文摘要：Thermal simulation is becoming increasingly critical in modern IC design and manufacturing. Feynman--Kac random walk methods can estimate localized temperatures without solving the global field, but in practical settings without Dirichlet boundaries they require very long paths to control the truncation residual. This paper presents FasterRW, a continuation-value framework for accelerating Feynman--Kac thermal random walks. We prove a stopping-time residual identity showing that the expected tail after truncation equals the current attenuation weight multiplied by the temperature at the stopping location. This identity enables a prior-corrected single-point estimator: a cheap, noisy prior replaces the unknown continuation value, making the truncation bias scale with prior error rather than absolute temperature and yielding an error-controlled threshold-selection rule. For multi-point queries, FasterRW further converts cross-query pass-through tails into pseudo-samples and refines the resulting observations in prior-error coordinates through kriging. Compared with prior state-of-the-art methods, FasterRW achieves up to $28\times$ acceleration while maintaining accuracy. Our code is open-sourced at this https URL.

AI 总结：本研究将ConsRNN嵌入Abaqus/Explicit的VUMAT子程序，解决了SimpleRNN预测随增量漂移的问题，实现了结构尺度的路径相关损伤预测，其峰值前结果与双参数断裂准则一致。

链接：https://arxiv.org/abs/2611.08494

作者：Muhammed Adil Yatkın, Mihkel Kõrgesaar, Hasan Kurban

英文摘要： Capturing sheet-metal localisation physics with a trained surrogate inside a finite element (FEM) solver requires the surrogate to deliver consistent predictions irrespective of the solver's strain-increment count, which is difficult to control in non-linear explicit codes. We address this by re-implementing a trained recurrent neural network (RNN) damage criterion in Fortran and embed it as a live, increment-by-increment fracture criterion inside an Abaqus/Explicit user material subroutine (VUMAT), advancing the network state alongside the solver. Two architectures are compared: a SimpleRNN and the proposed Consistent RNN (ConsRNN), whose transition function is designed so that predictions converge as the strain path is refined rather than drifting with the increment count. Both are trained on bilinear strain paths and evaluated under varying temporal discretisations and nonlinear histories. SimpleRNN predictions drift as the increment count increases, which disqualifies it for embedding; ConsRNN converges under refinement, at a substantial fixed-resolution accuracy cost relative to SimpleRNN on multilinear paths. Deployed at structural scale, the embedded ConsRNN surrogate governs element deletion in a clamped steel plate and reaches the same peak force and peak displacement as an established two-parameter fracture criterion. This pre-peak agreement is expected by construction, since no element is deleted before the peak and the two runs therefore share an identical constitutive path; the responses diverge only on the post-peak softening branch. The results establish discretisation consistency as the decisive property for embedding recurrent surrogates in explicit FEM solvers, and report the first embedding of a customised, non-standard-transition recurrent cell at structural scale.

AI 总结：本文提出QMAC方法，将数据选择建模为分布匹配与质量过滤的联合优化问题，经多类数据、模型及基准评估，其在多项任务上优于现有基线及全量数据训练。

链接：https://arxiv.org/abs/2611.08495

机构：Nanjing University（南京大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； Fudan University（复旦大学）； Zhejiang University（浙江大学）； Institute of Information Engineering（信息工程学院）

作者：Peng Sun, Yi Yang, Mingshuo Chen, Chunxiao Li, Yao Zhu, Huawen Shen, Tianfan Fu

英文摘要：Instruction tuning of large language models and large vision language models relies on massive training data, which incurs substantial computational and storage costs. Meanwhile, training data often contains redundancy, noise, and low quality samples. Existing data selection methods mostly rely on diversity, importance, or a combination of both, without explicitly constraining the distributional consistency between the selected subset and the full data in the embedding space. We propose QMAC, a quality aware multiband characteristic function matching method that formulates data selection as a joint optimization problem of distribution matching and quality filtering. QMAC matches the empirical characteristic functions of the selected subset and the full data across multiple frequency scales, capturing both global semantic coverage and local perturbations, while using task related quality scores to filter noisy and low quality samples. We systematically evaluate QMAC on 4 data types, 8 target models, and 44 benchmarks. Experimental results show that QMAC outperforms existing data selection baselines on standard image-text instruction data, substantially surpasses random selection on standard text instruction, image-text reasoning, and text reasoning data, and exceeds full data training in multiple model and budget combinations. The code will be made publicly available upon acceptance of the paper.

AI 总结：本研究探究地理语境对LLM零样本CKD筛查的影响，发现CKD阳性预测具地理敏感性，非CKD预测稳定，国家token的内部表示影响结果，为医疗场景部署LLM提供启示。

链接：https://arxiv.org/abs/2611.08507

机构：Rensselaer Polytechnic Institute（伦斯勒理工学院）； Charles Sturt University（查尔斯达尔文大学）

作者：Sirajam Munira, Muhammad Ashad Kabir

英文摘要：Large language models (LLMs) show strong zero-shot reasoning capabilities, yet their sensitivity to prompt context raises questions about reliability in deployment. This study investigates whether geographic context embedded in prompts influences LLM-based chronic kidney disease (CKD) screening, independent of any change in patient features. Using a community-based CKD dataset from Bangladesh (284 participants with 112 CKD and 172 non-CKD), we systematically varied the country attribute across 25 global contexts while holding all clinical inputs constant, and evaluated two open-weight LLMs (Qwen3 8B and Mistral 7B). Experiments were conducted on a common-correct subset of 156 participants for whom both models produced correct baseline predictions. Results show that non-CKD predictions were highly stable across geographic contexts, with both models maintaining consistent non-CKD predictions in nearly all settings. In contrast, CKD-positive predictions were considerably more sensitive. For Qwen3, CKD prediction dropped from a baseline of 65 to as low as 50 across country contexts, while Mistral showed smaller but non-negligible variation. Country contexts did not group according to known epidemiological or healthcare similarities; instead, groupings appear to reflect how country tokens are internally represented within each model. These findings demonstrate that geographic tokens can systematically shift clinical screening outcomes despite identical patient inputs, with implications for the deployment of LLM-based decision support in diverse healthcare settings.

AI 总结：本研究针对核反应堆流动建模的高保真CFD模拟成本高的问题，对比MFNN与可解释MFKAN，发现MFKAN精度与MFNN相当且提供符号方程，合成数据增强后跨保真度预测仍受限于保真度相关性。

链接：https://arxiv.org/abs/2611.08512

机构：University of Michigan（密歇根大学）

作者：Meredith Eaheart, Majdi I. Radaideh

英文摘要： High-fidelity computational fluid dynamics (CFD) simulations of nuclear reactor systems are computationally expensive, motivating machine learning methods that reduce cost while preserving accuracy. Multifidelity surrogate modeling addresses this by combining inexpensive low-fidelity data with limited high-fidelity data. This work investigates whether the high-fidelity data required to predict the spatiotemporal mass flow rate across all 193 fuel assemblies of a pressurized water reactor (PWR) core can be reduced, comparing black-box multifidelity feedforward neural networks (MFNNs) with interpretable multifidelity Kolmogorov-Arnold Networks (MFKANs). Cross-fidelity correlation across the core is weak, making this a challenging multifidelity problem, and neither architecture predicts the transient particularly well in absolute terms. MFKAN nonetheless performs comparably to MFNN for one-time-step-forward prediction while also providing closed-form symbolic equations unavailable with MFNN. To address the scarcity of CFD transients, with only one available per fidelity level, TabDDPM-generated synthetic data was used to augment cross-fidelity forecasting. KAN and FNN achieve comparable self-evaluation accuracy (Pearson correlation of roughly 0.73--0.81), but both perform poorly at true cross-fidelity forecasting (correlations of 0.03--0.06). Assembly-level analysis shows that each assembly's forecast correlation tracks its real cross-fidelity correlation for both architectures ($r=0.840$--$0.896$ for KAN, $r=0.804$--$0.903$ for FNN), confirming that forecasting accuracy is fundamentally limited by how correlated the fidelity levels already are. Overall, KAN-based multifidelity modeling achieves accuracy consistently comparable to MFNN across all settings, while additionally providing symbolic equations that match or exceed the spline representation's accuracy.

AI 总结：该研究提出MSKC原则，将其应用于风能骤增事件预测分析，实现自适应知识路由，在保持预测性能的同时减少64%的知识调用，验证了无需统一最大智能的结论。

链接：https://arxiv.org/abs/2611.08558

机构：University of Southern Denmark (SDU)（南丹麦大学）

作者：Purbak Sengupta, Aparna S. varde, Emil Jørgensen Njor

英文摘要：Resource-constrained cyber-physical decision systems often apply fixed sensing, knowledge, and computational pipelines despite state-dependent information needs. We introduce Minimum-Sufficient Knowledge and Computation (MSKC), a resource-aware computing principle: select the least-costly route meeting decision-risk and deployment constraints, escalating only when cheaper routes are insufficient. As proof of concept, we isolate adaptive knowledge routing, the decision underlying Knowledge-Guided Machine Learning (KGML), which conventionally injects external knowledge unconditionally rather than only where needed. We instantiate this for wind ramp-event predictive analysis, an edge-oriented decision-support task, evaluating local, relational, and physics-informed routes with a state-aware gate on publicly available real data from two wind farms. We establish conditions for feasibility preservation, cost dominance, and strict expected savings over always-on routing. At a 35.9% relational-knowledge injection rate, adaptive routing is statistically indistinguishable from always-on injection on the reported metrics while reducing knowledge calls by 64%, supporting sustainable, Green-IT-aligned deployment. These results support MSKC's premise that uniformly maximal intelligence is unnecessary. This offers intelligent data analysis for big data streams: the analysis itself decides, per state, how much knowledge and computation the data warrant.

AI 总结：该研究将UniTraj、TrajFM等轨迹基础模型的残差作为城市公交异常的候选信号，结合NetMob26等多源数据，通过XAI分析残差的空间分布与关联变量，为城市范式评估提供新视角。

链接：https://arxiv.org/abs/2611.08703

机构：Institute for Computer Science and Control, Hungarian Research Network（匈牙利研究网络计算机科学与控制研究所）

作者：Csaba I. Sidló, Jamil J. Ghazal, Domonkos Rózsay, Rita Rónai, András J. Molnár

英文摘要：Pretrained trajectory models encode mobility patterns learned across cities, but their errors when transferred to a new city are usually treated only as performance limitations. We instead ask whether these residuals reveal systematic local conditions. Architectures such as UniTraj and TrajFM learn transferable trajectory representations, although cross-context transfer remains challenging. Using the NetMob26 bus location, ticketing, weather, network, and socioeconomic data for Niteroi, we analyze spatial and travel-time residuals of these recent trajectory foundation models. We test whether high residuals concentrate spatially, whether spatial and travel-time residuals overlap, and which urban-context variables explain their distribution. We interpret high residuals as candidate proxy signals of transit irregularity rather than direct evidence of service disruption, and analyze their contextual associations using Explainable AI (XAI). Insights into such varied environments are increasingly valuable for evaluating new urban paradigms; for instance, the 15-minute-city perspective serves as a key motivation for our approach, guiding our methods and expanding the analysis beyond standard mobility metrics.

AI 总结：该研究针对零阶优化的维度诅咒问题，提出从激活几何推导搜索方向的谱零阶方法SZO-κ，提升梯度对齐度，为非传统硬件上的学习算法提供有效替代方案。

链接：https://arxiv.org/abs/2611.08712

机构：Donders Institute for Brain, Cognition, and Behaviour（唐德斯脑、认知与行为研究所）； Radboud University（拉德堡德大学）

作者：Justus Huebotter, Serge Thill, Marcel van Gerven, Nasir Ahmad

英文摘要：As novel hardware architectures are explored for the purposes of machine learning, including neuromorphic chips, asynchronous systems, and ASICs, effective learning algorithms are highly desirable. While backpropagation is the standard for differentiation on standard hardware, its requirement for global synchrony and exact differentiability limits the exploration of exotic algorithms on non-traditional substrates and devices. Zeroth-order (ZO) optimisation methods, such as SPSA and weight perturbation, offer a compelling alternative by estimating gradients through inference-only passes; however, these methods have historically suffered due to the `curse of dimensionality', where random perturbations become increasingly misaligned with the true gradient in high-dimensional spaces. In this work, we move beyond blind random noise by deriving zeroth-order search directions from activation geometry available during the forward pass. This leads to a family of Spectral Zeroth-Order methods, SZO-$\kappa$, whose directions solve local response-based gradient-guessing objectives under explicit stochastic assumptions. These methods explore feature-supported directions that are more likely to produce informative loss responses. Using multilayer and convolutional networks, we analyse gradient alignment, bias-variance structure, and training stability of these methods relative to standard perturbation baselines and backpropagation.

AI 总结：该研究针对冻结的梯度提升树欺诈检测器的盲区，提出基于LLM的可逆规则叠加框架，融合三种LLM主干，在真实电商和公开基准数据集上显著提升了欺诈检测的精度与召回率。

链接：https://arxiv.org/abs/2611.08714

机构：eBay（亿贝）

作者：Bo Qu, Zhurong Wang, Frank Zahradnik, Ming Ouyang

英文摘要： In industrial tabular fraud classification, gradient-boosted trees remain state-of-the-art, but even a well-trained model has blind spots, and retraining the deployed model is not always safe. We propose a framework that patches such a model without modifying it: LLMs propose rules anchored on features the model underweights by SHAP, and the resulting noisy pool is screened for empirical support and calibrated into an additive, reversible log-lift overlay that runs at the production cut-off. Single-LLM benefit is high-variance and inverts between datasets, so we pool three diverse backbones by equal-weight logit averaging, trading peak gain for a bounded worst case. On a real-world e-commerce fraud detector trained on selection-biased data, continued training regresses even when carefully tuned, whereas the overlay gains on average +2.26% recall at equal precision ($\Delta$R@P) and +1.60% precision at equal recall ($\Delta$P@R) over production cut-offs spanning 30-57% precision and 23-63% recall. On a public benchmark of seven designed bias-shift variants it raises $\Delta$P@R on every variant and keeps $\Delta$R@P near neutral. Each amendment is a readable predicate naming the fraud pattern it covers.

AI 总结：本文提出随机符号提升（RSB）方法，通过对随机生成的语法树群体提升构建加性符号模型，引入自适应几何早停机制，在符号回归基准上达帕累托最优，真实数据集排名第一，表格分类基准表现具竞争力。

链接：https://arxiv.org/abs/2611.08753

机构：Tecnológico Nacional de México/Instituto Tecnológico de Tijuana（墨西哥国立理工学院/蒂华纳理工学院）； Universidad Autónoma de Baja California（下加利福尼亚自治大学）

作者：José R. Ortegaa, José Manuel Muñoz Contreras, Leonardo Trujillo

英文摘要：Symbolic models offer interpretability, but their construction through generational evolution can be computationally expensive. This article presents Random Symbolic Boosting (RSB), a method that constructs explicit additive symbolic models via boosting over populations of randomly generated syntax trees, eliminating the need for generational evolution. The idea combines two observations: high-dimensional spaces can be spanned by enough linearly independent vectors, and the semantics of syntax trees can be directly manipulated as such vectors. It is shown that, for Ordinary Least Squares, the boosting process guarantees a monotonic reduction of the training error for both regression and classification. Furthermore, an adaptive geometric early stopping mechanism is introduced. It is based on the angle between the prediction and target vectors, is independent of the problems scale, and requires no adjustments across tasks. Evaluated on a standard benchmark for symbolic regression, the method is located at the Pareto-optimal point between predictive accuracy and training time, ranking first on the real-world datasets. Additionally, it was tested on a large tabular classification benchmark with 200 problems, achieving competitive results.

AI 总结：提出TopoSHAP框架，通过TopoSHAP-cell和TopoSHAP-neighbor分别解释拓扑结构与模型架构，在GraphXAI基准上效率提升，可识别更优架构并降低训练成本。

链接：https://arxiv.org/abs/2611.08789

机构：University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）

作者：Mathilde Papillon, Nina Miolane

英文摘要：Topological deep learning (TDL) extends learning on graphs, such as molecules or social networks, to higher-order structures, such as rings in a molecule or groups in a social network. Explaining which of these structures drive a model's predictions, and which architectural components matter most for its performance, remains challenging. We introduce TopoSHAP, an efficient and general explanation framework that addresses both questions across topological domains and model architectures. TopoSHAP-cell assigns Shapley values to topological data cells and extracts compact explanations. These explanations match or outperform graph-based counterparts on GraphXAI benchmark data while running up to 112$\times$ faster. They also reveal advantageous topological feature design, leading to measured improvements in explanation recovery and predictive accuracy. On the architecture side, TopoSHAP-neighbor explains how neighborhoods contribute to model performance, and turns these evaluations into a backward-elimination search that identifies smaller, competitive architectures early in training. This is up to $11.3\times$ cheaper than traditional TDL training sweeps.

AI 总结：针对冷启动电商广告的LLM角色模拟，研究确定三类关键信号形式维度，提出的方法MAE较非LLM基线降51.3%、较特定LLM配置降77.3%，验证了极简人口统计描述与相对定性线索的优势。

链接：https://arxiv.org/abs/2611.08840

机构：Dosan International（斗山国际）； SolverX

作者：Jiwoo Choi, In Ik Lee, Woo Sung Seo, Minho Lee, Yun Young Choi

英文摘要：Estimating advertising performance in cold-start settings is challenging because historical logs are unavailable before launch. Large language models (LLMs) offer a potential alternative by simulating persona-conditioned user responses, but it remains unclear which design choices actually drive LLM-based persona simulation. Using real Google Ads e-commerce campaign data across five demographic segments, we identify three signal-form dimensions that affect simulation quality: (i) a demographic anchor without noisy rich attributes, (ii) a relative qualitative banner-blindness signal rather than quantitative anchors, and (iii) prompt phrasing. On this campaign, our method attains an MAE of 24.9 and a MAPE of 26.1%, a 51.3% lower MAE than the best tested non-LLM baseline and 77.3% lower than an LLM configuration using explicit CTR anchors. Systematic ablations show that minimal demographic descriptions achieve lower mean error than richer persona configurations, while relative qualitative cues substantially outperform the tested quantitative anchors. We additionally compare these configurations with direct-prior and rule-based baselines and with alternative LLM configurations.

AI 总结：该研究针对LLM谱系无法验证的问题，提出TRACE-Edge方法，通过微调路径推断重构有向模型树，在25个模型树配置上父匹配准确率达0.74，优于输出相似度基线。

链接：https://arxiv.org/abs/2611.08866

机构：Institute of Science Tokyo（东京科学研究院）； RIKEN（理化学研究所）

作者：Sota Ogawa, Shojiro Yamabe, Daiki Nishiyama, Jun Sakuma

英文摘要：Fine-tuned (FT) derivatives of large language models (LLMs) are now released in large numbers, yet their provenance relies on self-reports and cannot be verified. Misattributed lineage leaves a verifier unable to audit outsourced fine-tuning, confirm license compliance of derived models, or trace vulnerabilities that a parent passes to its children. All three require the direction of derivation, not merely its presence. Existing output-only methods are limited to pairwise derivation tests or undirected lineage estimation, while recovering a directed tree requires white-box access to model weights. We formalize the problem of reconstructing a directed model tree, including internal nodes, under gray-box access, where only teacher-forced log-likelihoods are observed and weights are never inspected. Fine-tuning raises the log-likelihood of the training data, and a child inherits this increase from its parent. Building on this property, we define an asymmetric per-task log-likelihood deviation between any two models as a trace of fine-tuning history, and derive from it an edge weight for each ordered pair of models. We propose TRACE-Edge, which exactly solves for the maximum spanning directed tree under these edge weights, with neither hyperparameters nor tree-structure constraints. We evaluate it on five configurations totaling 25 model trees built from three base models and seven tasks. TRACE-Edge achieves a parent-match accuracy of 0.74 when probed with the fine-tuning examples, and on average outperforms an output-similarity baseline even with held-out probes drawn from the same distribution as the training data.

AI 总结：该研究针对现有手动设计重启规则的缺陷，开发了基于连续时间极限的可微重启策略框架，通过代理梯度训练的重启策略在二次规划等任务上表现更优且具备零样本迁移能力。

链接：https://arxiv.org/abs/2611.08883

机构：Tsinghua University（清华大学）； Peking University（北京大学）

作者：Yiman Fong, Zhonglin Xie, Zaiwen Wen

英文摘要：Adaptive restart mechanisms, which reset the momentum or other auxiliary state of an iterative optimizer, play a central role in the empirical performance of accelerated first-order methods, yet existing restart rules remain almost entirely hand-designed. The obstruction to learning restart policies is that, unlike the typical Learning to Optimize (L2O) setting, the discrete restart events make the resulting trajectory non-differentiable in the algorithm parameters and thus block gradient-based optimization of the restart policy. We resolve this obstruction by developing a differentiable framework for restart policies through their continuous-time limit. We introduce surrogate gradients for the restart events and optimization trajectories that are efficient to compute and provably converge to their continuous-time counterparts. We validate the effectiveness of our surrogate gradients in L2O settings, training restart policies that improve upon standard handcrafted adaptive restart criteria on quadratic and linear programs, and that transfer zero-shot from synthetic quadratics to logistic regression on real datasets.

AI 总结：该研究针对PPO固定裁剪范围的缺陷，提出有序策略优化（OPO），通过小批量排序重要性比率并为极端比率分配自适应样本级半径，在MuJoCo和Atari基准上实现了优于基线的性能。

链接：https://arxiv.org/abs/2611.08936

机构：Duke University（杜克大学）

作者：Dongkyu Derek Cho, Pan Xu

英文摘要：Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers simplicity and effectiveness, it fails to distinguish statistically harmful extreme ratio values from large, yet tolerable changes. We study how to adapt the clipping radius to the reliability of the induced importance ratio distribution. Our case study demonstrates that reliable updates require controlling these extreme ratios, rather than merely verifying that individual ratios fall within a fixed interval. Motivated by this observation, we propose Ordered Policy Optimization (\textsc{OPO}). In each minibatch, \textsc{OPO} sorts the importance ratios, selects the extreme ratios that potentially have the largest effect on the update, and assigns them adaptive sample-wise radii instead of using the fixed clipping radius. These radii are derived from a prescribed tail profile, which specifies desired target values for the selected extreme ratios. The resulting objective remains first-order and requires only minibatch sorting and a modified policy loss. Experiments conducted on MuJoCo and Atari benchmarks demonstrate that this simple modification achieves strong performance relative to established baselines.

AI 总结：针对机器学习模型选择的需求，提出结合预测精度与模型复杂度的复合指标SQS，通过加权乘积整合二者，可控制精度-复杂度权衡，为模型选择提供系统客观的方法。

链接：https://arxiv.org/abs/2611.08937

作者：Maaz Ahmad, Iftekhar A. Karimi

英文摘要：The growing reliance on high-fidelity, state-of-the-art machine learning based models for engineering decision-making necessitates robust and systematic approaches for model selection. While high predictive accuracy at untrained points is a necessary trait in the final model, other attributes such as model complexity, forecastability, explainability, scalability, and physics-awareness may be equally important or relevant criteria depending on application context and user requirements. In this work, we propose a novel composite performance metric, Surrogate Quality Score (SQS) for model selection based on predictive accuracy and model complexity simultaneously. SQS heuristically integrates these two attributes through a weighted product of normalized measures, yielding a unified score to reflect overall model quality. A user-specified parameter in SQS enables explicit control over the accuracy-complexity trade-off, thereby incorporating human judgement and preference in the model selection process. We extensively discuss and justify the formulation of SQS and demonstrate its utility through an illustrative example. By combining predictive accuracy and model complexity, SQS offers a systematic and objective approach for model selection based on both attributes.

AI 总结： 该研究指出弱监督器的价值应基于学生模型的继承内容，提出学生相关价值的判定方法，证明结合干净标签的弱监督器优于仅用干净标签的方法。

链接：https://arxiv.org/abs/2611.08959

机构：Brown University（布朗大学）

作者：Romano Li, Xunfan Cai

英文摘要：Weak supervisors are usually judged by their own errors, but what matters is what a student learns from them. For squared loss and any linear learner shared by all supervisors, we show that a supervisor's value is determined by its errors after they pass through the student's learning operator. Consequently, the inner products of the supervisors' raw errors can be compatible with every feasible value of the student's risk, and weighting supervisors by them can be arbitrarily worse than the best weighting in relative excess risk. This student-relative value is not identifiable from unlabeled data, but what is missing is small: one finite-dimensional projection of the target decides whether training on a weak aggregate helps, another decides how to weight the supervisors. Known teacher training rules, or a label-model condition stated in student-relative form, shrink it further. Clean labels close the remaining gap at a cost set by the geometry of the unresolved directions rather than by the dimension of the student's representation, with matching worst-case lower bounds. In Gaussian designs we also quantify when exact teacher structure beats ordinary stacking and when weak supervisors, combined with clean labels, beat every procedure that uses the clean labels alone. The guarantees extend to fitted ridge students and finite unlabeled data.

AI 总结：本文提出KnowEvo框架，将外化知识作为优化目标，通过策略变异树等实现知识演化，在蛋白质优化任务上优于基线方法，可持续改进专业知识。

链接：https://arxiv.org/abs/2611.09013

机构：Dalian University of Technology（大连理工大学）

作者：Zijie Xing, Xingyue Liu, Runze Wang, Luoming Hu, Yanming Shen

英文摘要：Large language models (LLMs) have shown promise in scientific discovery, yet systematically accumulating and refining reusable scientific knowledge remains challenging. Existing approaches primarily improve LLM-based problem solving through parameter optimization or feedback-driven refinement of prompts, programs, and solution trajectories, leaving acquired expertise either embedded in model weights or scattered across iterative problem-solving processes. As a result,knowledge is difficult to systematically inspect, evaluate, and refine. We propose KnowEvo, a framework that treats externalized knowledge itself as the optimization target. Our key insight is that scientific knowledge is inherently modular: multiple interacting mechanisms jointly determine the design outcomes. This makes knowledge evolution fundamentally challenging, as improvements cannot be attributed to individual components in isolation. To address this, KnowEvo represents knowledge as executable expertise blocks and organizes their refinements into strategy mutation trees, enabling structured exploration over a combinatorial knowledge space. The framework combines a Thompson-style forward allocation strategy that adaptively distributes evaluation budgets across strategy variants with a backward revision process, in which a code agent operates in an isolated sandbox to translate rollout evidence into localized program updates. This design enables persistent accumulation, evaluation, and refinement of mechanistic expertise across iterative experimentation. We evaluate KnowEvo on protein optimization tasks including stability and solubility. Results show that knowledge evolution consistently improves over initial strategy blocks and outperforms monolithic program evolution and prior LLM-guided evolution baselines across metrics such as pass@k, MRR, MAP,and NDCG@5. Code is available at this https URL.

AI 总结：本研究审计蛋白质语言模型ESM-2的高阶上位性互信息估计，发现部分估计器族在特定维度下可稳定估计值，但现有稳定估计器不足以支持盲搜索下的阶分辨依赖性主张，并提出可复用诊断协议。

链接：https://arxiv.org/abs/2611.09046

机构：University of Central Florida（中佛罗里达大学）

作者：Maryam Rahimimovassagh, Waldemar Karwowski, Niloofar Yousefi

英文摘要：Mutual information (MI) estimation is used to probe what neural representations encode, including in protein language models, but variational MI estimators have variance that scales at least exponentially in the true MI. We audit a prior neural-MI study of order-resolved epistasis in ESM-2 on the four-site GB1 landscape. Run-to-run differences show no systematic bias and a magnitude comparable to ordinary cross-seed retraining variability, and the evaluation-pairing scheme shifts scores substantially. At the original dimensionality, two of three alternative estimator families stabilize the estimate across seeds and one does not. In a synthetic calibration at the representation dimensionalities of two other protein language models (a Gaussian channel with known MI; no model representations), all three families recover materially less signal than required, despite correct signal ordering and stable seeds. A control critic given the true signal direction, which also reduces its input to one dimension, recovers 93.3% and 98.7% of the analytic MI at gain 1.5 (at 5,120 and 4,096 dimensions), so the signal is recoverable with privileged information, but the control does not identify why blind estimation fails. We package the checks into a reusable diagnostic protocol and conclude that even a stabilized estimator is not currently sufficient for order-resolved dependence claims made under blind search at this dimensionality and sample size.

AI 总结：研究人员推出LeanDojo-v2端到端框架，整合多项定理证明相关功能，搭配Lean4Code轻量IDE，助力相关人员便捷开展LLM辅助定理证明实验。

链接：https://arxiv.org/abs/2611.09048

机构：National Taiwan University（台湾大学）； Washington University in St. Louis（圣路易斯华盛顿大学）； California Institute of Technology（加州理工学院）

作者：Ryan Hsiang, William Adkisson, Robert Joseph George, Anima Anandkumar

英文摘要： Building on recent progress in machine learning for formal theorem proving in Lean, we introduce LeanDojo-v2: an end-to-end framework that unifies repository data extraction, LLM fine-tuning, proof search, AI autocompletion, and LLM-assisted theorem proving in a single software library. In addition, we provide Lean4Code, a lightweight IDE that integrates the various features of LeanDojo-v2 through a simple, mathematician-friendly UI. These tools will enable mathematicians and researchers to easily fine-tune language models on domain-specific Lean codebases and experiment with LLM-assisted theorem proving without a complex setup.

AI 总结：提出WearableBridge方法，固定参考编码器与分类器，通过任务引导迁移映射提升仅腕戴设备的自由生活活动识别效果，在多数据集上显著提升宏F1值，训练成本低且可复现。

链接：https://arxiv.org/abs/2611.09067

作者：Jingjing Zou, Yixin Wang

英文摘要：Wrist-worn accelerometers make activity monitoring feasible at scale, but incidental arm motion, device orientation, and shifting context blur the signal that separates activities. Calibration studies supply higher-quality references such as concurrent thigh recordings or supervised laboratory wrist sessions, but they are expensive, cover few participants, and are rarely available at deployment. How can limited reference data improve recognition for participants who wear only a wrist device? We propose WearableBridge, which holds the reference encoder and classifier fixed and learns a task-guided transport map, the bridge, that carries each wrist feature into the region the classifier associates with its activity. Reference features or the classifier's predictions indicate the destination, and a classification loss penalizes wrist features that land in the region of another activity. We instantiate WearableBridge with three bridges: Mapper regresses onto reference features, Distillation matches the classifier's class probabilities, and MeanFlow learns a one-step flow from wrist toward reference features. On 40 held-out free-living PAAWS participants, all three bridges improve macro-F1 in every training run, and the strongest, MeanFlow, raises mean macro-F1 from 35.1% to 56.0% with concurrent thigh references (Thigh2Wrist), and from 54.0% to 63.5% with group-matched laboratory wrist references (Lab2Freeliving). Fitted only on PAAWS, MeanFlow also raises macro-F1 on the CAPTURE-24 cohort from 42.8% to 54.7%. The gains replicate on selfBACK, hold across four reference encoders, and grow with temporal context. A study can therefore collect reference recordings for a calibration subset and improve wrist-only recognition for every other participant, training only a bridge of 0.13 to 2.44 million parameters while the reference encoder and classifier stay unchanged.

AI 总结：本研究提出BrainCoT，一种多任务零样本脑信号基础模型，通过神经测量锚定思维链推理实现零样本分类，在无下游训练数据时性能优于仅用1%标记数据训练的线性探测基线。

链接：https://arxiv.org/abs/2611.09082

机构：New Cornerstone Science Laboratory（新基石科学实验室）； Guangdong Provincial Key Laboratory of In-Memory Computing Chips（广东省存算芯片重点实验室）； Shenzhen Graduate School, Peking University（北京大学深圳研究生院）； Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省超高清沉浸式媒体技术重点实验室）； Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）

作者：Yiyu Gui, Mingzhi Chen, Guibo Luo, Yuchao Yang

英文摘要：Brain signals exhibit substantial multi-center heterogeneity, strong inter-subject variability, and highly diverse task settings, which makes it difficult to build models that generalize beyond a single task. While recent brain signal foundation models leverage large-scale pretraining to learn generalizable representations, they often fall short in practice because they still require target-data-specific supervised adaptation, lack multi-task zero-shot capability, and rarely provide verifiable evidence to support their predictions. In this work, we present BrainCoT, a multi-task zero-shot Brain signal foundation model with neurometric-anchored Chain-of-Thought (CoT) reasoning. BrainCoT unifies heterogeneous tasks into an instruction-driven framework so that, after pretraining, a single model can be directly applied to multiple tasks in zero-shot settings without additional adaptation. It further introduces neurometric-anchored chain-of-thought grounded in neurometric evidence for verifiable reasoning, and adopts Decision-Consistent Rationale Training to keep process learning aligned with correct predictions. Across extensive evaluations, BrainCoT achieves an average ACC of 67.41% and AUC of 74.33% in zero-shot classification without downstream training data, outperforming the strongest linear-probing baseline trained with 1% labeled downstream data by 3.85% in ACC and 5.97% in AUC.

AI 总结：本研究提出自动化流程COMBIO，将常规实验室检测面板的机器学习模型提炼为紧凑复合生物标志物，在6项任务中其性能与逻辑回归接近，可用于临床结局预测。

链接：https://arxiv.org/abs/2611.09102

机构：Stein Faculty of Computer and Information Sciences, Ben-Gurion University of the Negev（内盖夫本-古里安大学斯坦因计算机与信息科学学院）； Clalit Research Institute, Clalit Health Services（克拉利特医疗服务克拉利特研究所）

作者：Tomer D. Meirman, Lior S. Rokach, Bracha Shapira, Seffi Cohen, Noa Dagan

英文摘要：Machine-learning models based on routine laboratory panels can predict outcomes but can be difficult to interpret and operationalize. We present COMBIO, an automated pipeline that distils such a model into a compact closed-form biomarker. The composite is a product of laboratory measurements raised to integer powers from minus two to two. The sign of each exponent indicates whether higher values of the corresponding measurement increase or decrease the composite. Shapley additive explanation values from the gradient-boosted reference model rank five candidate measurements and guide eligible exponent signs. An exhaustive search over small integer exponents selects the formula on an inner validation set, before evaluation on the reserved test set. We evaluated COMBIO across six tasks: three National Health and Nutrition Examination Survey outcomes, liver-disease classification in the Indian Liver Patient Dataset, and Medical Information Mart for Intensive Care IV in-hospital mortality and sepsis case-finding, with external evaluation in the eICU Collaborative Research Database for the two hospital tasks. Across the six test sets, COMBIO's area under the receiver operating characteristic curve differed by at most 0.03 from logistic regression using the five candidate laboratory measurements. The hospital mortality composite had an area under the curve of 0.698 in the external database. A version restricted to widely available measurements in the source hospital database achieved an area under the curve of 0.786 in a cohort covering 92% of admissions. The multiplicative representation provides compactness rather than additional accuracy, and local validation and recalibration are required before clinical use.

AI 总结：提出连续字典追踪（CDP）框架，解决信号分解的网格失配问题，在合成与真实数据集上实现最优稀疏性-准确率权衡，还可作为序列模型训练的结构化目标提升预测精度。

链接：https://arxiv.org/abs/2611.09163

机构：Institute of Information Processing（信息处理研究所）； Leibniz University Hannover（汉诺威莱布尼茨大学）

作者：Nick Janssen, Melanie Schaller, Bodo Rosenhahn

英文摘要：Deep learning models achieve high accuracy in signal processing but remain difficult to interpret. Classical matching pursuit and sparse coding offer better transparency but suffer from spectral leakage and grid mismatch when signal frequencies do not align with discrete dictionary atoms. We introduce Continuous Dictionary Pursuit (CDP), a framework for interpretable signal decomposition that learns the parameters of closed-form functions directly from data. CDP optimizes over a continuous manifold of differentiable atoms and, unlike prior continuous pursuit methods that operate on a single analytic family, searches a heterogeneous library spanning periodic, trend, transient, and discontinuous structures. The algorithm employs a greedy iterative strategy using data-driven priors and gradient-based optimization to isolate individual signal components, with discontinuous waveforms made differentiable through spectral sharpness annealing. To ensure a sparse atom set for reconstruction, the framework utilizes a stopping criterion based on a predefined atom budget and residual error convergence. Evaluations on synthetic and real-world datasets show that CDP removes the grid discretization error for atom families contained in its library, recovers generative parameters to within $1\%$ on stationary synthetic signals expressible in that library, and achieves the best sparsity-accuracy trade-off among classical, continuous-pursuit, and neural baselines in the sparse regime. Beyond decomposition, we demonstrate that the extracted atoms can serve as structured curriculum targets for training sequence models, improving forecasting accuracy over standard end-to-end training on most evaluated datasets. The method offers a glass-box alternative for signal decomposition by providing high reconstruction fidelity alongside direct physical interpretability.

AI 总结：RoleWalk是一种无训练的有向图结构嵌入，仅依赖节点固定半径邻域，可跨图迁移，在多基准任务上表现优异且效率高。

链接：https://arxiv.org/abs/2611.09189

机构：Trickstr（特里克斯特（Trickstr））

作者：Maixent Chenebaux

英文摘要：Structural role embeddings describe a node by its position in a graph - hub, bridge, periphery, member of a dense core - rather than by who its neighbours are. Existing methods either learn coordinates specific to one graph (struc2vec, Role2Vec, RESD) or read scales and normalisations from the whole graph (GraphWave, Digraphwave), so the same neighbourhood can receive different coordinates in two graphs; few read edge directions. We present RoleWalk, a training-free embedding that follows a short lazy random walk from each node and records, at each step, two distributions: that of the transition probabilities, through its characteristic function at a fixed grid of frequencies, and that of the walker's distance to its starting node. On directed graphs, walks that go forward then backward add who shares a node's targets or sources. The embedding depends only on a node's neighbourhood within a fixed radius, so its coordinates mean the same thing in every graph. We show that, without curvature, it is the kernel mean embedding of the walk's footprint, that it separates graphs that the Weisfeiler-Leman test cannot, and that pruning small probabilities comes with a per-node error certificate. Empirically, RoleWalk is competitive with the best role embeddings on five classification benchmarks at a fraction of their cost, has the highest scores on real directed roles in Wikipedia adminship, exceeds the published accuracy of Digraphwave at every noise level of its own Enron network-alignment benchmark, transfers centrality predictors to graphs four times larger better than existing inductive embeddings, hand-made features and a trained GIN, and embeds a million nodes in 20 s to 3 min on one CPU core. The code is open source (BSD license): this https URL

AI 总结：提出跨层TopK为CLT设置单一L0预算并动态分配到各层，在Qwen3-8B-Base上实现更低FVU、更少活跃潜在变量，还提升电路追踪效果与训练速度。

链接：https://arxiv.org/abs/2611.09233

作者：Anyuan Zhuo, Shaohua Zhang, Tianle Li, Yuan Lin, Diandian Gu, Jun Wang, Pinyan Lu

英文摘要：Cross-Layer Transcoders (CLTs) decompose the activations of large language models into human-interpretable features and trace how these features interact across layers to form circuits, making them a key tool for mechanistic interpretability. However, training CLTs effectively and efficiently is hard. Beyond the usual trade-off between sparsity and reconstruction quality, a CLT has to model all layers at once, which adds a further challenge. The common JumpReLU recipe controls sparsity only indirectly through a penalty, while the direct extension of TopK selects a fixed number of latents in every layer. Yet reconstruction difficulty differs widely across layers, and intermediate layers are much harder than others, so giving every layer the same budget is suboptimal. We propose Cross-Layer TopK, which sets a single L0 budget for the whole model and dynamically allocates it across layers during training. In a comparison with JumpReLU and other TopK variants on Qwen3-8B-Base, this gives lower FVU while using 20% fewer active latents than JumpReLU. The better reconstruction carries over to circuit tracing, yielding more complete circuits with higher replacement and completeness scores. The fixed per-token budget of Cross-Layer TopK also makes it easy to pair with sparse decoding, which cuts both computation and communication and gives a 2.9x speedup per training step. We further show that Cross-Layer TopK follows scaling laws in both latent size and sparsity. We have open-sourced the weights of our CLT at this https URL.

AI 总结：OpenYieldV2将拓扑作为可优化变量，通过参数化编译器、小样本TabPFN代理和多目标优化器，实现SRAM架构与尺寸的联合优化，使超体积最高提升17.3%，且为开源工具。

链接：https://arxiv.org/abs/2611.09248

机构： Nanjing University of Sci.&Tech.（南京理工大学）； Institute of Microelectronics of the Chinese Academy of Sciences（中国科学院微电子研究所）； University of Sheffield（谢菲尔德大学）

作者：Can Wang, Junhao Ma, Yikai Wang, Shan Shen, Wei W. Xing

英文摘要：SRAM's power-performance-area-stability trade-off depends on bitcell topology, a discrete architectural choice that interacts non-separably with continuous transistor sizing. However, no open-source SRAM tool treats topology as an optimizable variable. OpenRAM generates SRAM layouts but performs no optimization, while OpenYield supports high-fidelity evaluation but restricts optimization to scalar sizing of a fixed 6T cell. OpenYieldV2 closes this gap through three integrated contributions. First, a fully parameterized compiler generates complete 6T and 10T SRAM macros with peripheral circuits and replica-bitline self-timing, enabling topology comparison under identical simulation conditions. Second, a few-shot TabPFN surrogate learns topology-dependent PPA responses with limited full-macro SPICE samples. Third, a coarse-to-refined multi-objective optimizer combines global exploration of discrete architectural choices with local refinement of continuous transistor sizes. Experiments across varying design conditions reveal a topology decision boundary that shifts with operating constraints rather than following a fixed design rule. Jointly optimizing across this boundary improves hypervolume by up to 17.3\% over the strongest single-topology baseline. OpenYieldV2 is open-source to support reproducible SRAM design research.

AI 总结：该研究提出Lipschitz训练方案，使嵌入网络具备L-Lipschitz属性，结合基于原型的分类头与Lipschitz约束型嵌入，在三类数据集和三种攻击下实现更强的经验鲁棒性。

链接：https://arxiv.org/abs/2611.09327

机构：Faculty of Technology, Bielefeld University（比勒费尔德大学技术学院）

作者：Adia Khalid Khan, Lukas Gehring, Benjamin Paaßen

英文摘要：Robustness and interpretability are interrelated and desirable properties of machine learning models. A model that changes its prediction under imperceptible perturbations behaves inconsistently with human-recognizable features and, hence, is not interpretable. Prototype-based classifiers such as Generalized Learning Vector Quantization address both at once. They are interpretable by construction because they make the decision by comparing the input to the prototypical example; and their hypothesis margin yields a closed form robustness certificate. However, on high-dimensional data, these shallow models need deep embedding networks to achieve high accuracy, and this voids the robustness certificate. The margin is a statement about distances in the embedding space, and an unconstrained network can map an arbitrarily small input perturbation to arbitrarily large attacks in the embedding space. We close this gap with a theorem: if the embedding network is locally L-Lipschitz around a point, and the classifier is {\epsilon}-robust around its embedding, then the full model is {\epsilon}/L-robust in the input space. Based on this, we propose a Lipschitz training scheme to achieve L-Lipschitz properties for embedding networks. We evaluate three classification heads (linear, linear Support Vector Machine, and GLVQ) crossed with two embedding networks (standard and Lipschitz-constrained) on MNIST, CIFAR-10, and Imagenette-160, under FGS, PGD and C\&W attacks. The evaluation results show that combining a prototype-based head with a Lipschitz-constrained embedding provides the strongest robustness. This suggests that the Lipschitz constraint provides an additional robustness benefit in addition to the advantage provided by the prototype-based head. Since the Lipschitz constraint is enforced by sampling rather than by construction, the reported robustness is empirical rather than certified.

AI 总结：本研究提出一种带概念漂移自适应的开放世界基于重构的分类器，利用自编码器与KDE检测新类别、适应分布变化，经多组实验验证其在概念漂移场景下表现最优。

链接：https://arxiv.org/abs/2611.09350

机构：Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）

作者：Joanna Komorniczak

英文摘要：Data stream processing has become central to modern machine learning applications, with concept drifts and novel class appearances posing the primary challenges faced by recognition methods. Adapting to concept drifts while also being able to detect novel classes and distinguish groups of unknown observations can be seen as a step towards effective method employment in an open-world setting. This work proposes a classification method that can detect and learn the distributions of new, unknown classes, as well as adapt to concept drifts once the distribution of known classes shifts. The proposed method uses the autoencoders' reconstruction errors and the KDE that models their distribution. The autoencoders incrementally adapt to the changing distributions of known classes via weight fine-tuning, resulting in continuous adjustment to evolving concepts. Conducted experiments used a diverse set of synthetic data streams, embeddings of a real-world static CIFAR dataset arranged into a stream to simulate concept drifts and the emergence of unknowns, as well as real-world datasets where novelty is observed. The methodology was compared with state-of-the-art approaches with three-criterion recognition quality assessment and resource consumption evaluation. The results indicate that the proposed method is competitive with reference approaches in stationary environments and performs best when concept drifts occur.

AI 总结：本文针对行为克隆中的协变量偏移问题，提出DrilDICE方法，利用分布鲁棒的行为克隆目标结合平稳分布校正比率估计，经多场景实验验证，该方法可提升对偏移的鲁棒性，优于现有离线模仿学习方法。

链接：https://arxiv.org/abs/2611.09371

机构：KAIST（韩国科学技术院）； Korea University（高丽大学）； Gauss Labs Inc.（高斯实验室公司）； UC Berkeley（加州大学伯克利分校）

作者：Seokin Seo, Byung-Jun Lee, Jongmin Lee, HyeongJoo Hwang, Hongseok Yang, Kee-Eung Kim

英文摘要： We consider offline imitation learning (IL), which aims to train an agent to imitate from the dataset of expert demonstrations without online interaction with the environment. Behavioral Cloning (BC) has been a simple yet effective approach to offline IL, but it is also well-known to be vulnerable to the covariate shift resulting from the mismatch between the state distributions induced by the learned policy and the expert policy. Moreover, as often occurs in practice, when expert datasets are collected from an arbitrary state distribution instead of a stationary one, these shifts become more pronounced, potentially leading to substantial failures in existing IL methods. Specifically, we focus on covariate shift resulting from arbitrary state data distributions, such as biased data collection or incomplete trajectories, rather than shifts induced by changes in dynamics or noisy expert actions. In this paper, to mitigate the effect of the covariate shifts in BC, we propose DrilDICE, which utilizes a distributionally robust BC objective by employing a stationary distribution correction ratio estimation (DICE) to derive a feasible solution. We evaluate the effectiveness of our method through an extensive set of experiments covering diverse covariate shift scenarios. The results demonstrate the efficacy of the proposed approach in improving the robustness against the shifts, outperforming existing offline IL methods in such scenarios.

AI 总结：针对标注成本高的分类场景，提出k-Volume主动学习策略，兼具密度、多样性等特性，在多类数据集上表现稳定且优于部分现有方法。

链接：https://arxiv.org/abs/2611.09388

机构：SAMM, Université Paris 1（SAMM，巴黎第一大学）； IRIT, INP Toulouse（IRIT，图卢兹国立综合理工学院）

作者：Eliot Tron, Alain Celisse, Christophe Denis, Alice Le Brigant

英文摘要：In the classification context where revealing the label of a sample is costly, we propose a new Active Learning (AL) strategy named k-Volume (kVol). It randomly selects a sample to be labeled according to the volume of the smallest ball containing its k nearest neighbors. kVol is highly versatile: it can be applied either in the input space or in the output space, and it enjoys the desirable properties of the three main families of AL strategies: density, diversity, and (when performed in the output space) uncertainty. From a theoretical perspective, we establish that kVol is asymptotically equivalent to uniform sampling over the support of the (input or output) data distribution. Based on experiments on various synthetic and real-life tabular datasets and images, we observe that kVol is surprisingly stable: whatever the classifier or the experimental setup, it still lies among the best AL strategies unlike other competitors that fail dramatically. In particular, kVol outperforms state-of-the-art competitors such as CoreSet, TypiClust or Uncertainty on several real-life datasets, at a low computational cost.

AI 总结：针对iEEG被试间导联配置异质性导致的泛化难题，提出MOSAIC图学习框架，通过自蒸馏学习跨被试稳定的通道连接，在四个公共语料库上优于现有基线。

链接：https://arxiv.org/abs/2611.09496

机构：EPFL IEM and Neuro-X Institutes（EPFL IEM与Neuro-X研究所）

作者：Arya Jalali, Mahsa Shoaran

英文摘要：Intracranial EEG provides high signal-to-noise ratio and spatial resolution for detecting epileptic activity, but patient-specific electrode placement leads to substantial variation in channel count and montage across subjects. This heterogeneity limits the generalization of existing detectors under subject-independent evaluation. We propose MOSAIC (MOntage-agnostic Self-distilled Adaptive Inter-channel Connectivity learning), a lightweight graph-learning framework for subject-independent iEEG seizure detection. MOSAIC pairs a shared convolutional channel encoder with a patient-agnostic channel-attention module that infers a weighted inter-channel adjacency matrix from the encoded features, requiring no fixed montage graph. An exponential moving average self-distillation objective regularizes each prediction toward a slowly updated per-patient teacher. Across four public iEEG corpora (SWEC-ETHZ long- and short-term, Mayo, FNUSA), MOSAIC outperforms state-of-the-art baselines in F2 and Cohen's $\kappa$ while learning more stable inter-channel adjacencies, demonstrating that self-distilled connectivity learning transfers across unseen implantations.

AI 总结：本文提出e-means算法，基于指数移动平均优化，仅用1/10迭代轮次就超越k-means，在多数据集上损失更低、速度快10-45倍，可高效处理百亿级嵌入聚类。

链接：https://arxiv.org/abs/2611.09501

机构：FAIR at Meta（Meta FAIR实验室）； École Nationale des Ponts et Chaussées（巴黎路桥学院）

作者：Swann Bessa, Pierre-Emmanuel Mazaré, Gergely Szilvasy, Hugo Touvron, David Picard, Matthijs Douze, Hervé Jégou

英文摘要：Lloyd's k-means algorithm is a long-running standard for clustering, with applications in data analysis, retrieval, quantization and data curation. In this paper, we introduce an exponential moving average optimization procedure for k-means with mini-batch updates, powered by modern deep learning machinery and new insights. We also establish scaling laws on how decay rate and batch size impact final performance. This gives us a formulaic rule to fix them for multiple problem sizes and embedding datasets, without the need for any hyperparameter sweep. The resulting clustering algorithm, coined e-means, is much faster than Lloyd k-means and converges to lower losses, frequently even beating k-means++. On a wide array of embeddings datasets, it beats the loss of Lloyd k-means at 25 epochs in 1.4 to 2.6 epochs, which translates to 10-45x GPU wall-clock speedups compared to state-of-the-art k-means implementations. As an example, e-means partitions DINO10B, a dataset of 10 billion DINO embeddings, into 16 million clusters in only 2.5 epochs, reaching a loss below Lloyd's at 25 epochs.

AI 总结：该研究针对现有时间序列模型无法适配实时流应用的问题，提出CL-TSU范式与LiveTS-Suite数据集，构建TimeOmni-Live模型，在18项任务上实现更优性能与更低延迟，可支持边缘端实时时序理解。

链接：https://arxiv.org/abs/2611.09502

机构：Griffith University（格里菲斯大学）； Zhejiang University（浙江大学）； Langotime（朗时科技）； CSIRO（联邦科学与工业研究组织）； Zhejiang Lab（浙江实验室）

作者：Tong Guan, Alexander Chemeris, Yiqing Guo, Warren Jin, Zhao Li, Shirui Pan, Ming Jin

英文摘要： Existing time series language models predominantly follow an offline, one-shot paradigm: they process fixed-length inputs independently and do not retain past states. This static approach fundamentally misaligns with the continuous nature of real-world streaming applications and fails to maintain the historical context necessary for cross-window reasoning. To bridge this gap, we introduce Continuous & Live Time Series Understanding (CL-TSU), a novel paradigm that shifts the focus toward maintaining a persistent, stateful understanding over open-ended data streams. To systematically evaluate this paradigm, we present LiveTS-Suite, the first comprehensive data suite tailored for CL-TSU, supporting data generation, model training, and systematic evaluation across 18 tasks spanning six core capabilities. It comprises over 5K streams totaling 2.2B timesteps, annotated with 15K specific response events. We further design an evaluation protocol that jointly assesses response timeliness, content accuracy, and computational efficiency. Building on this foundation, we propose TimeOmni-Live, the first live time series understanding model. It integrates a hybrid time series encoding for natively temporal input, a stream-persistent hybrid memory mechanism to effectively preserve exact historical evidence and long-term task states, and an elastic stream-inference synchronization strategy to reduce processing lag. Evaluations show that TimeOmni-Live establishes a strong baseline for CL-TSU, outperforming frontier LLMs (90.0 vs. 79.3 for Opus 5) with only 4B parameters and achieving 206$\times$ lower p95 latency than its backbone. Deployment on a Jetson edge device further shows its ability to support real-time continuous temporal understanding locally at the edge.

AI 总结：本文提出一种无求解器的决策导向学习框架，通过神经优化层处理含不确定参数的NP难边选择问题，在两类组合优化问题上验证了其决策质量、训练效率与部署速度的优势。

链接：https://arxiv.org/abs/2611.09560

机构：Monash University（莫纳什大学）； ARC Training Centre in Optimisation Technologies, Integrated Methodologies, and Applications (OPTIMA)（ARC优化技术、集成方法与应用培训中心（OPTIMA））

作者：Xinda Zheng, Frits de Nijs, Edward Lam

英文摘要：Decision-focused learning trains prediction models to improve downstream decisions, but many methods require costly solver calls or optimal-solution labels. We propose a solver-free decision-focused learning framework for NP-hard edge-selection problems with uncertain parameters in the objective, the constraints, or both. A neural optimization layer is first trained without solution labels, using problem objectives and constraint penalties. Graph-informed edge scoring and iterative refinement encourage concentrated and structurally consistent continuous decisions. The layer is then frozen, and a prediction model is trained through its continuous output using a problem-specific loss evaluated under observed parameters. At deployment, the predictor, optimization layer, and a lightweight decoder produce decisions without solving the original NP-hard problem. Experiments on the asymmetric traveling salesperson and endpoint-free orienteering problems show consistently better decision quality than prediction-focused learning and improvements over most evaluated decision-focused baselines. Our framework requires less training time than the evaluated decision-focused baselines, even when optimization-layer pretraining is included. Neural deployment also produces decisions faster than solver-based deployment, offering a better quality-efficiency trade-off. The layer also reduces training cost in existing decision-focused methods when used as an approximate optimization oracle.

AI 总结：该研究针对重尾噪声下Adam算法，提出按坐标选择ε_i的策略，证明其可达到最优收敛速率，而共享ε的Adam存在下界，无法实现维度统一基准速率。

链接：https://arxiv.org/abs/2611.09596

机构：Yonsei University（延世大学）； Seoul National University（首尔大学）

作者：Jeonseong Kim, Chenglin Fan

英文摘要：Adam estimates second moments coordinatewise, but typically adds the same scalar $\varepsilon$ to every denominator. We study how this shared $\varepsilon$ affects convergence when noise and curvature vary across coordinates. Under coordinatewise finite-$p$ noise moments, $p\in(1,2]$, choosing $\varepsilon_i$ from the noise and curvature bounds for each coordinate attains the heavy-tailed $\ell_1$-stationarity benchmark $O(T^{-\frac{p-1}{3p-2}})$, matching the known optimal time exponent for smooth nonconvex stochastic optimization. For $1

AI 总结：该研究针对网络化系统在线因果配置问题，提出CAUSAL-UCB算法，通过双重鲁棒稳态学习方法，在基准测试中显著降低了目标遗憾与部署差距。

链接：https://arxiv.org/abs/2611.09665

机构：Smart Ocean Technology, University of Macau（澳门大学智慧海洋技术）； School of Statistics and Data Science, Shanghai University of Finance and Economics（上海财经大学统计与数据科学学院）； Institute of Big Data Research, Shanghai University of Finance and Economics（上海财经大学大数据研究院）

作者：Yuli Liu, Zhiheng Zhang

英文摘要：Measurement exploration reveals how interacting local controllers behave but can alter the steady-state regime a network operator seeks to optimize. Exploratory rewards may therefore fail to identify a configuration's no-exploration value: under full exploration, identical logged distributions can conceal different target values. Identification requires accounting for both action-law mismatch and shifts in the steady-state context distribution. We introduce CAUSAL-UCB, which selects configurations using optimistic bounds on target causal values. Its interference-aware clipped doubly robust evaluator produces predecision certificates separating statistical variation from calibrated identification, transport, and temporal-dependence errors. For any finite horizon and predetermined schedule of measurement-exploration rates $\{\eta_t\}$, we prove lower bounds of $\Omega((1+\sum_t\eta_t)^{-1/2})$ on minimax inference error and $\Omega(\sum_t\eta_t)$ on measurement-induced deployment loss in a stationary, potentially slow-mixing family. We bound regret under valid certificates and selected-information growth, and establish an anytime finite-sample certificate with a shared radius for estimation, selection, and reporting in a restricted known-local-interference model. In a high-mismatch benchmark with 24 paired seeds and 200 rounds, CAUSAL-UCB attains target regret of $1.732$ versus $6.326$ for certified IPS-UCB, with deployment gaps of $30.607$ and $23.217$, respectively. Independent-audit coverage tests and trace-driven semi-synthetic studies further assess certificate coverage and deployment trade-offs.

AI 总结：该研究将验证器噪声视为温度，在有限预算的LLM引导搜索中测试倾斜预测，发现倾斜预测与实际搜索结果存在偏差，且不同设置下的定量一致性未通过验证。

链接：https://arxiv.org/abs/2611.09699

作者：Xiaomeng Li

英文摘要：LLM-guided search loops propose a modified candidate, score it, and keep it if it scores better. When both candidates are re-scored at every comparison, as in the minibatch acceptance gates of prompt optimizers, keep-if-better is a reversible Markov chain if the score difference is logistic and the mutation operator is reversible, and its stationary law is the mutation equilibrium tilted by exp(beta f). For any continuous symmetric noise difference the same tilt is the stationary law of a small-step diffusion limit, with beta = 4F'(0); for a minibatch gate beta grows with the square root of the minibatch size. Caching the incumbent's score instead inflates the recorded score. We test the tilt as a prediction for LLM-guided program search, committing each prediction from calibration data before the search runs. The level after 150 steps rises with the minibatch size in six of seven settings, but its predicted value fails: on bin packing, search attains 62-88% of the predicted gain when the proposer edits the parent and 109-119% when it writes new heuristics. The attained fraction falls with the parent-child quality correlation of unselected mutation; a registered test on two new settings confirmed the direction, but not the quantitative agreement after a correction. Further registered tests found that runs started from a good program kept losing quality over 300 steps, more so from starts that search had selected, by a margin that passed its registered rule narrowly. Runs from different starts had not reached a common level, so whether the tilt describes the stationary law of LLM editing remains open. A registered test in prompt optimisation on frozen task-model scores failed: search exceeded the tilt, and the bin-packing relation did not transfer.

AI 总结：本研究提出无需训练的RidgeFill方法，通过岭回归拟合映射预测后期层输入以缩短预填充时间，在多款模型上实现1.25-1.60倍速度提升，精度损失较小。

链接：https://arxiv.org/abs/2611.09709

作者：Dylan Johnston, Robert P. Smith

英文摘要：RidgeFill shortens prefill by not computing most of a model's upper layers for the prompt. The lower layers run exactly up to a split; from the split layer's state a per-layer map predicts every later layer's input, and each late layer writes its cache from that prediction. The design follows YOCO and DeepSeek-V4.1-Flash, where the projection is trained into the model. RidgeFill retrofits it onto models that were never trained for it: the map is a ridge regression fitted once in closed form from one pass over calibration text, the layer's own projections run unchanged, and a chosen set of rows, the last few thousand tokens, and every decoding step run the full model. Nothing is trained and no token is dropped. Most of the work was in measurement, finding a repeatable methodology. Loss averaged over all tokens hides RidgeFill's error. Needle retrieval in the filled region, loss on tokens that depend on distant context, and splice tests that swap filled keys or values for exact ones show which component carries it: the keys on Llama-3.1-8B, half of it in their scale, and the values and the recurrent state on Qwen3.5-9B. On Qwen3.8-27B in a this http URL fork on an A100, time to first token is 1.25 to 1.31x faster at 16K to 120K tokens with the maps in VRAM; RULER changes by -1.2 and -1.4 points and LongBench v2 by -1.4; the 95 % intervals include zero but do not rule out losses of a few points. On Qwen3.8-Flash-Next in vLLM it is 1.50 to 1.60x faster than exact at 9K to 32K tokens, with RULER's needle tasks at 99.8 against 100.0 and perplexity on novel tokens 2.65 % higher [-0.02 %, +4.93 %]. On three 8 to 9B reference models, at the same split and tail as the identity fill, the fitted map retrieves 49.1 and 49.6 more filled-region RULER points on the two dense models (at that split Llama's loss is worse), and its long-document loss is +/-0.03 nats of the released SwiftKV checkpoint's.

AI 总结：本文以统一框架分析OpenAI智能体攻破Hugging Face与发布AI数学证明事件，指出安全为Π₁陈述、可证明性为Σ₁陈述，且统计提议器加演绎验证器的结构不改变不可判定性结果。

链接：https://arxiv.org/abs/2611.09736

机构：Gwangju Institute of Science and Technology（光州科学技术院）； Korea Institute for Advanced Study（韩国高等研究院）

作者：Jinho Kang, Jinsook Kim

英文摘要：OpenAI's agents breached Hugging Face in July 2026, and the same company released more than seven hundred AI-generated manuscripts of mathematical proofs in October 2026. The first event is read as a failure in security, while the second is read as a success in mathematics. We read both through the hybrid framework of our paper (Kim and Kang, 2026, arXiv:2611.01914 ), in which coding, proving, and learning from data are derivations by one and the same deductive mechanism, distinguished by the kinds of premises from which they are derived. Under this framework, the AI systems behind the two events ran the same loop, in which a statistical proposer produces candidate exploits or proofs and a deductive verifier settles each one by a derivation. What separates the events is the logical form of the statement wanted by each of the two domains, security and mathematics. The safety of a program is a $\Pi_1$ statement, for it says that no exploit exists, which is not assured by any finite list of tests that have been passed by the program. By contrast, the provability of a sentence is a $\Sigma_1$ statement, for it says that a proof exists, which is assured by a single instance, namely a proof that has been checked by the deductive verifier. The theorem behind both is Turing's Undecidability Theorem: the halting set is $\Sigma_1$ but not decidable, so its complement is $\Pi_1$ and not $\Sigma_1$, which is to say that membership has a finite witness but non-membership has none. We prove that attaching a statistical proposer to a deductive verifier does not change this undecidability result, however good the proposer is. We then discuss what does assure safety and where the residual risk goes.

AI 总结：本研究建立了首个思维链（CoT）计算的严格层次定理，证明增加CoT推理步骤数量可提升Transformer的计算能力，通过适配填充技术实现了该结果。

链接：https://arxiv.org/abs/2611.09759

机构：University of Nebraska–Lincoln（内布拉斯加大学林肯分校）； Iowa State University（爱荷华州立大学）

作者： Thanh Le, A. Pavan, N. V. Vinodchandran

英文摘要：Chain-of-thought (CoT) reasoning has emerged as a powerful paradigm for extending the computational capabilities of transformer-based models. A growing body of recent work has begun to uncover the fine-grained computational power of transformers augmented with CoT, as well as their connections to classical complexity theory. In this work, we advance this line of research by establishing the first hierarchy theorem for CoT-based computation. Our main result shows that for any reasonable resource bound $r(n) \geq n$ and any $\varepsilon > 0$, \[ \mathrm{CoT}(r(n)) \subsetneq \mathrm{CoT}(r(n)^{1+\varepsilon}), \] where $\mathrm{CoT}(r(n))$ denotes the class of decision problems solvable by transformers using $O(r(n))$ CoT reasoning steps on inputs of length $n$. Our result shows that increasing the number of CoT reasoning steps provably yields strictly greater computational power, establishing CoT steps as a fundamental resource in transformer-based computation. Unlike classical hierarchy theorems, which are typically proved via diagonalization, our approach leverages known coarse-grained simulations between CoT-augmented transformers and Turing machines in both directions. Building on these connections, we adapt the classical padding technique from complexity theory to this setting to obtain a tight hierarchy. A key technical contribution of our work is the implementation of padding within the transformer-based CoT model.

AI 总结：该研究提出计算机使用智能体（CUA）可作为具身通用者，其单一设计经软件更换后在四项ECCV workshop竞赛获多奖项，证明软件学习技能可迁移至具身任务，推动通用具身AI发展。

链接：https://arxiv.org/abs/2611.09847

机构：Carnegie Mellon University（卡内基梅隆大学）

作者：Pranjal Aggarwal, Sean Welleck

英文摘要：In many areas of AI, general-purpose models have increasingly replaced handcrafted methods and specialized architectures. We argue that embodied AI is poised for a similar shift. Our key claim is that embodied tasks can be formulated as interaction with digital software. Specifically, we build software that renders an agent's view of a physical environment on a screen and provides controls for acting in it. A computer-use agent (CUA) can then perform embodied tasks through the same screenshots and keyboard and mouse actions that it uses to operate ordinary software. Using a single CUA design and changing only the software, our entries win first-, second-, third-, and sixth-place prizes across four ECCV workshop competitions, without any competition-specific agent tuning. These results suggest that the skills CUAs learn on software, such as visual grounding, precise clicking, and exploration, already carry over to embodied tasks, giving CUAs a far broader scope in embodied AI than previously realized. We therefore advocate that computer-use agents can be embodied generalists. Further, we advocate that, by following the training strategy that made computer-use agents general, embodied AI can converge on a single general model as well, ushering in a new era of general embodied AI. Website: this https URL

AI 总结：该研究证明单隐藏层ReLU网络集合在特定Sobolev空间中弱闭，可用于多种深度学习方法，同时否定了双隐藏层有界宽度ReLU网络集合的闭性猜想。

链接：https://arxiv.org/abs/2611.09887

作者：Eloi Martinet, Leon Bungert

英文摘要：We prove that the set $\mathcal{N}_N$ of ReLU networks with one hidden layer and at most $N\in\mathbb N$ neurons is weakly closed in $W^{1,p}(\Omega)$, for a bounded connected open set $\Omega\subset\mathbb R^d$. Consequently, every coercive, weakly lower semicontinuous energy on this space attains its minimum over $\mathcal{N}_N$. This covers the Deep Ritz method with convex integrands, Sobolev training and Lipschitz learning. Moreover, as the weight decay parameter tends to zero, minimizers of the regularized problem converge, up to subsequences, to minimizers with minimal parameter norm. We also prove that the set of ReLU networks with two hidden layers of bounded widths is not closed in $W^{1,p}(\Omega)$ or in $C(\overline\Omega)$. This disproves a conjecture of Petersen, Raslan and Voigtlaender.