机器学习学术速递[7.29]

AI 总结：针对交通流预测，提出基于注意力的时空融合图卷积网络（A-STFGCN），设计时空融合块，通过掩码矩阵多头自注意力机制提取特征相关性，去除传播延迟误差，实验表明该方法相比基线方法性能最佳，效率良好。

链接：https://arxiv.org/abs/2607.24885

机构：School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications（北京邮电大学计算机学院（国家示范性软件学院））； Department of Automation, School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院自动化系）； School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）； Department of Automation, Tsinghua University（清华大学自动化系）； College of Information Science and Technology, Jinan University（暨南大学信息科学技术学院）

作者：Jinpeng Chen, Ziyu Yu, Tao Wang, Jun Ma, Hongbo Gao, Senzhang Wang, Zufeng Zhang, Kaimin Wei

英文摘要：Predicting traffic flow is crucial to optimizing transportation systems and improving urban mobility. Many graph convolution-based models have been proposed to extract spatial-temporal features and predict traffic flow. However, most focus on spatial-temporal and semantic correlation in topological relationships. There are two primary problems to address. Firstly, the convolutional structure in the model focuses on utilizing static spatial dependencies and spatial-temporal relationships in topological structures, while neglecting the different information propagation delays between adjacent nodes in the convolution. Secondly, these methods often stack a large number of complex structures, resulting in a substantial increase in computational time during the model training phase, thereby disregarding the model's requirements for timeliness. In this paper, we propose a novel network called the Attention-Based Spatial-Temporal Fusion Graph Convolution Network (A-STFGCN). We design a spatial-temporal fusion block to extract the spatial-temporal feature correlations with propagation delay errors removed and to capture both long-term and short-term temporal characteristics of the data within a multi-head self-attention mechanism based on a mask matrix. Extensive experiments on five real-world datasets demonstrate that our method achieves the best overall performance while having good computation and data utilization efficiency compared with the eight baseline methods.

AI 总结：研究旨在解决大语言模型训练从FP8降至FP4时的不稳定性问题，提出基于2D块FP4量化的低精度训练框架，结合多种策略控制量化误差，在多个模型上评估，实现稳定的端到端FP4训练，性能与BF16相近。

链接：https://arxiv.org/abs/2607.24953

作者：Mehdi Rahimifar, Amin Darabi, Mehran Taghian Jazi, Xing Huang, Yao Wang, Zhijun Tu, Yufei Cui, Yunke Peng, Hongliang Li

英文摘要：Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization. We identify a fundamental source of this instability in existing microscaling approaches: scale inconsistency induced by tensor transposition. In conventional 1D block quantization, forward and backward passes assign di erent scaling factors to the same values after transposition, leading to biased and unstable gradient updates. To address this issue, we propose a low-precision training framework based on 2D block FP4 quantization, which enforces transposition-invariant scaling and preserves consistency between forward and backward computations. We further combine this with truncation-free scaling and stochastic rounding to control quantization error and maintain unbiased gradients. To handle the sensitivity of attention mechanisms, we adopt MXFP8 quantization for query and key projections, yielding a practical mixed-precision design. We evaluate our method on dense LLMs up to 7B parameters and a 30B Mixture-of-Experts model, trained on up to 100B tokens. Across all settings, our approach achieves stable end-to-end FP4 training and closely matches BF16 performance, with less than 1.3% degradation in perplexity and downstream accuracy. These results demonstrate that enforcing forwardbackward scaling consistency is su cient to enable practical FP4 training at scale, providing a simple and e ective pathway toward more e cient LLM training.

AI 总结：研究提出在语义空间构建搜索轨迹网络（STN）的方法，通过离散化语义向量并聚类聚合到节点。应用于不同机器学习算法的任务及研究神经网络泛化，发现不同训练方式下STN结构有差异，能捕获学习算法与数据相互作用的训练动态，用于分析比较学习动态。

链接：https://arxiv.org/abs/2607.25122

机构：University of Stirling（斯特林大学）

作者：Julian Agudelo, Alberto Tonda, Gabriela Ochoa, Vincent Guigue, Cristina Manfredotti, Evelyne Lutton

英文摘要： Search Trajectory Networks (STNs) are a graph-based tool for visualizing and characterizing the behavior of optimization algorithms. STNs' reliance on discretization of the search space has largely confined them to low-dimensional or combinatorial settings. We introduce a methodology for constructing STNs in semantic spaces, defined as the space of a model's predictions on a fixed sample set. Our approach discretizes semantic vectors and aggregates them into network nodes via agglomerative clustering with complete linkage under a normalized Hamming distance. Since any predictor can be summarized by its semantic vector, this method enables comparison of learning dynamics across otherwise incomparable algorithm families. We apply semantic space STNs to classification and regression tasks solved using different machine learning algorithms, recovering known qualitative differences between them. Additionally, we use semantic space STNs to study neural network generalization by contrasting standard training with the label randomization regime of Zhang et al. (2017). The resulting STNs exhibit consistent structural differences, training on real labels produces denser, more efficient and more centralized graphs than training on shuffled labels. Together, our results show that semantic space STNs capture functional training dynamics arising from the interaction between learning algorithms and data, providing a tool for analyzing and comparing learning dynamics across machine learning models and training regimes.

AI 总结：研究针对线性时间序列模型长上下文召回权衡问题，提出Raven模型，通过固定内存插槽和依赖输入的路由，减轻SWA和SSMs的不足，在召回密集基准测试中表现出色，外推时也保持有效。

链接：https://arxiv.org/abs/2607.25357

机构：EPFL（洛桑联邦理工学院）； Carnegie Mellon University（卡内基梅隆大学）； MBZUAI（穆罕默德·本·扎耶德人工智能大学）； Cartesia AI（卡泰西亚人工智能公司）

作者：Arshia Afzal, Aviv Bick, Eric P. Xing, Volkan Cevher, Albert Gu

英文摘要：Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory. State-based linear models, such as state-space models (SSMs) and linear Transformers, write densely, updating the entire state for each newly arrived token, which leads to interference and makes specific past tokens hard to recover. Sliding-window attention (SWA) exhibits the opposite behavior: it writes sparsely by storing explicit token representations, but only within a fixed window, so recall drops once the relevant token is evicted. Interpolating between these models, we introduce Raven, a linear-time sequence model that maintains a fixed set of memory slots and, at each step, decays and updates only a selected subset via learned, input-dependent routing. This lets Raven mitigate SWA's position-based overwriting and hard eviction while reducing interference from dense state updates in SSMs, thereby preserving long-range content much more effectively. Across recall-intensive benchmarks, Raven is competitive with or outperforms prior linear-time baselines, achieving strong long-context recall where both SWA and SSMs sharply degrade. It remains effective when extrapolating to context lengths as large as 16x its training length, with similar gains in hybrid architectures.

AI 总结：研究贝叶斯神经网络中似然分布假设，通过比较如偏态或重尾等多种假设，发现学生t分布在回归任务中比高斯似然分布预测性能更好，与数据及MLP架构无关，还可能缩短训练时间且易实现。

链接：https://arxiv.org/abs/2607.25376

机构：Scientific Computing Center, Karlsruhe Institute of Technology（科学计算中心，卡尔斯鲁厄理工学院）； Helmholtz AI（亥姆霍兹人工智能中心）

作者：Pei-Hsuan Hsia, Lars H. Heyen, Arvid Weyrauch, Markus Goetz, Achim Streit, Sebastian Krumscheid, Charlotte Debus

英文摘要：In Bayesian neural networks (BNNs), variational inference is a widely adopted framework for modeling uncertainty in a distributional way, with the evidence lower bound (ELBO) serving as the standard objective function. Several distributions contribute to the ELBO loss, such as the prior, approximated posterior, and likelihood distribution. Typically, these distributions are all approximated by a Gaussian distribution, since it is easy to compute, allows for reparameterized gradients, and provides a closed-form loss for training. However, several works have highlighted that this assumption may not generally hold, posing the risk of model misspecification. Alternative distributions have been proposed for the prior specifically, while the effect of distribution choice on the likelihood distribution remains unexplored. In this work, our aim is to close this gap by investigating whether alternative assumptions for the likelihood distribution can outperform the commonly used Gaussian. We compare several likelihood distribution assumptions, such as skewed or heavy-tailed, across regression tasks on both artificial and real-world datasets using standard multilayer perceptrons (MLPs). Our findings demonstrate that Student's t yields better predictive performance than a Gaussian likelihood distribution, independent of the data distribution and MLP architecture (depth and width). In some cases, Student's t can also lead to shorter training times, while still being easy to implement.

AI 总结：研究大语言模型中仅通过输入优化提示来抑制“评估感知”潜在因素，采用特定方法在多种目标结构下对Llama模型进行实验，发现潜在因素可抑制，但激活可读性与行为可控性不同，还解决了相关问题。

链接：https://arxiv.org/abs/2607.25907

机构：Center for Data Science, New York University（纽约大学数据科学中心）

作者：Deepanshu Mody, Samarth Agarwal, Utkarsh Mittal, Dipesh Mahato

英文摘要： Activation steering controls model behavior by editing internal activations at inference time. We study its input-side dual: optimizing a fluent prompt so that a chosen internal latent is driven toward zero, with no inference-time model access. Our target is an "evaluation-awareness" latent-linearly readable and steerable in recent work-whose control would threaten the validity of safety evaluations if models behave differently when they detect being tested. Adapting Fluent Dreaming / EPO with a negated feature term (GCG-style token optimization plus a self-cross-entropy fluency regularizer, swept over a fluency weight), we suppress the latent under five target constructions-a CAA direction, a subspace norm, an SAE feature, a single MLP neuron, and a behavioral logit-on Llama-3.2-3B and Llama-3.1-8B. The latent is robustly suppressible ($z\approx-7$), and a causally-validated Llama Scope SAE feature can be fully and selectively turned off. But our controls tell a cautionary story about the CAA direction: a placebo random direction is suppressed just as hard and shifts behavior just as far, and when we hold a real eval passage in context and optimize only a prefix, suppressing the eval-direction fails to reduce-and slightly increases-the model's behavioral eval judgment. Activation-readability, in short, is not behavioral controllability. We further find that a single MLP neuron is eval-correlated but not causal at both scales, and that scanning the real Pile yields a natural-text baseline competitive with the optimizer for the internal direction. A positive control validates our erasure detector, bounding an erasure-vs-rotation question earlier left open.

AI 总结：研究针对专家混合LoRA路由中简单与困难令牌服务不均问题，提出置信度自适应路由CARE，它以核心方式接纳专家，校准阈值使活跃专家数匹配目标，是单前向传递规则，在多任务中改进效果显著，还提升了分布外检测能力。

链接：https://arxiv.org/abs/2607.26052

机构：University of California, Irvine（加州大学欧文分校）； University of Washington（华盛顿大学）

作者：Tom Saliencro, Rohan Desai, Priya Nair, Maya Lindqvist, Daniel Whitmore

英文摘要：Mixture-of-Experts (MoE) variants of Low-Rank Adaptation (LoRA) route every token to a fixed number of experts $k$. Tokens differ in how uncertain the model is about them, so a single k over-spends on easy tokens and under-serves hard ones. We observe that the router's output distribution is already a per-token uncertainty signal: peaked mass indicates confidence, while a flat distribution indicates ambiguity. We introduce CARE (Confidence-Adaptive Routing of Experts), which admits experts in a nucleus fashion. Experts are activated in decreasing router weight until their cumulative mass reaches a threshold, with a small extension when the admitted experts disagree. A budget thermostat calibrates the threshold so that the average number of active experts matches any target. CARE is a drop-in, single-forward-pass rule with no extra parameters. Across eight commonsense benchmarks on LLaMA-3.1-8B and Qwen2.5-7B, as well as math, code, and knowledge tasks, CARE improves over fixed top-k MoE-LoRA at matched compute and matches the fixed-k=4 baseline while activating fewer experts. The same confidence and disagreement signals also improve out-of-distribution detection over MSP, entropy, and multi-pass proxies. We support the design with nucleus fidelity, budget optimality, and an epistemic reading of disagreement, and we release code.

AI 总结：研究单细胞聚类中深度表示学习是否必要，通过九个聚类管道在十个真实数据集上的诊断基准测试及相关分析，集成多种测试方法，揭示不同模式，确定主要方差贡献者，提供数据集感知和计算意识决策框架。

链接：https://arxiv.org/abs/2607.25288

机构：Van Lang University（范朗大学）

作者：Nguyen Thanh Phong, Truong Viet Vu, Nguyen Ha Thu, Tran An Ky, Tran Hoang Thong, Le Pham Thuy Hien, Nguyen Thai Anh

英文摘要：Single-cell ribonucleic acid sequencing (scRNA-seq) is a foundational technology for precision-medicine workflows that contribute to United Nations Sustainable Development Goal 3 on Good Health and Well-being, and unsupervised clustering is the analytical step that turns raw expression matrices into interpretable cell populations. Practitioners therefore face a recurring engineering decision: is an additional deep representation stage worth its compute and tuning cost, or do classical principal component analysis (PCA) pipelines already suffice? We address this question with a diagnostic benchmark of nine clustering pipelines on ten real datasets (90-5,685 cells, 19,046-41,480 genes, 4-11 cell types), augmented by a partial scVI V2 specialized comparison on seven datasets. The protocol integrates Optuna hyperparameter search, repeated-run robustness, Friedman/Wilcoxon-Holm/TOST testing, and Sobol total-order sensitivity analysis. The contrastive autoencoder achieved the highest mean Adjusted Rand Index (0.7872), but Holm-corrected tests did not establish dominance over the strongest baselines. Per-dataset analysis reveals three reproducible regimes: probabilistic variational autoencoder (VAE) variants help on the smallest datasets, deep autoencoders win on mid-scale data with multi-batch or many-type structure, and classical PCA pipelines remain competitive when linear projection already captures the dominant variation. Sobol indices identify learning rate ($S_T=0.70$) and latent dimensionality ($S_T=0.56$) as the dominant variance contributors, indicating where limited tuning budgets should be allocated. The contribution is therefore a dataset-aware and compute-conscious decision framework for biomedical AI pipelines supporting sustainable healthcare analytics, rather than a universal superiority claim.

AI 总结：针对从纵向临床数据理解疾病轨迹的难题，提出以时间图建模多变量疾病轨迹，用对比图神经网络学习表示，借结构感知随机游走引导对比学习，实现相似疾病进展模式患者的稳健聚类并揭示数据潜在结构。

链接：https://arxiv.org/abs/2607.25609

作者：Bastian Pfeifer

英文摘要：Understanding disease trajectories from longitudinal clinical data remains challenging due to complex temporal dynamics and heterogeneous patient cohorts. Here, we present a contrastive representation learning framework that models multivariate disease trajectories as temporal graphs and learns representations using contrastive graph neural networks. Nodes represent patient observations over time, while edges capture temporal continuity and structural similarity between trajectories. Structure-aware random walks guide contrastive learning to generate embeddings that preserve temporal context and trajectory topology. The resulting representations enable robust clustering of patients with similar disease progression patterns and reveal latent structure in longitudinal data.

AI 总结：研究基于模型的强化学习中，非对称学习对观测及特权信息表示的影响。针对‘信息梦行者’局限性，提出用潜在引导的新目标，形成‘强化信息梦行者’算法，实验显示其比之前非对称方法有更持续改进。

链接：https://arxiv.org/abs/2607.26040

作者：Gaspard Lambrechts, Adrien Bolland, Daniel Ebi, Damien Ernst

英文摘要： Much like humans benefit from guidance while learning, reinforcement learning algorithms may benefit from additional supervision beyond rewards. Leveraging additional information during training to learn better representations and behaviors has been the focus of asymmetric reinforcement learning. This learning paradigm has proven effective under partial observability when additional state information is available, but also under full observability when more refined state information is available. Focusing on model-based reinforcement learning, we study the effect of asymmetric learning on observation representations and on privileged information representations. First, we identify a limitation in the privileged information representations learned by an asymmetric model-based algorithm known as the Informed Dreamer. Then, we propose a novel asymmetric representation learning objective using latent guidance, resulting in a new algorithm called the Reinformed Dreamer. Experiments across several benchmarks show a more consistent improvement over Dreamer than previous asymmetric approaches.

AI 总结：研究语言模型对齐问题，受逆强化学习启发提出PARED方法，通过恢复示范的隐式奖励来改进基础策略，无需特定任务偏好注释，经实验验证其有效性及可用于上下文对齐。

链接：https://arxiv.org/abs/2607.24900

作者：Michał Wiliński, Liu Leqi, Chirag Nagpal

英文摘要：Language model alignment aims to make model behavior reliably reflect desirable properties such as helpfulness, safety, and instruction following. Current approaches typically use supervised fine-tuning on demonstrations or reinforcement learning with rewards derived from verifiers or human feedback. These paradigms leave an important question underexplored: can demonstrations alone yield an implicit reward that can be inspected, reused, and optimized on-policy to align AI? Motivated by inverse reinforcement learning, we introduce Projected Alignment Reward Estimated from Demonstrations (PARED). PARED recovers the implicit reward underlying expert demonstrations as an explicit function over a small set of response-level features, learned by a lightweight discriminator that separates demonstrations from the policy's own samples in this feature space. Unlike a standard reward model, PARED requires no task-specific preference annotations: demonstrations provide the task-specific supervision, which can be augmented with AI feedback as additional dimensions of supervision. Through experiments involving inference-time reranking and adversarial on-policy RL, we show that the recovered reward improves a base policy without a supervised loss and yields further gains when optimized after standard supervised fine-tuning. Additionally, we demonstrate that PARED can be used for contextual alignment, in which a single policy can be tailored to the preferences of different audiences.

AI 总结：研究连续强化学习中神经网络训练问题，提出校准部分重置（CPR）优化器，定期拉低效用神经元至初始化，拉动强度依效用缩放。该方法避免策略崩溃，在多基准测试中表现优，揭示可塑性与峰值性能权衡，为连续学习提供新方向。

链接：https://arxiv.org/abs/2607.24996

作者：Luc McCutcheon, Evangelos Chatzaroulas, Saber Fallah

英文摘要：Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data settings, such as continual supervised and reinforcement learning. Recently, neuron resets have been used to maintain gradient flow and restore plasticity. However, full unit reinitialization often sacrifices peak performance and can destabilize training, leading to policy collapse. To preserve plasticity without destabilizing training, we propose Calibrated Partial Resets (CPR), an optimizer that periodically pulls low-utility neurons toward their initialization, with pull strength scaled by each neuron's utility. Unlike binary reset methods, partial resets avoid brittleness; unlike uniform decay, calibrated utility-scaling concentrates adjustment on the units that need it most. Among compared methods, only CPR avoids policy collapse over 400M training steps in SlipperyAnt, and it outperforms prior decay and reset-based methods on Continual MetaWorld and Continual MinAtar benchmarks. Ablations reveal a tunable trade-off between plasticity and peak performance, highlighting utility-scaled reinitialization as a promising direction for continual learning.

AI 总结：研究在深度强化学习中压缩近期缓冲区的方法，提出存储相连n步序列链端点派生的代表性转换的压缩方法，经实证评估，该方法防止系统偏差，在相关环境和基准测试中与传统大型缓冲区性能相当。

链接：https://arxiv.org/abs/2607.25123

作者：Parham Mohammad Panahi, Armin Ashrafi, Haoyu Du, Andrew Patterson, Martha White, Adam White

英文摘要：Experience replay remains one of the most practical and useful algorithmic tools in the deep reinforcement learning (DRL) toolbox. Aside from the limited success of prioritized replay and specialized approaches for large asynchronous systems, most DRL algorithms make use of a large, uniformly sampled recency buffer---even the size, one million, remains unchanged. Could we store less data, reduce redundancy, or more effectively chain experience together to speed up value propagation and still retain the performance of large buffers? In this paper, we investigate a simple compression approach that stores representative transitions derived from the end-points of a chain of connected $n$-step sequences. By curating these end-points in a smaller recency buffer, our method maintains an effective memory horizon comparable to a standard large buffer while requiring an order of magnitude less storage. Through empirical evaluation, we demonstrate that this approach prevents the systematic bias inherent in naive compression strategies and matches the performance of traditional large buffers in the Pinball environment and the Atari 2600 benchmark.

AI 总结：研究表格型MDP中混合强化学习，提出含MIN-UCB-VI和MAX-LCB-VI的统一算法框架，利用细粒度偏差信息有效利用离线数据，给出理论保证并通过实验验证，解决离线数据因转移动态而无效的问题。

链接：https://arxiv.org/abs/2607.25207

机构：Southern University of Science and Technology（南方科技大学）； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））； City University of Hong Kong（香港城市大学）； Fudan University（复旦大学）； Shanghai Academy of AI for Science（上海人工智能研究院）

作者：Zheshun Wu, Renjie Zheng, Jinhang Zuo, Zenglin Xu, Fang Kong

英文摘要：This paper investigates a hybrid reinforcement learning setting in tabular Markov Decision Processes (MDPs), where an agent aims to learn an optimal policy by combining online interactions with a target environment and offline data from a source environment. A central challenge is that offline data may be collected from outdated environments with shifted transition dynamics, making naive integration of historical data ineffective. To address this, we propose a unified algorithmic framework featuring two algorithms: MIN-UCB-VI for regret minimization and MAX-LCB-VI for best policy identification. Both algorithms leverage fine-grained bias information to more effectively exploit offline data under general transition shifts. We provide theoretical guarantees for our framework, including both instance-dependent and independent upper bounds on regret and sub-optimality gap. Furthermore, we establish matching lower bounds to demonstrate the optimality of our approach and validate our theoretical findings through extensive experiments.

AI 总结：研究针对代码优化中强化学习的问题，通过构建DMC - Optim和校准沙盒、组合正确性与速度及调整GRPO和评估等方法，使执行时间可学习，在DMC - Optim等任务上取得显著效果，提升了代码优化能力。

链接：https://arxiv.org/abs/2607.25970

作者：Pierre Chambon, Kunhao Zheng, Juliette Decugis, Benoit Sagot, Gabriel Synnaeve

英文摘要：RL for code correctness is now established: have the model generate a program, run it against hidden test cases, and reward solutions that pass. Extending this to code optimization seems straightforward: just add execution time to the reward. But in practice, once timing drives the reward, small problems in measurement noise, reward sparsity, or GRPO instability overwhelm the signal and make RL fail: generated solutions are barely faster, and more of them can fail. We make execution time learnable through three stages: (1) how code is tested, by building DMC-Optim with large optimization tests and a calibrated sandbox; (2) how speed is turned into reward, by composing correctness and speed in the RL environment and using an offline simulator to predict the most promising configurations; and (3) how the model learns from that reward, by adapting GRPO and evaluation to the sparser, noisier timed-execution setting. On DMC-Optim, the strongest optimization-aware configurations improve strict top-50% pass@1 from 18.0% to 31.3% on Qwen 2.5 7B and from 30.7% to 50.4% on CWM 32B. These gains further increase at stricter percentiles such as top-30%, with 125% relative improvement for CWM 32B, while preserving pure-correctness scores. When the timing sandbox is degraded, robust optimization RL reaches 100% to 200% improvement over standard RLVR, depending on the evaluation criterion. On LCB, CWM 32B wins up to 83% of median-sample speed comparisons against standard RLVR. Relative to the fastest correct human submissions per problem, it reaches about half the human rate of complexity-class improvements (14% vs. 28%).

AI 总结：针对量热计模拟中扩散模型物理错误及标准度量忽略相关结构问题，引入CFD，编码软样本结构为两个物理感知辅助损失，通过GradBlend结合去噪得到Lantern，实验表明其能提高相关指标，消融实验揭示不同损失对调度的敏感性。

链接：https://arxiv.org/abs/2607.25060

机构：University of Virginia（弗吉尼亚大学）； Biocomplexity Institute, University of Virginia（弗吉尼亚大学生物复杂性研究所）

作者：Farzana Yasmin Ahmad, Vanamala Venkataswamy, Geoffrey Fox

英文摘要：Monte Carlo simulation of calorimeter showers is a principal bottleneck for the High-Luminosity LHC, and diffusion models have emerged as fast, high-fidelity surrogates. Their denoising objective is purely statistical, however: a model can minimize it while placing the physics wrong. Existing physics-informed generative methods cannot close this gap, because they assume a closed-form law, a governing PDE residual or a hard per-sample constraint, that a shower does not supply: no per-sample PDE governs a stochastic cascade, and energy conservation fixes only one scalar per shower. Standard metrics ignore the correlation structure across calorimeter layers and voxels, comparing showers only in a physics feature space. We address both gaps. We introduce the Correlation Frobenius Distance (CFD), a single normalized score for correlation fidelity at layer-wise and voxel-wise scales. We then encode the soft per-sample structure available in a shower as two physics-aware auxiliary losses: a variance-stabilized voxel residual loss grounded in counting statistics, and a graph Laplacian loss over the detector geometry. We combine both with denoising through GradBlend, which anchors the step magnitude to the denoising gradient while letting the auxiliary steer its direction, yielding Lantern, a physics-guided diffusion surrogate. On CaloChallenge Dataset 2, injecting the physics losses through task-symmetric rules such as PCGrad, GradNorm, IMTL-G, and ConFIG inflates FPD by 2-100x relative to denoising alone, whereas GradBlend admits the same signal without regression and, with the Laplacian loss, Lantern improves both FPD and CFD. Our ablation on the auxiliary loss scheduler shows that the voxel residual loss, whose gradient conflicts with denoising, requires a terminal denoising-only phase to preserve shower fidelity, whereas the non-conflicting Laplacian loss is insensitive to the schedule.

AI 总结：研究约束在线凸优化问题，通过保留标准论证中省略的量进行更严格分析，提出AdaOGD - PFS自适应步长方法，在保持每轮可行性时实现\(O(\sqrt{G_T})\)遗憾值，实验使遗憾值界提升38% - 43%。

链接：https://arxiv.org/abs/2607.25480

作者：Wentao Zhang

英文摘要： Constrained online convex optimization requires minimizing regret against adversarial convex costs while satisfying a convex constraint at every round, as needed in safety-critical applications. A computationally efficient method combines online gradient descent with a Polyak feasibility step, using one constraint evaluation and one subgradient per round. Although this method achieves O(sqrt(T)) regret with per-round feasibility, we derive a tighter, data-dependent analysis by retaining two quantities omitted by the standard worst-case argument. First, we replace the gradient envelope G_f^2 T with the observed accumulation G_T = sum_t ||grad f_t(x_t)||^2. Second, we identify a nonnegative Polyak correction P_T that measures the cumulative squared displacement caused by feasibility projections and enters the regret bound with a negative sign. The resulting improvement, Delta_T = (eta/2)(G_f^2 T - G_T) + P_T/(2 eta), is always nonnegative. We further propose AdaOGD-PFS, an adaptive-step-size method that achieves O(sqrt(G_T)) regret while preserving per-round feasibility. Experiments on ball- and halfspace-constrained problems improve the regret bound by 38 to 43 percent, with both data-dependent gradients and Polyak corrections contributing substantially.

AI 总结：研究重尾噪声下随机优化，提出量子均值估计器，基于此构建量子归一化和投影随机梯度下降方法，在低维情况下，相比经典方法，能以更少查询次数找到近似平稳点或\(\epsilon\)-最优解。

链接：https://arxiv.org/abs/2607.25492

机构：The Chinese University of Hong Kong（香港中文大学）； Westlake University（西湖大学）； Tencent Quantum Laboratory（腾讯量子实验室）

作者：Bin Luo, Chengchang Liu, Jonathan Allcock, Shengyu Zhang, John C.S. Lui

英文摘要：We study stochastic optimization with heavy-tailed gradient noise. We first propose a novel quantum mean estimator for multivariate heavy-tailed random variables that achieves lower query complexity than optimal classical estimators in the low-dimensional regime. We further develop an unbiased quantum mean estimator by applying a generalized multi-level Monte Carlo technique. We prove quantum lower bounds showing that, when the dimension $d$ of the random vector is small and can be viewed as a constant, our quantum estimators are optimal up to logarithmic factors. We further derive stronger dimension-dependent lower bounds for tail index $p>4/3$, showing that a nontrivial dependence on the dimension is unavoidable in the low-dimensional regime. Based on these estimators, we propose a quantum normalized stochastic gradient descent method ($\texttt{QNSGD}$), which finds an $\epsilon$-stationary point using $\tilde{\mathcal{O}}\big(\sqrt d\,\epsilon^{-\frac{5p-4}{2p-2}}\big)$ queries to the quantum stochastic gradient oracle. For a convex objective function, we propose a quantum projected stochastic gradient descent method ($\texttt{QPSGD}$), which computes a solution with $\epsilon$-optimal solution using $\tilde{\mathcal{O}}\big(\sqrt d\,\epsilon^{-\frac{3p-2}{2p-2}}+\epsilon^{-2}\big)$ queries in expectation. These sharper bounds improve upon the classical lower bounds $\Omega\big(\epsilon^{-\frac{3p-2}{p-1}}\big)$ for nonconvex problems and $\Omega\big(\epsilon^{-\frac{p}{p-1}}\big)$ for convex problems in the low-dimensional regimes $d\lesssim\epsilon^{-\frac{p}{p-1}}$ and $d\lesssim\epsilon^{-\frac{2-p}{p-1}}$, respectively.

AI 总结：研究在约束函数未知且不可查询时的约束优化问题，提出动态约束学习（DCL）框架，通过学习局部代理在数据支持的信赖域内解决子问题，相比全局约束学习更具优势，在合成测试和案例研究中展现良好性能。

链接：https://arxiv.org/abs/2607.25719

机构：Gebze Technical University（Gebze技术大学）； University of Amsterdam（阿姆斯特丹大学）

作者：Ezgi Oztekin, Figen Oztoprak, S. Ilker Birbil

英文摘要：We propose Dynamic Constraint Learning (DCL), a data-driven framework for constrained optimization when constraint functions are unknown and cannot be queried during optimization. At each iteration, the method learns a local surrogate from nearby data and solves a subproblem within a data-supported trust region. Compared with offline global constraint learning, the approach uses local surrogates that adapt to the data distribution during optimization and can achieve solution quality comparable to that of global models while using simpler local models and smaller optimization subproblems. We demonstrate the performance of DCL on a synthetic test problem and two case studies from the literature.

AI 总结：针对非常规油藏气举优化问题，提出基于机器学习的自动化数据驱动工作流程，集成预测气举性能曲线的模型与贝叶斯优化框架，利用历史数据求解最佳注气速率，试点及部署效果良好，为相关资产提供有效经济方案。

链接：https://arxiv.org/abs/2607.25885

作者：Sha (Sasha) Miao, Alexandra Vendetti, Logan Smart, Gunta Chomchalerm, Yang Chen, Christopher Frazier, Dustin Haralson, Jeremy Sorenson, Xiao Ma, Huafei Sun, Aaron Shinn, Haining Zheng, Xiao-Hui Wu, Peng Xu

英文摘要：In this paper, we present an automated data-driven workflow using Machine Learning (ML) for gas lift optimization in unconventional fields. This workflow integrates a ML model that accurately forecasts the Gas Lift Performance Curve, and a Bayesian Optimization Framework to solve for the optimal gas injection rates under the constraints of facility capacity. The ML model leverages the historical production time series data without requiring downhole gauges or multi-rate well tests. We piloted this workflow on 30 wells across 5 well pads in Bakken and obtained >5% production uplift on average. With the success of the pilot, we have now fully-deployed this workflow in Bakken across 200+ gas lift and plunger-assisted gas lift (PAGL) wells. Moreover, the ML-based gas lift optimization workflow presented in this paper is an effective and economic solution for other assets where downhole data or multi-rate testing are not available/feasible due to cost or facility constraints.

AI 总结：研究针对设备端语音情感识别中大型模型成本高的问题，提出自适应多教师关系蒸馏方法。通过单类支持向量机分配教师权重，用关系蒸馏损失捕捉结构，在多数据集和学生架构上优于单教师蒸馏，两组件互补增益。

链接：https://arxiv.org/abs/2607.25289

作者： Yuqi Li, Yi-Cheng Lin, Xianglong Wang, Kuo Yang, Xiaoqin Feng, Yixuan Wang, Huiran Duan, Yingli Tian

英文摘要：On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models that excel at SER are too costly for edge devices. Multi-teacher knowledge distillation can compress them into a lightweight student, but two challenges remain: teacher reliability varies across batches, and logit-level distillation ignores inter-sample relational structure. We propose Adaptive Multi-teacher Relational Distillation (AMRD) to address both. A one-class SVM on each teacher's logit similarity matrix assigns per-batch weights favoring more coherent teachers. A relational distillation loss aligns teacher and student similarity matrices, capturing structure that logit matching misses. On IEMOCAP and CREMA-D datasets across four student architectures, AMRD outperforms single-teacher distillation baselines in most settings, and ablations confirm both components yield complementary gains.

AI 总结：研究针对初级护理中糖尿病视网膜病变筛查模型的部署问题，提出OrthKD框架，从异构教师中选择性蒸馏知识，在资源受限设备上实现实用筛查，提升模型性能，如MobileNetV3学生模型在相关数据集上取得更好的指标。

链接：https://arxiv.org/abs/2607.25545

机构：Tongji University（同济大学）

作者：Yi Xu, Cheng Chen, Mufan Cao

英文摘要：Deploying diabetic retinopathy (DR) screening models in primary care requires edge-efficient systems that remain accurate, safe, and reliable under domain shift. Multi-teacher knowledge distillation (KD) is a natural compression strategy, but existing approaches largely assume that all teachers provide equally trustworthy supervision. In our setting, this assumption fails: a strong CNN teacher (EfficientNet-B3, 0.876 QWK) and a weaker Transformer teacher (Swin-Base, 0.830 QWK) are complementary, yet the Transformer's logits can still mislead the student. We therefore propose OrthKD, a selective-trust distillation framework that transfers full supervision from the strong CNN, uses feature-only distillation from the weak ViT, and enforces orthogonality between teacher-specific student projections to encourage complementary rather than redundant evidence. This design preserves local lesion precision, injects global structural context, and improves robustness to distribution shift. On 132,049 retinal images, a 5.4M-parameter MobileNetV3 student reaches 0.885 QWK on EyePACS and improves zero-shot Messidor-2 performance from 0.507 to 0.728 QWK, while also achieving strong referral AUC and calibration. These results show that selectively distilling heterogeneous teachers can enable practical DR screening on resource-constrained devices.

AI 总结：该研究针对慢性肾病预测问题，运用带投票分类器的联邦学习，结合随机森林等算法为全局服务器选最佳模型，用GridSearchCV优化客户端模型性能，还引入可解释人工智能技术，其全局模型平均准确率达99%，助力早期CKD诊断和数据驱动医疗。

链接：https://arxiv.org/abs/2607.25348

作者：Md Zahid Hasan Ontor, Md Al Amin, Anik Dev Nath, Bikash Kumar Paul

英文摘要：Chronic Kidney Disease (CKD), characterized by the gradual loss of kidney function, remains a significant public health challenge. Early detection is crucial for preventing severe complications and enhancing patient outcomes. In this study, Federated Learning (FL) with a VotingClassifier was used to predict CKD using a clinical dataset, where Random Forest, AdaBoost, and XGBoost were utilized to compare and identify the best-fitting model for the global server. Additionally, GridSearchCV was applied to optimize the models' performance on the client's side. To enhance model transparency and trustworthiness, explainable AI (XAI) techniques were incorporated to interpret the prediction mechanisms. The global model's average accuracy was 99%, highlighting the potential of interpretable FL models in supporting early CKD diagnosis and advancing data-driven healthcare solutions.

AI 总结：研究针对跨训练数据分区的协变量偏移问题，提出PIcsC框架，利用Fisher信息矩阵近似分区散度并纳入正则化，还引入条件适应机制，实验表明该方法在多数据集及联邦学习基准上有效减轻协变量偏移，提升性能。

链接：https://arxiv.org/abs/2607.25441

机构：Institute of Business Administration Karachi（卡拉奇工商管理学院）； Habib University（哈比卜大学）； St. John’s University（圣约翰大学）

作者：Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari, Tahir Qasim Syed

英文摘要：Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated learning. We propose \textit{Partition-Induced Covariate-shift Correction} (\texttt{PIcsC}), a Fisher information-based regularization framework that mitigates distribution mismatch between data partitions and a reference distribution. \texttt{PIcsC} approximates partition divergence using the Fisher Information Matrix (FIM) and incorporates the resulting statistic as a regularizer during optimization. The same formulation applies to both centrally partitioned datasets (batches or cross-validation folds) and inherently distributed data (federated clients or decentralized nodes), requiring only partition-local gradient statistics rather than raw data. We further introduce a conditional adaptation mechanism that combines FIM shift with KL divergence to detect significant distribution shifts and activates regularization only when necessary. Experiments on more than 40 datasets demonstrate consistent improvements under both natural and synthetic covariate shift. On fragmented batch and fold settings, \texttt{PIcsC} reduces fragmentation-induced performance degradation by more than 20\% and 25\%, respectively. On seven federated learning benchmarks, it consistently outperforms FedAvg, FedProx, and SCAFFOLD by 3 -5 percentage points without requiring client-specific personalization. These results demonstrate that Fisher information provides an effective and unified mechanism for mitigating partition-induced covariate shift across both centralized and distributed learning.

AI 总结：研究多模态大语言模型中对比解码减轻对象幻觉的有效性，通过重现和扩展相关研究，进行多实验验证其在不同数据集上效果，发现其带来的改善常是虚假的，挑战了当前策略有效性，推动更可靠方法开发。

链接：https://arxiv.org/abs/2607.25196

机构：Indian Institute of Technology, Roorkee（印度理工学院鲁尔基分校）

作者：Arnav Bendre, Guneesh Gupta, Kavish Grover, Chayan Aggarwal, Shreyansh Modi

英文摘要：Contrastive decoding (CD) has been proposed as a training-free strategy for mitigating object hallucinations in multimodal large language models (MLLMs), with reported gains on benchmarks such as POPE. However, recent work has questioned whether these gains reflect genuine improvements in visual grounding. In this study, we reproduce and extend the findings of "The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs." Specifically, we test the claim that CD induces a unidirectional output distribution shift in discriminative datasets and examine its generalizability across datasets. We also verify that the adaptive plausibility constraint (APC) reduces sampling to greedy search on both discriminative and generative benchmarks. Beyond reproduction, we rigorously study the effects of CD across generative and discriminative datasets. We conduct several experiments that provide additional insights: we analyze the logit distributions induced by different CD strategies on generative datasets, propose a proxy method and compare its performance against CD techniques, and investigate how hallucination signals propagate through each layer of the expert and amateur models. Experimental results across MME, POPE, and CHAIR using LLaVA and Qwen validate the original claims and show that the apparent improvements from CD are often spurious and do not consistently translate into stronger visual grounding for reducing hallucinations. These findings challenge the effectiveness of current contrastive decoding strategies and motivate the development of more reliable approaches for mitigating hallucinations in MLLMs.

AI 总结：研究贝叶斯神经网络不确定性量化中高维多峰后验分布探索的计算成本问题，提出基于优化器派生几何的预处理采样策略，可减少采样预热阶段，提升性能与稳定性，且无额外计算成本，经多数据集和架构验证。

链接：https://arxiv.org/abs/2607.25312

机构：TUM（慕尼黑工业大学）； LMU Munich（慕尼黑大学）； RIKEN AIP（理化学研究所先进智能项目中心）

作者：Moritz Schlager, Emanuel Sommer, Thomas Möllenhoff, David Rügamer

英文摘要：Sampling-based methods offer a principled approach to uncertainty quantification in Bayesian neural networks. Their practical use, however, is often challenged by the computational cost of exploring high-dimensional and multimodal posterior distributions. To overcome these difficulties, Bayesian Deep Ensembles, i.e., warmstarting the sampling from several optimized solutions, have proven to be an effective strategy. In this paper, we demonstrate that curvature estimates computed during the warmstart as a byproduct in adaptive optimizers such as AdamW can inform the sampling phase at negligible additional cost. Specifically, our proposed preconditioned sampling strategy based on optimizer-derived geometries can substantially reduce or even eliminate the need for a lengthy sampling burn-in phase and leads to greater numerical stability. This approach consistently maintains or improves predictive performance and uncertainty quantification without any additional computational costs. We confirm the consistency of our findings across various datasets and network architectures.

AI 总结：研究对九种表格基础模型进行分布外性能实证评估，涵盖多种策略与架构，用三个真实世界数据集测试。结果显示模型在分布变化下会退化，还存在可扩展性差距，扩展了表格数据分布外的基准，为高风险领域应用提供证据。

链接：https://arxiv.org/abs/2607.26000

机构：Colegio de Ciencias e Ingenierías, Universidad San Francisco de Quito (USFQ)（基多圣弗朗西斯科大学科学与工程学院）； Rey Juan Carlos University（胡安·卡洛斯国王大学）； Facultad de Ingeniería, Universidad Latina de Panamá（巴拿马拉丁大学工程学院）

作者：Malena Loza, David Chushig-Muzo, Eva Milara, Luis Bote-Curiel, Luis Estrada-Petrocelli, Felipe Grijalva

英文摘要：Tabular Foundation Models (TFMs) have emerged as novel approaches for tabular predictive tasks, demonstrating competitive predictive performance to ensemble tree-based models. Most TFMs are trained and evaluated on independent and identically distributed data, but this assumption changes in real-world scenarios due to distribution shifts, which compromise the robustness of models. Limited research has been conducted of TFMs under distribution shifts. We present an empirical evaluation of Out-Of-Distribution (OOD) performance of nine TFMs, spanning diverse pre-training strategies and architectures: TabPFNv2, TabPFNv2.5, TabPFNv2.6, TabPFNv3, TabICL, TabICLv2, Mitra, LimiX and TabFM. Three real-world datasets from the TableShift study were considered (HELOC, Voting, Childhood Lead), covering label, socioeconomic, and geographic shift types. Our results show that all evaluated TFMs degrade systematically under distribution shift regardless of pre-training strategy, with shift gaps ranging from 0.003 to 0.060 depending on shift type. The relationship between in-distribution and OOD predictive performance documented for classical tabular models extends into TFMs. We also identified a scalability gap, as high-performing models demand significant memory and computational resources beyond what standard deployment infrastructure can support. This study extends existing benchmarks for OOD in tabular data, providing evidence to support their adoption in high-stakes domains characterized by structural distribution shifts.

AI 总结：研究针对消息传递图神经网络局限，提出CondPSE编码器，用多项式图滤波器组和条件调制处理节点探针，预训练后冻结用作下游输入编码。在合成基准上提升结构判别准确率，在分子性质预测中与GPSE相当，探讨了其优势及局限性。

链接：https://arxiv.org/abs/2607.25169

机构：Sungkyunkwan University（成均馆大学）

作者：Woohyun Lee, Hogun Park

英文摘要：Message-passing graph neural networks are bounded by the 1-WL test and can miss topological structure that distinguishes non-isomorphic graphs. Positional and structural encodings (PSE) inject such topology-derived signals, and learned PSE encoders such as GPSE pretrain a single encoder to produce these signals from random node probes, which can then be frozen and reused as inputs across downstream graph models. We present CondPSE, a learned PSE encoder that applies a learnable polynomial graph filter bank to standard Gaussian node probes and refines the resulting structural-response branches through FiLM-style modulation conditioned on cross-filter, local message-passing, and graph-level signals. CondPSE is pretrained to reconstruct node-level positional/structural targets and graph-level invariants, and is then frozen for use as a downstream input encoding. On synthetic structural-discrimination benchmarks, CondPSE separates graph structures that 1-WL-bounded message passing cannot: it raises CSL accuracy from 42.9% to 97.3% and EXP accuracy from 68.3% to 99.9% relative to GPSE, and ablations show that the polynomial filter bank accounts for most of this gain. On real molecular property prediction, the picture is more limited. With a hybrid local-message-passing/global-attention backbone, CondPSE performs comparably to GPSE without surpassing it, and a ZINC backbone sweep shows no consistent ordering between the two encoders. We report these results and discuss why strong synthetic structural discrimination does not, on its own, yield a downstream advantage for frozen learned PSE encoders, including the role of downstream integration and possible mismatch between structural pretraining targets and molecular property labels.

AI 总结：研究针对图神经网络共形预测中扩散方法的不足，提出HeAD-CP，通过GNN softmax导出的无标签局部同质性估计确定系数，有三个变体，在多个基准测试中表现优于DAPS，有效解决异质性问题。

链接：https://arxiv.org/abs/2607.25273

作者：Phan Binh Nguyen Lam, Nguyen Thai Anh

英文摘要：Conformal prediction (CP) provides distribution-free uncertainty quantification, and its extension to graphs is an active research direction. Diffused Adaptive Prediction Sets (DAPS) is a widely used graph-aware diffusion baseline, propagating Adaptive Prediction Sets (APS) non-conformity scores along edges with a uniform coefficient $\lambda$. We identify a fundamental shortcoming of this design: the uniform low-pass diffusion presupposes graph homophily and proves detrimental on heterophilic graphs, enlarging the mean prediction-set size by up to 10.6% relative to plain APS. To mitigate this, we propose HeAD-CP, a family of node-wise diffusion variants whose coefficients are determined by a label-free local-homophily estimate derived from the GNN softmax. Three variants, namely signed-$\gamma$, edge-compatibility, and a DAPS-baseline-with-correction, are most effective at extreme heterophily, intermediate heterophily, and moderate-to-high homophily, respectively, and all preserve the marginal coverage guarantee. On ten benchmarks, the HeAD-CP family stays at or below plain APS on every dataset, while DAPS exceeds APS on six. The post-hoc oracle over the family improves over DAPS on 8/10 datasets at $p<0.01$ (paired Wilcoxon), with the largest gains on heterophilic graphs (10.3% on Texas); on the two homophilic datasets where DAPS still wins (CiteSeer, PubMed), it retains a marginal advantage of at most 0.002, statistically insignificant on CiteSeer ($p=0.23$). Designing a calibrated label-free selector that approaches this oracle is the main outstanding empirical question.

AI 总结：研究层状图神经网络中检查点依赖性与任务级价值，用两个估计量区分相关说法，通过任务零定理和精确框架模型说明差异，经实验验证，表明学习的映射可控制计算但非不可或缺，相关说法应结合检查点干预与重新训练。

链接：https://arxiv.org/abs/2607.25387

作者：Yi Liu

英文摘要：Learned restriction maps in sheaf graph neural networks are often treated as proof that the model has discovered useful edge geometry. That conclusion does not follow from parameter movement or from a post-hoc ablation: both can show how one checkpoint is organized while leaving open whether learned transport still helps after the rest of the model adapts. We separate these claims with two estimands. Checkpoint reliance intervenes on the maps of a fixed predictor; protocol-relative replacement retrains matched families that remove map capacity, edge variation, or persistent edge assignment. A task-null theorem shows why the claims can diverge: labels identify only the transported classifier directions, leaving $d^2-d$ invisible degrees of freedom in every full $d\times d$ map. An exact frame model then gives the boundary at which reliance becomes unreplaced task value. Label-only training realizes the predicted separation, while audits of public NSD, DNSD, and Directed Sheaf Neural Network (DSNN) implementations recover both replaceable and unreplaced transport regimes on real graphs. All five DNSD benchmarks exhibit fixed-checkpoint reliance. After retraining, assignment-breaking or shared-map controls recover Full performance on four; Roman-Empire retains a $.0675$ advantage over continually resampled assignment and a $.0391$ advantage over a parameter-matched shared map across ten official splits. Thus, a learned map can govern a fitted computation without constituting indispensable edge geometry. Claims of learned transport should pair checkpoint interventions with matched retraining.

AI 总结：研究针对肽疗法结构预测难题，提出Vilya-2扩散变换器，能对不同分子与靶点相互作用建模。通过生成多样结构集合排序，在肽界面恢复等方面远超现有模型，还在小分子对接等表现出色，可作基础模型，统一了预测准确性与通用性。

链接：https://arxiv.org/abs/2607.25156

机构：Vilya Research（Vilya研究团队）

作者：Vilya Research: Pascal Sturmfels, Naozumi Hiranuma, Milad Salem, Benjamin D. Sellers, Stephen Rettie, CJ San Felipe, Chase A. P. Wood, Jeffrey K. Holden, Adam P. Moyer, Patrick J. Salveson, Ivan Anishchanka

英文摘要： Structure-prediction networks built on co-evolutionary statistics have transformed protein-based drug discovery, yet their accuracy does not extend to peptide therapeutics--an increasingly important modality defined by non-canonical residues, macrocyclization, and complex topologies. We introduce Vilya-2, a diffusion transformer that extends the all-atom representation of Vilya-1 from modeling individual molecules to modeling their interactions with protein targets. This all-atom representation enables transfer learning between different molecular types, and delivers highly accurate structural modeling of peptides across sizes, classes, and compositions bound to therapeutically relevant targets. By generating diverse structural ensembles and ranking them with calibrated confidence, Vilya-2 recovers 59.1% of peptide interfaces to sub-2 Å backbone RMSD, far exceeding the performance of a representative co-folding model even when that model is given the bound receptor as a template. In addition, Vilya-2 is state-of-the-art at small-molecule docking, and generalizes to novel protein-small molecule complexes unlike those seen in training. It also generalizes to modeling molecular conformations of diverse macrocycles and disulfide-stapled miniproteins several-fold larger than any molecule seen in training. Finally, Vilya-2 can be used as a foundation model, and fine-tuned to enrich for active compounds in hit-to-lead campaigns. By unifying predictive accuracy with broad generalizability across chemical space, Vilya-2 is the structure-prediction oracle that de novo peptide design pipelines require--establishing the all-atom approach as a general foundation for the design and evaluation of de novo peptide therapeutics.

AI 总结：研究针对Stiefel流形优化中现有方法的问题，提出无回缩且无惩罚参数算法，利用相关特性建立收敛保证。将LoRA微调问题转为流形优化问题，引入Manifold-LoRA，经实验验证其在加速训练及下游性能方面的优势。

链接：https://arxiv.org/abs/2607.25299

机构：Center for Data Science, Peking University（北京大学数据科学中心）； Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）； Beijing International Center for Mathematical Research, Peking University（北京大学北京国际数学研究中心）； Department of Mathematics, University of California, Berkeley（美国加州大学伯克利分校数学系）； Center for Machine Learning Research and Changsha Institute for Computing and Digital Economy, Peking University（北京大学机器学习研究中心和长沙计算与数字经济研究院）

作者：Yuan Zhang, Jiang Hu, Zhijian Lai, Lin Lin, Zaiwen Wen

英文摘要：Optimization over the Stiefel manifold plays a significant role in various machine learning tasks. Existing methods either use the retraction operators, requiring costly orthonormalization for large-scale matrices, or employ landing methods that rely on careful step size selection and penalty parameter tuning. To address these challenges, we propose a retraction-free and penalty parameter-free algorithm that directly lands on the manifold. By leveraging the strongly-convex-like property of the quadratic penalty function and the proximal smoothness of the Stiefel manifold, we establish global convergence guarantees with the best-known iteration complexities under both constant and diminishing step sizes. Then, we reformulate the low-rank adaptation (LoRA) fine-tuning problem for large language models as a manifold optimization problem, introducing Manifold-LoRA for geometry-accelerated adaptation. This approach employs the proposed landing technique and a carefully designed step size strategy to accelerate the training process. Numerical experiments on benchmark datasets demonstrate the efficiency and strong downstream performance of the proposed method.

AI 总结：研究针对持续、可理解视觉识别问题，提出跨多尺度编码形状结构的新视觉特征表示并集成到网络细化学习中，改进学习动态和读出，在类增量MNIST上大幅提准确率，保留早期学习类且表示可解释。

链接：https://arxiv.org/abs/2607.25531

作者：Zeki Doruk Erden

英文摘要：Contemporary machine learning struggles to learn continually, reuse prior knowledge, and expose a comprehensible internal structure. A recently proposed developmental, gradient-free learning framework addresses these limitations by learning a discrete, topological model of its inputs through local variation and selection, yielding an inherent continual-learning guarantee: new observations refine existing structure without overwriting past knowledge, and without replay buffers or predefined task boundaries. Its extension to visual inputs demonstrated this principle on shape recognition, but relied on a feature representation of limited expressivity that capped recognition accuracy. We introduce a new visual feature representation that encodes shape structure across multiple scales, capturing edge and contour features together with their spatial relations, and integrate it with the network-refinement learning process; we further improve the learning dynamics and the read-out used to predict from the learned model. The study targets two-dimensional shape, with class-incremental MNIST as a controlled, interpretable benchmark in which continual-learning behavior can be measured directly. Our approach substantially increases accuracy over the prior representation, matching or exceeding replay- and regularisation-based baselines at comparable storage while storing no past data, and preserves the framework's defining behavior: earlier-learned classes are retained as new ones are introduced, with no destructive adaptation, and the learned representations remain human-interpretable. What separates the methods is retention: the baselines surrender most of a just-trained class within its own cycle and relearn it afterwards, which ours does not. The significance lies in the manner of learning. The system integrates information one sample at a time while provably preserving its responses to...

AI 总结：研究如何从权重中检测用于生成CSAM的文本到图像的LoRA，利用LoRA更新的左上角奇异向量形成的指纹$u_1$，以人类主体年龄为代理，发现其能识别训练内容、跨模型泛化且对良性内容不判断，可直接从权重筛选有害LoRA。

链接：https://arxiv.org/abs/2607.25750

作者：David Demitri Africa, Cate Heine, Nadine Staes-Polet, Kimberly Mai

英文摘要：Low-rank adaptation (LoRA) fine-tuning has made it cheap and easy to customize open-weight image generation models for specific tasks, including the production of child sexual abuse material (CSAM). Existing moderation relies on metadata or generated outputs, but metadata can be deceptive and generating outputs may itself be unacceptable or illegal. We show that a safer signal lives in the weights. The top-left singular vectors of a LoRA's updates form a compact, inference-free fingerprint ($u_1$) of its strongest learned change. Using human-subject age as a benign proxy for CSAM, we find that $u_1$ identifies what a LoRA was trained on, generalizes across base models, and abstains on unrelated benign content. The signal is robust to additive weight noise, rescaling, and precision reduction. These results indicate that harmful LoRAs could be screened directly from their weights without relying on metadata or generating harmful outputs.

AI 总结：研究针对交通传感器网络动态变化致传统预测模型性能下降问题，提出A2TTA框架，将拓扑诱导误差转化为输出校准问题，区分时间自适应，联合应对拓扑演变和多尺度时间偏移，实验证明该框架能有效提升预测性能。

链接：https://arxiv.org/abs/2607.25875

机构：University of New South Wales（新南威尔士大学）； Griffith University（格里菲斯大学）； Beihang University（北京航空航天大学）； RMIT University（皇家墨尔本理工大学）

作者：Du Yin, Xiachong Lin, Yue Tan, Jinliang Deng, Estrid He, Hao Xue, Flora D. Salim

英文摘要：Traffic forecasting is important for efficient traffic management and route planning in smart cities. Existing traffic forecasting studies typically assume fixed sensor graphs, overlooking the continuous evolution of real-world traffic networks, e.g., ongoing road network construction and evolving human mobility patterns. These dynamic changes can substantially degrade conventional forecasting models, motivating test-time adaptation (TTA) to efficiently adapt pretrained models during deployment. However, applying TTA to evolving traffic sensor networks remains challenging in two aspects. First, topology expansion introduces new sensors and connections, continuously reshaping the sensor graph. Second, tem- poral shifts vary in time scale and stability, requiring differentiated adaptation to long-term and short-term shifts. In this study, we address these challenges by proposing A2TTA, an Anchored-and-Agile Test-Time Adaptation framework for evolving traffic sensor networks, which transforms topology-induced forecasting errors into an expandable output calibration problem and separates tem- poral adaptation into persistent global correction and agile context-specific specialization. By jointly addressing topology evolution and multi-scale temporal shifts, A2TTA enables efficient and robust adaptation to continuously evolving traffic environments. Extensive experiments on ten real-world traffic networks demonstrate that A2TTA consistently improves forecasting performance across different backbones, datasets, and prediction horizons. Our code is available in this https URL.

AI 总结：研究针对乳腺X线摄影分类性能提升难题，提出DITL框架，整合数据集难度信号与邻域监督，引入自适应组件，无需超参数调整，在大规模和小数据集上均有出色表现，建立了通用的乳腺X线摄影分类框架。

链接：https://arxiv.org/abs/2607.26043

机构：Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg（模式识别实验室，埃尔朗根-纽伦堡弗里德里希-亚历山大大学）； Siemens Healthineers（西门子医疗）

作者：Adarsh Bhandary Panambur, Siming Bayer, Andreas Maier

英文摘要：Enhancing classification performance in mammography remains a persistent challenge across both small curated datasets and large-scale clinical cohorts. Conventional transfer learning approaches often neglect dataset-specific characteristics, while recent neighborhood-informed methods have been restricted to narrow tasks with rigid formulations, limiting their scalability to population-level datasets. To address these challenges, we propose the Dataset-Informed Transfer Learning (DITL) framework, which integrates dataset-derived difficulty signals with neighborhood-based triplet supervision in a unified objective. DITL introduces two adaptive components: (i) Adaptive Difficulty-Weighted Cross-Entropy (A-DWCE), which assigns per-sample weights based on k-nearest neighbor label purity in a self-supervised feature space, and (ii) Adaptive Neighborhood Representation Triplet (A-NR-Triplet), which enforces intra-class compactness and inter-class separation using a learnable margin. Unlike focal loss, DITL requires no hyperparameter tuning, removes heuristic weighting and fixed margins, and incurs negligible computational overhead, yielding a robust and scalable optimization strategy. On the large-scale VinDR-Mammo dataset, DITL achieves state-of-the-art performance for whole-image breast density classification, with significant improvements across accuracy, F1-score, and AUC (p < 0.0001). Beyond large cohorts, DITL also delivers consistent, statistically significant gains on small ROI datasets (p < 0.0001). By bridging small-scale lesion analysis with large-scale density estimation, DITL establishes a clinically relevant, scalable, and generalizable framework for mammography classification, spanning the full breast cancer screening-to-diagnosis spectrum.

AI 总结：研究针对金融模型无标准答案的问题，引入GAUGE基准，依据分析师实际做法评估代理构建的估值模型，通过多种方式验证，揭示高级、初级分析师及学生在模型评分上的差异，指出当前代理在模型构建与估值判断上的强弱情况，并发布相关资源。

链接：https://arxiv.org/abs/2607.24889

机构：Shanghai Jiao Tong University（上海交通大学）； University of Adelaide（阿德莱德大学）； Tsinghua University（清华大学）； National University of Singapore（新加坡国立大学）； Peking University（北京大学）

作者：Jiacheng Lu, Sinuo Wang, Wentao Zhao, Rui Sun, Cheng Hua, Tao Song, Hui Cai, Beidi Luan, Zhengze Wu, Lingjing Teng, Yijia He, Jing Li, Daxin Jiang, Zuo Bai, Haibing Guan

英文摘要：Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations. While some components can be checked mechanically, forecasts, discount rates, and target prices often admit multiple reasonable answers. Existing benchmarks nevertheless tend to grade such outputs against a single expert reference. Using independently built analyst models for the same companies, we find that across 108 directed pairs covering 65 companies, the median single-reference score is 0.33, 92.6% score below 0.70, and no same-vintage pair agrees on implied price within 10%. Point-tolerance grading can therefore penalize disagreement already present among professionals. We introduce GAUGE, a benchmark for evaluating agent-built valuation models against observed analyst practice rather than a single point answer. GAUGE uses 1,001 vendor-classified analyst workbooks and a 196-task evaluation set, with a three-layer observed-practice envelope, 56 auditable facets, eight validity gates, and deterministic structural checks. We validate the benchmark with a 55-participant known-groups study, company-grouped cross-fitting, and judge-stability audits. On the failure-aware score $\phi_0$, senior analysts average 88.3, juniors 66.0, and finance students 43.2. Across 24 agents and 1,011 scored generations, the best agent scores 53.4, above the student mean but below every senior and most juniors. It passes 93% of mechanical facets and 78% of judgment facets, with a fleet-median gap of 26 points. Current agents are substantially stronger at model construction than valuation judgment. We release the methodology, a gated de-identified data tier, a controlled training split, a versioned 48-task evaluation core, and a withheld refresh pool.

AI 总结：研究从多个无标签混合物进行多类学习的问题，利用后验单纯形几何结构，提出无先验程序，通过训练标准分类器区分混合物身份并提取潜在类结构，实验证明能恢复潜在类及其比例，缩小弱监督与全监督性能差距。

链接：https://arxiv.org/abs/2607.24943

机构：Università degli Studi di Milano（米兰大学）； Istituto Nazionale di Fisica Nucleare（意大利国家核物理研究所）

作者：Raphaël Bonnet-Guerrini, Johann Ioannou-Nikolaides, Troels Petersen, Vincenzo Piuri

英文摘要：In many classification problems, reliable instance-level labels are unavailable. However, it is often possible to construct weakly enriched unlabeled samples: datasets selected by different cuts, sources, populations, or experimental conditions that change latent class proportions without revealing them. Classification without Labels (CWoLa) shows that, in the binary case ($K=2$), a classifier trained to distinguish two impure mixtures with different class proportions can recover an optimal class discriminator without knowing the mixture proportions. We extend this principle to multiclass learning from several unlabeled mixtures ($K>2$), where the learner observes only mixture identity and neither latent class labels nor class-prior matrices. We prove that, for a multiclass mixture model, the Bayes-optimal mixture classifier $g^\star$ maps data points into a $(K-1)$-simplex embedded in mixture-posterior space. The $K$ vertices of this simplex are induced by the latent classes through the unknown mixing matrix. Leveraging this geometry, we propose prior-free procedures that train a standard classifier to distinguish mixture identities and then extract latent class structure using either post-hoc simplex fitting or a bottleneck architecture. Experiments on MNIST, CIFAR-10, and Galaxy10 DECaLS show that mixture identity alone can recover latent classes and their fractions in the mixture. By narrowing the gap between weakly supervised and fully supervised performance, we provide a mathematically grounded, scalable tool for multiclass discovery in label-scarce domains.

AI 总结：该研究基于Neurai-VN数据集构建可重复基准，定义四个临床相关二元分类任务，用标准化受试者交叉验证评估，在预定义特征配置下评估多种基线模型，给出各任务F1分数，为心理健康分类任务的多模态DP研究提供可重复基线。

链接：https://arxiv.org/abs/2607.25232

机构：College of Engineering and Computer Science, VinUni-Illinois Smart Health Center, VinUniversity（工程与计算机科学学院，VinUni - 伊利诺伊智能健康中心，Vin大学）； School of Biomedical Engineering, International University, Vietnam National University HCMC（生物医学工程学院，胡志明市越南国立大学国际大学）

作者：Quoc-Cuong Pham, Hoang-Thuy-Duong Vu, Thi-Thanh-Huong Ha, Huy-Hieu Pham

英文摘要：Digital phenotyping (DP) using smartphones and wearable devices has shown considerable potential for mental health monitoring. However, progress remains difficult to evaluate due to heterogeneous datasets, inconsistent preprocessing pipelines. In this study, we present a reproducible benchmark built upon the Neurai-VN dataset, a high-resolution, multimodal dataset comprising passive sensing and active assessment from wearable and smartphone devices, collected from 100 Vietnamese adults over two weeks. The benchmark defines four clinically relevant binary classification tasks evaluated using standardized subject-wise cross-validation. Representative linear, tree-based, and neural baseline models are evaluated across predefined feature configurations. Mean subject-level F1 scores across five cross-validation folds reached 0.71 for Healthy Control vs. Depression and Healthy Control vs. Clinical, while Healthy Control vs. Anxiety and Depression vs. Anxiety achieved 0.69 and 0.56, respectively. These benchmark results provide reproducible baselines for future research on multimodal DP for mental health classification tasks.

AI 总结：研究张量多视图聚类中基于t-SVD方法依赖样本排列“周期性假设”的问题，提出基于图傅里叶变换的图谱低秩张量学习框架及锚点变体，不依赖特定排序捕捉内在结构，实验证明该方法性能优于现有方法。

链接：https://arxiv.org/abs/2607.25295

作者：Jintian Ji, Xingsu Li, Songhe Feng

英文摘要：Tensorial multi-view clustering (TMC) has achieved strong performance due to its ability to capture high-order correlations across multiple views. Most existing t-SVD-based TMC frameworks apply the Fast Fourier Transform (FFT) along the sample mode to impose frequency-domain low-rank constraints. However, we reveal that this widely adopted design critically relies on an implicit ``periodicity assumption'' induced by the sample arrangement. When samples are ordered by class, neighboring indices tend to be semantically similar, creating artificial local continuity along the sample mode and a favorable spectral structure for FFT-based low-rank regularization. Once this ordering is removed by random permutation, existing t-SVD-based TMC methods suffer severe performance degradation. This strong sensitivity to class ordering conflicts with the permutation-invariant nature of clustering and indicates that part of the reported performance may be attributed to a privileged sample arrangement rather than genuine high-order structure modeling. In this paper, we systematically investigate this phenomenon and its underlying algebraic and spectral mechanisms. To address this fundamental flaw, we further propose a graph-spectral low-rank tensor learning framework based on the Graph Fourier Transform (GFT), which replaces the fixed Fourier basis along the sample mode with a data-driven graph spectral basis, thereby capturing the intrinsic manifold structure without relying on a particular sample ordering. Moreover, we develop an anchor-based variant to address large-scale datasets efficiently. Extensive experiments on various benchmarks validate our findings and demonstrate the competitive or superior performance of the proposed methods compared with state-of-the-art TMC approaches.

AI 总结：研究序列模型在部分可观测下如何表示潜在随机动态，发现在随机波动率设置中有两阶段计算，Transformer中潜态可解码性在特定阶段出现，输出头替换揭示部分退化原因，为机械可解释性提供有用基准。

链接：https://arxiv.org/abs/2607.25459

机构：Temple University（天普大学）； Dickinson College（迪金森学院）

作者：Xiaoyu Huang, Lulu Wang

英文摘要： Mechanistic interpretability has largely focused on language models and deterministic toy tasks. Much less is known about how sequence models internally represent latent stochastic dynamics under noisy, partially observed observations. We study this question in a controlled multivariate stochastic volatility setting, where models observe only returns while the ground-truth latent volatility state is known to the researcher. This setting provides a useful benchmark for mechanistic interpretability under partial observability: the latent state is hidden from the model but directly available for evaluation. Across architectures, losses, and output heads, we find evidence for a two-stage computation. Hidden representations encode substantial information about the next latent volatility state, and the output head maps this representation to squared return forecasts. Furthermore, in Transformers, latent-state decodability emerges at identifiable architectural stages whose location depends on the volatility period. In long-cycle regimes, this computation simplifies into an explicit latent-state filter consisting of a learned linear projection followed by $\ell^2$ normalization. Output-head replacement further shows that part of the degradation under noisy MSE training arises from readout misalignment rather than representation failure. These results suggest that stochastic volatility models provide a useful benchmark for mechanistic interpretability under noisy latent dynamics and partial observability.

AI 总结：研究针对抗菌肽计算发现评估问题，引入AMPBench-MT基准，将多种相关指标纳入同源性控制协议，通过模型评估揭示高二元性能与实验终点行为不符，指出应转向终点感知证据审核，为抗菌肽评估提供新方法。

链接：https://arxiv.org/abs/2607.25518

机构：Shanghai Ocean University（上海海洋大学）； Tongji University（同济大学）； Center for Safe AGI（安全通用人工智能中心）； DP Technology（DP技术公司）

作者：Ziheng Zhou, Huiyu Luo, Xiaohu Zhu, Nan Wang, Xuebiao Qin, Chaoyan Zhang, Jun Yan

英文摘要：Computational AMP discovery is often evaluated through AMP/non-AMP recognition, yet follow-up decisions depend on assay-derived evidence such as target-species potency, hemolysis, toxicity, and selectivity. Existing AMP and peptide benchmarks cover binary recognition, multilabel annotation, assay regression, or broader peptide-model comparison, but they do not jointly place AMP recognition, species-conditioned potency, spectrum, safety-facing proxy endpoints, and cross-endpoint behavior within one sequence-homology-controlled protocol. To address this problem, we introduce AMPBench-MT, a provenance-preserving benchmark that standardizes canonical peptide records and organizes them into binary recognition, species-conditioned pMIC regression, and endpoint-specific potency and safety-facing readouts. Across 161 endpoint-specific model evaluations, high binary performance does not reliably indicate assay-endpoint behavior. Frozen protein-language-model embeddings form the leading pMIC error cluster, while graph and classical regressors remain close. Spectrum labels further reveal that PR-oriented metrics can be misleading under scarce observed negatives, whereas low-toxicity, HC50 hemolysis, and selectivity expose smaller but more assay-facing signals. AMPBench-MT shows that AMP evaluation should move beyond recognition leaderboards toward endpoint-aware evidence auditing. Our proposed benchmark is available at this https URL.

AI 总结：针对2022年IEEE大数据杯出行目的地预测挑战，提出基于规则的访问循环（RVC）模型。该模型利用出发地信息和个人出行行为确定目标大都市区目的地，无需从训练区域学习，实验表明其性能优于监督学习方法和其他启发式方法，在竞赛中获第二名。

链接：https://arxiv.org/abs/2607.25751

作者：Eng-Shen Tu, Yong-Han Chen, En-Chao Liu, Hao-Yun Keng, Cheng-Te Li

英文摘要：In this paper, we propose the Rule-based Visiting Circulation (RVC) model in tackling the challenge in the IEEE Big Data Cup 2022: Trip Destination Prediction. Given trips containing travel information, personal attributes, origin zones, and their features in the training metropolitan areas, the task is to predict the destination of every trip in a targeted metropolitan area whose destinations are not given at all at the training stage. We highlight the challenges in this destination prediction task -- having no knowledge of the destinations in the targeted metropolitan area. We provide insights from the datasets, in which revisiting behaviors and the relationships between origins and destinations play a crucial role in individuals' trips. Hence, we design a simple but comprehensive method, rule-based visiting circulation, which directly utilizes the origin information and individuals' trip behaviors to determine the destinations in the targeted metropolitan area, i.e., requiring no learning from the four training areas. Experimental results on both offline evaluation and leaderboard submission consistently exhibit the proposed RVC can significantly outperform supervised learning methods and other heuristics. The RVC method eventually brings us to second place in the competition leaderboard.

AI 总结：研究针对欧拉 - 伯努利梁振动问题，提出SpectONet框架，融合DeepONet算子学习能力、物理信息约束与CGL传感器放置，采用非均匀谱传感器位置，经实验验证其比多个基线模型预测误差更低，为结构振动分析提供有效框架。

链接：https://arxiv.org/abs/2607.25790

机构：Department of Mathematics and Scientific Computing, National Institute of Technology Hamirpur（印度国家技术学院哈米尔布尔分校数学与科学计算系）； The Hatter Department of Marine Technologies, Leon H. Charney School of Marine Sciences, University of Haifa（海法大学莱昂·H·查尔尼海洋科学学院哈特海洋技术系）

作者：Shivani Saini, Ramesh Kumar Vats, Arup Kumar Sahoo

英文摘要： This paper proposes a novel physics-guided spectral deep operator network, termed SpectONet, for solving Euler-Bernoulli beam (EBB) vibration problems. The proposed framework integrates the operator-learning capability of DeepONet with physics-informed constraints and Chebyshev-Gauss-Lobatto (CGL) sensor placement. Unlike conventional DeepONet frameworks, which commonly employ uniformly distributed sensors, SpectONet uses nonuniform spectral sensor locations with a higher concentration of points near the domain boundaries. This sampling strategy improves the finite-dimensional representation of boundary-sensitive structural responses while requiring only a limited number of branch-network inputs. The governing beam equation, together with the associated initial and boundary conditions, incorporated into the training objective to promote physically consistent and generalizable predictions. Numerical experiments on three synthetic EBB vibration problems and a real-world bridge vibration dataset demonstrate the effectiveness of the proposed framework. Comparisons with strong baselines such as, Vanilla DeepONet, PI-DeepONet, PINN, and CNN-UNet show that SpectONet consistently achieves lower prediction errors across all considered evaluation metrics. In particular, SpectONet achieves at least \(64\%\) improvement over the considered baseline models across the three synthetic problems and at least \(37\%\) for the real-world problems. These results demonstrate that SpectONet provides an accurate, computationally efficient, and physically consistent operator-learning framework for structural vibration analysis.

AI 总结：研究针对上肢截肢者假肢控制中组合运动识别难题，提出CPI和SAP两种零样本学习方法，基于嵌入空间线性插值假设，在多数据集实验中，SAP表现出色，组合运动准确率大幅提升，在在线推理实验中优势也得以保持。

链接：https://arxiv.org/abs/2607.25826

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

作者：Rui Liu, Benjamin Paassen

英文摘要：Surface electromyography (sEMG) enables the control of prostheses, allowing upper-limb amputees to re-gain some hand function. Most current research focuses on recognizing basic movements for prosthesis control. However, in most daily activities, such as opening a door, combined movements are essential. However, collecting training data for all possible combined movements is time-consuming and requires re-training of the model for any new combination. We propose two novel recognition approaches, Compositional Prototype Interpolation (CPI) and Synthetic Adaptation for Prototypes (SAP), that enable zero-shot learning of combined, novel and unseen movements in Prototype Networks after training only with basic movements. Our methods rest on a linear interpolation assumption in the embedding space, which we study by inspecting the geometry of combined motions in signal and embedding space. In experiments on the NearLab and NinaPro DB3 data sets as well as our newly recorded BasCom dataset, our proposed SAP outperforms prior zero-shot learning methods with accuracy improvements on combined movements of more than 20%. This advantage is maintained in online inference experiments in a user study.

AI 总结：研究针对大语言模型在金融预测中证据不足时高置信度的问题，提出FinAbstain框架，通过多模态检索增强生成及选择性预测，经多种不确定性评估方法和指标评估，贡献了时间安全架构、复合不确定性公式和可重复评估蓝图。

链接：https://arxiv.org/abs/2607.24875

作者：Dorothy Torres, Wei Cheng, Henan Huang

英文摘要：Large language models (LLMs) can synthesize financial narratives but may express high confidence when evidence is sparse, stale, or contradictory. This failure is especially consequential in forecasting, where filings, news, prices, volume, and technical signals can disagree. We present FinAbstain, a research framework for uncertainty-calibrated multimodal retrieval-augmented generation (RAG) with selective prediction. A point-in-time retriever admits only information public at the forecast timestamp and supplies modality-specific evidence to fundamental, news, technical, risk, and verification agents. Their probabilistic assessments are aggregated with retrieval relevance, evidence contradiction, repeated-sample consistency, and historical calibration statistics. Temperature scaling, isotonic regression, conformal prediction, and a proposed hybrid uncertainty score are evaluated under a common chronological protocol. A controller predicts bullish, bearish, or neutral outcomes only when uncertainty is below a validated threshold; otherwise it abstains, requests evidence, reduces exposure, or routes the case to human review. The evaluation covers one- and five-day abnormal-return direction, twenty-day volatility intervals, and abstention decisions, using accuracy, calibration, risk--coverage, citation, trading, latency, and cost metrics. To make the design auditable before a full data collection is complete, we report explicitly labeled simulated results rather than empirical claims. These results illustrate the intended hypothesis: calibrated abstention may trade coverage for lower selective error and drawdown. The contribution is a time-safe architecture, a composite uncertainty formulation, and a reproducible evaluation blueprint for evidence-grounded selective financial forecasting.

AI 总结：研究文本条件时间序列预测问题，核心方法是将预测设为TSFM生成轨迹上的规划问题，以冻结TSFM为模拟器、LLM为策略和价值函数，实例化\rc{}框架，主要贡献是通过实验证明该框架能带来持续改进。

链接：https://arxiv.org/abs/2607.24892

机构：Deakin University（迪肯大学）； Applied Artificial Intelligence Initiative（应用人工智能倡议）

作者：Huu Hiep Nguyen, Dung Nguyen, Minh Hoang Nguyen, Dai Do, Hung Le

英文摘要：Text-conditioned time-series forecasting predicts a series from both its numerical history and natural-language context, allowing forecasts to account for events and constraints that the past alone cannot reveal. This requires both reliable numerical forecasting and the ability to interpret contextual information. Time-series foundation models (TSFMs) provide strong numerical forecasts, while large language models (LLMs) can reason over text, but combining their strengths remains challenging because asking an LLM to generate or revise forecast values directly can distort the temporal structure captured by the TSFM. We instead formulate forecasting as a planning problem over TSFM-generated trajectories. The frozen TSFM acts as a simulator that proposes numerical continuations, while the LLM acts as a policy and value function that guides candidate selection and evaluates completed trajectories against the context. We instantiate this as \rc{} (\textbf{L}LM \textbf{A}s \textbf{F}orecasting \textbf{P}lanner), a training-free framework that bridges the modality gap without retraining either model, using Monte Carlo tree search (MCTS) over the forecast horizon with a \emph{Ranker} LLM as policy and a \emph{Judge} LLM as value function. Experiments on Context-is-Key and Time-MMD across two TSFM backbones (Chronos and TimesFM) and four LLMs show that \rc{} delivers consistent improvements across model choices, supporting sequential search as an effective training-free approach to text-conditioned forecasting.

AI 总结：研究提出物理信息广泛学习系统（PI-BLS）求解偏微分方程，将控制微分算子等嵌入线性输出层优化问题，以确定性最小二乘解取代非线性梯度训练，简化学习过程，实验显示其在减少训练时间和模型参数时性能更优。

链接：https://arxiv.org/abs/2607.25608

机构：Indian Institute of Technology Gandhinagar（印度理工学院甘地讷格尔分校）； Università degli Studi di Firenze（佛罗伦萨大学）； Indian Institute of Technology Indore（印度理工学院印多尔分校）

作者：Pinki Khatun, M. Sajid, Abhinav Jha, M. Tanveer

英文摘要：Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding governing physical laws into deep neural networks. However, their reliance on computationally expensive gradient-based optimization and deep architectures often results in slow training, high computational cost, and limited scalability. In this work, we propose a novel physics-informed broad learning system (PI-BLS), the first physics-informed learning framework based on broad RdNNs. The proposed formulation embeds the governing differential operator and the associated initial and boundary constraints directly into a linear output-layer optimization problem, thereby replacing nonlinear gradient-based training with a deterministic least-squares solution obtained via the pseudoinverse. Consequently, the entire learning process is reduced to a single linear optimization stage while preserving the underlying physical constraints. As a result, PI-BLS offers an efficient learning paradigm for a physics-informed learning framework for solving PDEs that eliminates iterative backpropagation while preserving the underlying physical constraints. Experimental results on representative forward PDE benchmarks demonstrate that PI-BLS achieves competitive and often superior performance with reduced training time and model parameters compared with conventional PINNs.

AI 总结：针对炎热干燥气候下低收入农村住房墙体材料热排序问题，提出两阶段计算框架，先利用有限差分法求解热方程并采样，再用物理信息神经算子学习，实现高精度排序，还得出相关指标，支持循证材料选择。

链接：https://arxiv.org/abs/2607.25668

机构：NED University of Engineering and Technology（国立工程技术大学）

作者：Muhammad Akbar Khan, Fahim Raees, Ubaida Fatima

英文摘要：Identifying cost-effective indigenous building materials that minimise heat penetration through walls is critical for indoor thermal comfort in low-income rural housing in hot-dry climates, where summer temperatures routinely exceed 45 C. We present a two-stage computational framework for thermal ranking of five low-cost indigenous wall materials: mud brick, clay-straw adobe, lime-stabilised bamboo panel, fired clay brick, and lime-mud composite. First, a validated Crank-Nicolson finite difference method (FDM) solves the one-dimensional transient heat equation with Robin boundary conditions under diurnal solar and outdoor air-temperature forcing, generating 1500 periodic-day solutions across a nine-dimensional parameter space by Latin Hypercube sampling. Second, a Physics-Informed Neural Operator (PINO) with a Fourier Neural Operator (FNO) backbone learns the parameter-to-solution operator mu -> T(x,t), enforcing both data fidelity and PDE consistency. The trained PINO attains a relative L2 field error of 5.14e-4 and a 0.201 K mean absolute error on the peak inner surface temperature, preserving the FDM material ranking exactly; PINO trained on 150 FDM samples matches a data-only FNO trained on twice as many, so the physics loss is most valuable when data are scarce. The periodic-day formulation also yields the ISO 13786 time lag and decrement factor, reproduced to within 0.99 h and 0.010. At nominal hot-dry summer conditions, clay-straw adobe achieves the best cost-performance index among widely available materials. A climate sweep, confirmed by FDM spot checks, reveals a regime boundary: under sub-ambient outdoor conditions the ranking inverts to conductive fired clay brick, delineating heat-exclusion and heat-rejection regimes. The framework supports evidence-based material selection for post-flood reconstruction in hot-dry regions.

AI 总结：研究针对ICU时间序列预测问题，提出DRIFT混合框架，直接模型主预测，递归行动条件模型校正。在MIMIC-IV和eICU-CRD数据上评估，结果显示其在降低MAP平均绝对误差上有优势，在特定审核及稳健性实验中表现良好。

链接：https://arxiv.org/abs/2607.25864

机构：MIMIC-IV； eICU-CRD

作者：Weixin Liu, Juming Xiong, Congning Ni, Yanfan Zhu, Xingtao Lin, Bradley A. Malin, Zhijun Yin

英文摘要：Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and laboratory values are influenced by treatments such as vasopressors. However, models that predict the full future sequence all at once make little use of these treatments, whereas autoregressive models can accumulate errors. We introduce DRIFT, a hybrid framework in which a direct model produces the primary forecast and a recursive, action-conditioned model contributes constrained corrections. We evaluate DRIFT on 6,046 admissions from MIMIC-IV and 8,345 admissions from eICU-CRD. Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673% relative to an action-conditioned Temporal Fusion Transformer (TFT-action) on MIMIC-IV and achieves the lowest corresponding error among the compared models on eICU-CRD. Although the overall accuracy improvement is modest, a MIMIC-IV audit restricted to windows in which the supplied treatment sequence was altered showed that DRIFT achieved lower observed-target MAP error than TFT-action at 8 and 24 hours. Treatment-sequence alteration increased DRIFT's MAP error by 0.21-0.26 mmHg more than it increased TFT-action's error, with prediction changes occurring primarily after the supplied paths diverged. In a separate robustness experiment, the MAP advantage persisted under three shared checkpoint-selection rules emphasizing overall endpoint error, MAP error, or both equally.

AI 总结：研究用于产品生命周期管理等系统相似性搜索的表格嵌入，指出领先方法未针对人类偏好对齐排名优化，标准指标不足以评估嵌入可信度，提出具体评估程序并通过PLM用例说明问题。

链接：https://arxiv.org/abs/2607.24880

机构：CONTACT Software GmbH（CONTACT软件有限公司）

作者：Frederik Hoppe, Astrid Franz, Marianne Michaelis, Lars Kleinemeier, Udo Göbel

英文摘要： Task-agnostic tabular embeddings are increasingly used for similarity search in real-world business systems such as Product Lifecycle Management (PLM). However, leading embedding approaches are optimized primarily for prediction tasks - not for producing human preference aligned similarity rankings. We argue that standard downstream metrics are insufficient to fully assess embedding trustworthiness for similarity search and that human preference aligned evaluation is a necessary and currently missing component. We present a concrete evaluation procedure and illustrate the problem through a PLM use case.

AI 总结：研究针对系统复杂性增加致理解困难的问题，利用行为驱动开发（BDD）提出行为驱动的可解释性（BDX）方法，通过结构化场景给出功能操作序列并转化为解释，以RISC-V处理器为例展示其在系统设计中的支持作用。

链接：https://arxiv.org/abs/2607.24881

作者：Caroline Dominik, Rolf Drechsler

英文摘要：As system complexity has vastly increased, it has become significantly more challenging for a single person or a team to fully understand all aspects of an entire system. Particularly, this holds when considering all the different stages of a system's development life cycle, such as, e.g., design or maintenance. But especially for safety-critical systems it is essential that the final design can be trusted. Because of this, explainability is becoming an important requirement for modern systems. In this paper, we aim to achieve this goal by utilizing Behavior-Driven Development (BDD), where the expected system behavior is given in the form of structured scenarios. These scenarios give a sequence of actions for each functionality, and by this can be directly translated into explanations. We introduce this method of deriving explanations based on the specification as Behavior-Driven Explainability (BDX). While applicable at any development stage or abstraction level, a case study for the explanation of exceptions in a RISC-V processor shows the support this concept adds during system design.

AI 总结：研究神经网络宽度缩放问题，引入有效对齐维度，推导训练与测试梯度内积的均值和方差以获失准概率上界，集成到框架得测试风险改进条件，实验表明宽模型有效对齐维度大、失准低，对齐统计量可预测损失变化。

链接：https://arxiv.org/abs/2607.24887

作者：Jinhao Zhang, Zeyu Liu, Zicheng Yan, Yunquan Zhang, Guangming Tan, Fangming Liu, Daning Cheng

英文摘要：Existing theories of neural-network width characterize asymptotic limits, but provide limited guidance on whether an expansion direction identified from finite training data remains beneficial on unseen data. We study this problem for function-preserving residual expansion and introduce the effective alignment dimension, a measurable quantity describing the signal-noise geometry of activation gradients. By deriving the exact mean and variance of the inner product between independently estimated training and test gradients, we obtain a finite-sample upper bound on misalignment probability. The bound depends only on the effective alignment dimension and an effective sample size, requiring finite second moments and a nonzero population gradient, without covariance spectral assumptions or prescribed width-growth rates. We integrate this certificate into the train-test residual-expansion framework, yielding a high-probability condition for test-risk improvement. Experiments across width-controlled LLaMA-style Transformers, Pythia, and ResNet-20 show that wider models exhibit larger effective alignment dimensions and lower empirical misalignment. Direct residual interventions confirm that the alignment statistic predicts the sign and magnitude of held-out loss changes.

AI 总结：研究提出生成式分布鲁棒优化（GDRO）框架，接受可采样条件生成器为名义模型，通过采样器-辛科恩配对限制最坏情况法则，可直接有限样本近似和可微实现，相比名义决策降低了罕见上下文库存遗憾和SocialGAN导航碰撞。

链接：https://arxiv.org/abs/2607.24983

机构：Telfer School of Management, University of Ottawa（渥太华大学泰尔弗管理学院）； Department of Electrical and Computer Engineering, Western University（西安大略大学电气与计算机工程系）

作者：Ziwei Zhang, Jonathan Yu-Meng Li, Zhihao Jin

英文摘要：Generative models are increasingly adopted in distributionally robust optimization (DRO), but existing approaches trade off model compatibility and adversarial structure: methods that accept arbitrary samplers do not restrict worst-case laws to a generator family, while generator-parameterized adversaries rely on model-specific access such as likelihoods, scores, or training data. We propose Generative Distributionally Robust Optimization (GDRO), a principled framework that accepts any sampleable conditional generator as the nominal model and restricts worst-case laws to a chosen conditional generator family. The key is the sampler-Sinkhorn pairing: samplers represent the conditional laws exactly, while Sinkhorn divergence compares their induced distributions without likelihood access and can be estimated from samples alone. The resulting population problem admits a direct finite-sample approximation and differentiable primal-dual implementation at the active decision context. For Lipschitz losses, the population Sinkhorn radius bounds downstream degradation. Across explicit and implicit generators, our method reduces rare-context inventory regret by 60% and SocialGAN navigation collisions by 50% relative to nominal decisions.

AI 总结：研究针对LLM级联推理成本高、置信分数校准不当等问题，提出共形级联框架，以共形预测集大小为推迟规则，提供无分布精度保证，在多基准测试中表现优于启发式级联，且无需模型训练，仅需黑盒API访问。

链接：https://arxiv.org/abs/2607.25018

机构：Department of Computer Science, Florida State University（佛罗里达州立大学计算机科学系）

作者：Yifan Dou, Shikan Fang, Shibo Li

英文摘要： Large language model (LLM) cascades reduce inference cost by routing easy queries to a small model and deferring hard queries to a larger one. Production cascades govern this deferral through a confidence threshold, but LLM confidence scores are miscalibrated, the threshold must be tuned per model pair and per domain, and no setting yields a formal bound on cascade accuracy. We introduce \textbf{Conformal Cascade} (CC), a multi-tier inference framework that uses conformal prediction set size as the deferral rule: accept when the calibrated set collapses to a single answer, defer otherwise. The procedure delivers a distribution-free, finite-sample accuracy guarantee. By a per-tier union bound, the prediction set at the accepting tier covers the correct answer with probability at least $1 - K\alpha$ for any user-specified $\alpha$; under a selection-preservation condition (consistent with, but not strictly implied by, our marginal coverage results), the bound tightens to $1 - \alpha$. We further characterise expected cascade cost as an explicit function of $\alpha$ and the calibration-set acceptance rate. Across 18 multiple-choice benchmarks spanning science, medicine, commonsense, and standardized exams, evaluated on two-tier cascades drawn from four open-weight model families, CC strictly improves over the strongest calibration-tuned heuristic cascade on the majority of family--benchmark pairs, with the largest gains on reasoning-heavy benchmarks where majority vote is unreliable; on easier benchmarks the cascade commits the vast majority of queries to the small model at no accuracy cost. Extension to open-ended generation requires an answer-clustering step that we leave for future work. The method requires no model training and only black-box API access.

AI 总结：该研究针对偏微分方程数值模拟提出基于分数的稳定化框架，通过学习的分数模型定义稳定化算子，增强标准时间步长方案，经数值实验验证该方法能提高鲁棒性、抑制非物理不稳定性并保持定性动力学。

链接：https://arxiv.org/abs/2607.25119

作者：Eshed Gal, Eldad Haber, Uri Ascher

英文摘要：We propose a score-based stabilization framework for numerical simulation of partial differential equations, in which a learned score model defines a stabilization operator applied to provisional numerical updates. This operator augments standard time-stepping schemes by enforcing structure and physical consistency through a correction that drives iterates toward the manifold of admissible states. We show that the stabilization operator acts as a contraction toward this manifold, yielding a correction mechanism with basin-conditional stability. Numerical experiments on Advection, Korteweg-de Vries (KdV), Nonlinear Schrodinger (NLS), and Burgers' equations demonstrate improved robustness, suppression of nonphysical instabilities, and preservation of qualitative dynamics.

AI 总结：研究针对隐藏规则游戏中Transformer智能体的可解释性，通过在其决策令牌嵌入上训练稀疏自编码器，在双规则任务中恢复结构，单个维度对应可解释策略，为解释智能体行为提供方法。

链接：https://arxiv.org/abs/2607.25132

机构：Rutgers University（罗格斯大学）； The University of Hong Kong（香港大学）

作者：Shiwei Tan, Yusong Zhao, Weiyi Qin, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang

英文摘要：A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We report interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR). We focus on a compact two-rule task in which both hidden rules map object shapes to target buckets, but with different permutations. The policy is trained on episodes sampled from these two hidden rules and then evaluated with fixed weights. It is never given a rule label and does not use an explicit rule classifier; any rule information must be inferred implicitly from interaction history. In this setting, the correct rule is not identifiable before the agent tries an informative move and observes accept/reject feedback. Sparse autoencoders (SAEs) trained on the agent's decision-token embeddings recover this structure. When held-out decisions are labeled by simple concepts such as the chosen shape or bucket, SAE dimensions that are highly selective for a concept cover most decisions where that concept is present. Individual SAE dimensions also correspond to interpretable strategies such as probing one rule hypothesis and switching after negative feedback.

AI 总结：研究针对城市洪水预测，开发物理信息训练框架用于CNN-LSTM模型，嵌入三个可微惩罚项。在诺福克洪水数据集评估，物理约束模型重力违规近零、街道通道召回率最高，地形感知惩罚项协调权衡，解决了总体精度与街道层面合理性的矛盾。

链接：https://arxiv.org/abs/2607.25148

机构：University of Virginia（弗吉尼亚大学）； Chandra Robot Autonomy Lab（钱德拉机器人自主实验室）； Link Lab（链接实验室）； Multidisciplinary Research Center（多学科研究中心）； Hydroinformatics Research Group（水文信息学研究组）

作者：Luc DCosta, Yidi Wang, Jonathan L. Goodall, Rohan Chandra

英文摘要：Deep learning surrogate models trained with mean-squared-error loss produce statistically accurate but physically unconstrained flood predictions: water may flow uphill, appear spontaneously, or smooth over street-level corridors. We develop a physics-informed training framework for CNN-LSTM models that predict urban flood depths at 15 min intervals over a 128x128 spatial grid. Three differentiable penalty terms are embedded into the loss: (i) a gravity loss penalizing depth increases against the water-surface-elevation gradient, (ii) a continuity loss enforcing local mass conservation with rainfall-adaptive thresholds, and (iii) a topography-aware false-alarm penalty modulated by the topographic wetness index (TWI). We evaluate on the Norfolk, Virginia flood dataset spanning two storm events (August 2017 and September 2022, 300 samples), with all variants trained on identical splits and robustness assessed over repeated random splits and leave-one-storm-out tests. A road-proximal evaluation restricted to a TWI-derived street mask quantifies street-level skill. The physics-constrained model achieves near-zero gravity violations (order 1e-6) and the highest street-channel recall (0.77 +/- 0.09 vs 0.44 +/- 0.10 for the unconstrained baseline), the capability most relevant to traffic routing, and its advantage more than doubles on a held-out storm; a uniform false-alarm variant attains 16% lower mean absolute error but suppresses street recall to 0.25. The TWI-modulated penalty reconciles this trade-off: it improves on the uniform variant on every metric, recovering 60% higher street recall at the lowest MAE among constrained variants and the best street-level F1. These results expose a fundamental tension between aggregate pixel-level error and application-specific physical plausibility, and show that terrain-aware loss modulation offers a principled resolution.

AI 总结：研究常数深度和对数深度神经网络的算法分离，识别出一类布尔函数，对数深度网络能用逐层坐标下降法通过重构谱高效学习，还展示了一个子类，常数深度网络在此子类上有常数\(L^2\)逼近误差。

链接：https://arxiv.org/abs/2607.25200

机构：Princeton University（普林斯顿大学）； Stanford University（斯坦福大学）； University of California, Berkeley（加利福尼亚大学伯克利分校）

作者：Yunwei Ren, Zihao Wang, Jason D. Lee

英文摘要：Despite the empirical advantages of deep networks over shallow ones, theoretical depth separations largely concern approximation power, while algorithmic results are mostly limited to comparisons between two- and three-layer networks. In this work, we prove the first algorithmic separation between constant-depth and logarithmic-depth networks. Specifically, we identify a class of Boolean functions with hierarchically structured Fourier spectra that logarithmic-depth networks can learn efficiently using layerwise coordinate descent by reconstructing the spectra hierarchically and adaptively. We also exhibit a subclass for which every constant-depth, polynomial-width network with sufficiently regular activations and controlled spectral norms must incur constant $L^2$ approximation error under the uniform distribution over the hypercube.

AI 总结：研究长期广告自动出价问题，提出SWAG - Bid分层框架，将其分解为轮次级规划与步骤级执行，规划器用掩码轨迹模型预测市场，控制器通过PSG - AdaLN调整，实验表明该方法在滑动窗口评估下有竞争力。

链接：https://arxiv.org/abs/2607.25233

机构：Dalian University of Technology（大连理工大学）； Alibaba International Digital Commerce Group（阿里巴巴国际数字商业集团）； City University of Hong Kong（香港城市大学）

作者：Binglin Wu, Chuan Yue, Yingyi Zhang, Xianneng Li, Ruyue Deng, Weiru Zhang, Xiaoyi Zeng

英文摘要：Auto-bidding systems optimize bids to maximize value under efficiency constraints such as Cost-Per-Action (CPA). Existing methods treat each day as an independent episode. However, many advertisers produce value so sparsely that per-day efficiency ratios become statistically unreliable, undermining advertiser retention. Platforms therefore evaluate window-level efficiency over sliding windows of $W{=}7$ days, ensuring fair evaluation and long-term advertising effectiveness. This creates cross-episode coupling: each day's bidding decisions affect up to $W$ overlapping windows, so setting daily targets requires anticipating future market conditions. We propose SWAG-Bid (Sliding-Window Aware Generative Auto-Bidding), a hierarchical framework decomposing this challenge into episode-level planning and step-level execution. The planner uses a Masked Trajectory Model to forecast markets and generate candidate plans, scored across all overlapping windows by Multi-Window Model Predictive Control Sampling (MWMS) with exponential confidence decay. The controller adjusts reliance on this guidance through a state-adaptive gate, Per-Step Gated Adaptive Layer Normalization (PSG-AdaLN), complemented by Return-to-Go and Cost-to-Go channels carrying budget and constraint information. Experiments on AuctionNet-Sparse and online A/B tests on AliExpress show that SWAG-Bid achieves competitive constraint satisfaction and value acquisition under sliding-window evaluation.

AI 总结：研究针对计算增长快于高质量数据可用性的问题，提出计算-数据（CD）缩放定律框架，通过引入令牌有效性函数η拟合数据扩展策略，划分训练操作模式，指出经典计算最优分配在多数实际设置下次优。

链接：https://arxiv.org/abs/2607.25271

机构：Harvard University（哈佛大学）； MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

作者：Tian Qin, Kimia Hamidieh, David Alvarez-Melis

英文摘要：Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data. We propose Compute-Data (CD) scaling laws, a unified framework that bridges compute-optimal scaling, where data scales freely with compute, and data-optimal scaling, where the corpus is fixed while compute can grow without bound. CD scaling extends classical scaling laws by introducing a token-effectiveness function, $\eta$, which quantifies the value of a derived token-produced, for example, through multi-epoch repetition or paraphrasing-relative to a fresh token, ranging from a perfect substitute to having no value. We fit $\eta$ for two data-expansion strategies, multi-epoch repetition and paraphrasing, across model sizes from 14M to 600M parameters using the Dolma-3 corpus. We find that token effectiveness is far from constant: it depends jointly on model size, the tokens-per-parameter ratio, and the amount of derived data, and it saturates as the corpus is expanded. The functional form of $\eta$ implies diminishing returns when substituting compute for data as either model size or data availability increases. It also partitions training into three operational regimes---compute-bound, data-bound, and model-bound---and shows that classical compute-optimal allocation is suboptimal across most practically relevant settings.

AI 总结：针对实际运行中风信息多为稀疏离散的问题，提出织女座端到端重建框架，能将稀疏观测编织成轮毂高度风场。实验表明其可准确高效重建风场，相比克里金法误差降低约66%，支持实时风资源评估。

链接：https://arxiv.org/abs/2607.25298

作者：Zongwei Zhang, Chin Chun Ooi, Lianlei Lin, Sheng Gao, Tiantian He, Yew Soon Ong, Junkai Wang, Hangyi Yu, Jiaqi Zhang, Hanqing Zhao, Yu Zhang

英文摘要：The high proportion of wind power connected to the grid places higher demands on fine-grained knowledge of regional wind fields. Since the wind information directly obtainable in actual operations is mostly sparse, discrete, and irregularly distributed local observations, it is difficult to directly meet the needs of tasks such as wind power regulation, wind resource assessment, and low-altitude environmental perception of continuous regional wind fields. Therefore, we propose Zhinv, an end-to-end reconstruction framework that directly weaves sparse and irregular observations into a fine-grid wind field at hub-height. Experiments in Northeast China, Europe, and Southeast Asia demonstrate that Zhinv can accurately, robustly, and efficiently reconstruct fine-grid wind fields from sparse observations, reducing the error by about 66% compared with Kriging. With local wind-power observations as input, Zhinv enables wind power centers to bypass NWP and complex assimilation processes, supporting direct and real-time wind resource assessment from locally available data.

AI 总结：研究在线广告中延迟反馈下的长期转化预测问题，提出TWICE框架，将长期点击后转化率分解，利用双时钟提供互补监督训练模型，实验证明该方法有效，提升了快手广告系统的相关指标。

链接：https://arxiv.org/abs/2607.25404

机构：Kuaishou Technology（快手科技）

作者：Kaiyuan Li, Kun Wang, Zhongbo Wang, Teng Sha, Ming Yan, Yanhua Cheng, Xialong Liu

英文摘要：Long-horizon conversion prediction under delayed feedback creates a two-clock, two-window learning problem in online advertising. A short base observation window releases recent clicks on the click clock before their outcomes mature, whereas conversions continue to arrive on the conversion clock throughout a longer target conversion window. The click clock provides timely but partially observed status supervision. The conversion clock reveals long-tail delays, but the delay composition within an arrival-time slice is weighted by historical click cohorts with different traffic volumes and target-window conversion rates. We present TWICE, a framework that factorizes long-horizon post-click conversion rate (CVR) into a target-window conversion probability and a grouped elapsed-delay cumulative distribution function (CDF). The two clocks provide complementary supervision. Click-clock records train the target-window CVR head through a current-status likelihood over the base observation window. Newly arrived conversions train the delay model on the conversion clock. To account for the cohort mixture, TWICE uses fixed click-time predicted CVR (pCVR) mass as cohort exposure in an arrival-conditioned likelihood. This accounts for differences in cohort traffic and conversion propensity. The resulting aggregate records are self-contained. A single learned CDF produces monotone predictions for all requested horizons up to the target conversion window. Serving requires neither historical lookup nor convolution. Experiments on a public benchmark and an industrial advertising dataset demonstrate the effectiveness of TWICE. In an online A/B test in Kwai's advertising system, TWICE increased expected revenue, revenue, and conversions by 2.486%, 1.858%, and 2.061%, respectively. It was subsequently deployed to full traffic.

AI 总结：针对B2B电子商务交易倾向预测难题，提出基于DiCE合成数据生成及PyPARC框架的倾向建模框架，通过生成高质量少数类样本和校准倾向概率，提升预测精度，助力高精度营销活动。

链接：https://arxiv.org/abs/2607.25413

作者：Shivani, Subhayan Roy

英文摘要：Transaction propensity prediction in B2B e commerce presents unique challenges distinct from B2C contexts, primarily due to the heterogeneous procurement behaviors of organizational entities, which violate SMOTE's implicit assumption of within class feature homogeneity. Specifically, B2B buyers exhibit multi modal procurement cycles that render linear interpolation between minority class samples structurally invalid, producing synthetic data that does not represent real purchasing behavior. This paper introduces a production deployed propensity modeling framework designed to address these complexities through two primary contributions. First, we replace conventional SMOTE based augmentation with a synthetic data generation approach leveraging Diverse Counterfactual Explanations (DiCE). This method produces minority class samples with superior distributional fidelity compared to SMOTE, as validated through quantitative proximity analysis and UMAP cluster visualization. Second, we adapt the PyPARC piecewise affine classification framework to generate calibrated propensity probabilities, facilitating the interpretable segmentation of customers into actionable risk tiers. Evaluated on two years of longitudinal data from a large scale B2B e commerce platform with a 1 to 9 class imbalance ratio, the proposed architecture achieves 93.1% precision at a decision threshold of 0.8, a 9.2 percentage point improvement over SMOTE based baselines at the same threshold (83.9%), and a 26.1 point improvement over SMOTE at threshold 0.7 (66.04%), demonstrating consistent superiority across operating points. These results demonstrate the framework's efficacy in enabling high precision marketing campaigns with significant improvements in customer activation and return on investment.

AI 总结：研究语言模型量化中逐字提取情况，用Pythia模型及公共序列集，在多精度级别和模型大小下跟踪，发现量化是有选择性的遗忘器，但不足以成隐私保护手段，得出压缩非去记忆训练数据方法，从业者应关注提取的结论。

链接：https://arxiv.org/abs/2607.25451

作者：Akshay Sasi

英文摘要：Language models are almost always quantized before they are deployed, and a growing line of work asks whether quantization also lowers their privacy risk. That work measures privacy almost entirely with membership inference. We think this is the wrong thing to measure for the risk that most people actually worry about, namely a model reproducing its training data word for word, and we measure that directly. Using the Pythia models and the public set of sequences each of them is known to have memorized, we track verbatim extraction across five precision levels, from full precision down to four bits, and across three model sizes, while measuring general capability (perplexity) at every point. We find two things. Quantization is a selective forgetter: verbatim memorization falls off faster than capability at every precision and every model size we tried, and this holds under two unrelated quantization algorithms and two evaluation corpora. But the selectivity is not enough to make quantization a privacy defense, which cuts against the optimistic reading of earlier membership-inference results. At the largest model we study, four-bit quantization still reproduces most of the memorized sequences while giving up only a few percent of capability, and the fraction of memorized data that survives quantization grows with model size. We conclude that compression should not be treated as a way to remove memorized training data, and that extraction, not membership inference, is the number practitioners should be watching. All code, sampled evaluation data, and per-configuration results are released.

AI 总结：研究针对神经网络后门的训练阶段防御，将其转化为核心集选择问题，提出用累积熵作选择标准，在各 epoch 去除所选样本，构建良性核心集训练无后门模型，有效减轻后门攻击且对自然性能影响小。

链接：https://arxiv.org/abs/2607.25502

作者：Qi Zhao, Christian Wressnegger

英文摘要：Recent training-time defenses against neural backdoors isolate a benign subset from poisoned training data, to learn a backdoor-free model from it. In this paper, we formulate this defense strategy as a coreset selection problem, giving rise to so-called "Anti-Backdoor Coreset Selection." Since poisonous samples have (a) lower prediction uncertainty and are (b) less frequent than benign samples, coreset selection naturally focuses more on samples associated with benign functionality than the backdoor functionality. We use the Cumulative Entropy as selection criterion to further facilitate this effect. The metric tracks the learning dynamics of training samples and allowing us to select benign samples with high informativeness for the coreset. Additionally, we unlearn the chosen samples in each epoch to facilitate the separability between benign and poisonous samples. Together, this yields an exceptionally effective training-time defense that constructs a benign coreset to train a backdoor-free model. Unlike prior defenses that compromise natural accuracy and fail against certain attacks, our method mitigates backdooring attacks consistently with a negligible impact on natural performance.

AI 总结：针对群体学习中因特征异质性导致的问题，提出用随机森林解决，给出确定性和概率性推理时策略，在九个数据集上评估，结果显示该方法在多种场景下优于交集基线和本地训练模型。

链接：https://arxiv.org/abs/2607.25538

机构：Institute of Medical Informatics, University of Münster（明斯特大学医学信息学研究所）

作者：Mohammad Tajabadi, Dominik Heider

英文摘要：Swarm Learning is a decentralized collaborative learning mechanism that allows multiple organizations to train a shared model without central coordination or direct data sharing. In typical horizontal Swarm Learning, datasets across sites are usually assumed to share the same feature set. However, in real-world applications, sites often have partially overlapping features because measurements, protocols, and available covariates differ across sites. This feature heterogeneity creates a practical issue for machine learning algorithms such as Random Forests. Specifically, when decision trees are pooled into a global Random Forest, inference at a given site can become ill-defined if a traversal encounters a split on a feature that is not available locally, often forcing organizations to discard site-specific variables upfront. In this paper, we address feature heterogeneity in Swarm Learning with Random Forests under partially overlapping feature spaces. We propose several deterministic and probabilistic inference-time strategies that resolve such missing splits without restricting training to the intersection of features. We evaluate the methods on nine datasets and demonstrate that they outperform both the intersection baseline and locally trained models across a broad range of scenarios.

AI 总结：研究针对大语言模型应用于特定领域产生的对齐代价问题，提出MemSFT方法，通过参数内存解耦领域专业化与主干参数更新，经多领域多模型评估，能提升领域性能且通用性能下降小，实现通用与专业能力解耦。

链接：https://arxiv.org/abs/2607.25614

机构：Shanghai AI Laboratory（上海人工智能实验室）； Tsinghua University（清华大学）

作者：Jiarui Wang, Xiang Shi, Jiaqi Cao, Rubin Wei, Xiquan Wang, Hao Sun, Jingzhi Wang, Zhiqi Yang, Qipeng Guo, Bowen Zhou, Zhouhan Lin

英文摘要：Adapting Large Language Models (LLMs) to specialized domains often incurs an alignment tax, as fine-tuning on domain-specific tasks can cause catastrophic forgetting and substantially degrade performance on general tasks. We propose MemSFT, which mitigates the alignment tax by decoupling domain specialization from backbone parameter updates through a plug-and-play parametric memory. The memory is trained to imitate the behavior of a non-parametric retriever operating over domain data, thereby memorizing knowledge and patterns that would otherwise be accessed through retrieval. Once trained on a specific domain, the memory can be reused across LLMs of different sizes. During generation, a learned router dynamically fuses the output distributions of the memory and backbone at each decoding step, allowing domain expertise to be invoked selectively. Across biology, geoscience, and law, evaluations with models ranging from Qwen3-8B to Qwen3-235B-A22B show that MemSFT consistently improves domain performance with negligible degradation in general performance, whereas full SFT suffers severe forgetting on general tasks. Overall, our results demonstrate a practical path to decoupling general model capabilities from domain-specific knowledge at the parameter level, thereby equipping LLMs with new specialized capabilities without compromising their general capabilities.

AI 总结：研究针对近红外化学计量学中CNN架构设计问题，通过计算光谱数据集属性描述符，利用贝叶斯超参数优化优化两个一维CNN支架，得出光谱描述符可提供设计先验，引导浅层模型至合理超参区域，且相关启发式方法与HPO有竞争力。

链接：https://arxiv.org/abs/2607.25636

机构：Faculdade de Ciências e Tecnologia da Universidade do Algarve（阿尔加维大学科学与技术学院）

作者：Dário Passos

英文摘要： Convolutional neural networks (CNN) for near-infrared (NIR) chemometrics are often designed using generic architectural rules, although spectral datasets differ in sampling, smoothness, redundancy, and sample size. We tested whether these properties can provide empirical priors for CNN design. Across 25 NIR regression tasks, we computed descriptors of dataset size, spectral length and spacing, entropy, intrinsic rank, autocorrelation, and wavelet-scale structure. Two interpretable 1D-CNN scaffolds (a minimal single-convolution model and an extended shallow model with optional branching, dilation, etc) were optimized using five-fold cross-validated Bayesian hyperparameter optimization (HPO). Relationships extracted from near-optimal trials were converted into warm-start heuristics and evaluated directly and through leave-one-dataset-out (LODO) validation. The clearest relationships involved convolutional receptive fields. In the minimal CNN, the preferred kernel fraction decreased with spectral entropy and intrinsic rank, increased with the wavelet energy-support fraction, and the learning rate tended to decrease with training-set size. Direct and LODO heuristics were competitive with HPO, with median test-RMSE ratios of 0.953 and 1.017, respectively. The extended CNN showed similar but less transferable structure across branch usage, dilation, dropout, filter counts, and receptive-field choices. Ten stochastic refits showed seed sensitivity comparable to that of HPO-selected configurations. In a separate experiment, joint preprocessing and CNN HPO outperformed standardized-spectra HPO in 19 of 25 tasks, although gains were dataset-dependent. These results show that spectral descriptors can provide practical CNN design priors, guiding shallow NIR models toward plausible hyperparameter regions before target-specific tuning

AI 总结：研究针对机器学习需求预测运营波动性大的问题，提出上下文反卷积（CD）方法，通过核调制算子分离冲击与基线、分层部分池化实现目录规模部署，经样本外评估，CD在降低成本和提高预测可靠性上有贡献。

链接：https://arxiv.org/abs/2607.25664

机构：Amirkabir University of Technology（伊朗德黑兰阿米尔卡比尔理工大学）

作者：Mohammad Forouhesh

英文摘要：Machine learning demand forecasts optimize statistical accuracy yet leave excess operational volatility that inflates safety stock and amplifies the Bullwhip effect. We introduce \textbf{Contextual Deconvolution} (CD), a two-stage estimator that reframes demand sensing as a convex decomposition: a kernel-modulated banded operator separates transient promotion-driven shocks from a smooth structural baseline, and hierarchical partial pooling enables catalog-scale deployment without per-SKU training. The operator is data-derived, not imposed---it reduces to the identity wherever the promotional response is impulsive (most of M5, all of Favorita) and contributes only where genuine multi-day carryover exists, so the gains rest on the structural decomposition itself. Evaluating strictly out-of-sample on 30,490 M5 SKUs and 2,845 Favorita items, with calendar-aware baselines given CD's identical future calendar, we anchor the contribution on a full inventory-cost accounting: CD lowers safety stock, holding cost, and order variance but under-provisions event spikes, reducing total cost only when holding costs exceed $\sim$20\% of stockout costs (95\% CI $[17\%,25\%]$); otherwise it is an operational-stability and inventory-capital layer, not an expected-cost minimizer. Its accuracy contribution is reliability rather than central tendency: across eleven baselines, CD attains the lowest cross-sectional dispersion of per-SKU error and mis-forecasts by more than 200\% on 0.8\% of SKUs versus 9.9--20.6\% for every baseline, ranking first on both in all four M5 draws. Because the Variance Ratio and std-based safety stock are minimized by any sufficiently smooth forecast, we treat them as diagnostics, not objectives. A supporting analysis shows the learned demand operators are non-normal, yet CD's compact parametric kernel matches their operational performance interpretably.

AI 总结：研究针对心理健康评估中通用融合模型忽略问卷标签心理测量结构的问题，提出DynaBridge框架，通过编码多模态线索并结合语义摘要进行评估，在官方验证分割上优于基线和其他方法，展现了多模态融合与心理测量结构结合的价值。

链接：https://arxiv.org/abs/2607.25679

作者：Shiyu Teng, Haichen Yu, Jiaqing Liu, Hao Sun, Yu Song, Shurong Chai, Ruibo Hou, Lanfen Lin, Yen-Wei Chen

英文摘要：Multimodal behavioral analysis offers a scalable approach to assessing depression, anxiety, and stress, yet generic fusion models often ignore the psychometric structure of questionnaire labels. In DASS-21, risk labels are derived from ordered symptom items through fixed item-to-subscale mappings. We propose \textbf{DynaBridge}, a dynamic summary-guided cross-task multimodal framework for DASS-structured mental health assessment. DynaBridge encodes acoustic, visual, and textual cues across multiple sessions and augments them with frozen-LLM-generated DASS-aware summaries as participant-level semantic evidence. It predicts ordinal item distributions, reconstructs depression, anxiety, and stress risk evidence from item-level soft scores, and fuses this evidence with direct multimodal risk predictions. A confidence-aware refinement strategy further incorporates high-confidence semantic cues conservatively. On the official AdoDAS validation split, DynaBridge outperforms the official baseline and representative multimodal methods, achieving 0.5012 mean F1 for D/A/S risk prediction and 0.3216 mean QWK for DASS-21 item prediction. These results show the value of bridging multimodal cues, semantic summaries, and DASS-21 psychometric structure.

AI 总结：提出罗生门对齐（RA）评估模型功能相似性，引入几何视角，提出几何RA，通过90多个数据集实验分析，表明几何与分布对齐提供不同互补视角，RA可用于模型选择等多用途。

链接：https://arxiv.org/abs/2607.25680

机构：Faculty of Engineering, University of Porto（波尔图大学工程学院）； Artificial Intelligence and Computer Science Lab (LIACC)（人工智能与计算机科学实验室（LIACC））； Fraunhofer AICOS Portugal（弗劳恩霍夫葡萄牙人工智能与计算机科学中心）； BrightFactory（光明工厂）； LIACS, Leiden University（莱顿大学LIACS）； School of Computing and Mathematical Sciences, University of Waikato（怀卡托大学计算与数学科学学院）

作者：Moisés Santos, Peter van der Putten, Bernhard Pfahringer, Carlos Soares

英文摘要：We propose Rashomon Alignment (RA), a new measure to assess functional similarity between two models. Existing functional similarity measures are distributional, quantifying differences between outputs of models applied to real-world data. However, these measures can be regarded as ecologically valid only for regions in the input space represented by the available data. We introduce a geometrical perspective on functional model similarity, which estimates it across the entire data space, offering a comprehensive view of decision boundary alignment independent of any specific data distribution. We also propose geometric Rashomon Alignment as a measure of geometrical similarity, which is computed using data uniformly sampled from the instance space. We perform an experimental analysis on more than 90 datasets, examining critical cases where model alignment diverges from predictive accuracy. Our results show that geometrical and distributional alignment provide different and complementary perspectives on the similarity between models and algorithms. RA can be used for multiple purposes, including model selection, ensemble construction, and enhanced interpretability of machine learning models and algorithms.

AI 总结：针对城市空气质量重建难题，应用深度学习技术，从四种关键污染物的稀疏观测出发，引入基于扩散的生成框架并对比确定性模型，通过数据增强实现泛化，凸显机器学习模型在空气污染重建中可靠实际部署的潜力。

链接：https://arxiv.org/abs/2607.25687

作者：Abhishek A.Sabnis, Mihai Mitrea, Lya Lugon, Karine Sartelet, Marc Bocquet, Xiaoyuan Cheng, Shupeng Zhu, Sibo Cheng

英文摘要：Full-field reconstruction of air pollution is essential for evaluating pollution exposure and supporting public health decision-making. However, the complex interactions among pollutants, hard-to-predict weather patterns, and limited monitoring station coverage make this a complex task. We apply deep learning techniques to provide fast and accurate reconstructions from sparse observations of four key pollutants: NO2, O3, PM2.5 and PM10. Models are trained on full-field simulation data and evaluated on real-world observations collected from 9 to 28 monitoring stations in the city of Paris. We introduce a diffusion-based generative framework for multi-pollutant reconstruction and benchmark its performance against deterministic deep learning models. Despite noisy observations and strong spatial variability, the models achieve high structural similarity on simulated validation data and produce realistic spatial patterns on real-world observations, as indicated by power-spectrum analysis. We introduce data augmentation methods that enable transfer to real-world observations without retraining, allowing the models to generalise beyond the training period. These findings highlight the potential of ML models for reliable real-world deployment in air pollution reconstruction tasks.

AI 总结：研究LLM智能体的工具检索问题，提出HYSET方法，将其表述为查询条件超边预测，通过特定基数交互捕捉工具兼容性，设计为预选择模块，实验证明该方法在工具检索性能及任务成功率上优于基线，还支持零样本/少样本迁移。

链接：https://arxiv.org/abs/2607.25718

作者：Xinyi Hong, Pinjun Dong, Xinyang Yu, Binyan Jiang

英文摘要：Large language model (LLM) agents increasingly rely on invoking external tools to complete real-world tasks. Tool retrieval, which selects a small task-relevant subset from a library of thousands of tools before the agent acts, has therefore become a critical component of LLM agent pipelines. However, existing retrievers either score each tool in isolation or assemble the tool set sequentially, so the joint utility of a candidate set is never evaluated as a whole. In this paper, we propose HYSET, short for HYperedge-based SEt-level Tool retrieval. Our contributions are threefold: (i) we formulate tool retrieval as query-conditioned hyperedge prediction on a tool co-invocation hypergraph, under which the tool set itself becomes the unit of scoring and most existing retrieval paradigms reduce to restricted instances; (ii) we capture size-dependent tool compatibility through cardinality-specific interactions; and (iii) we design HYSET as a pre-selection module requiring no modification to the downstream agent. Experiments on ToolBench demonstrate that HYSET consistently outperforms state-of-the-art baselines in both tool retrieval performance and end-to-end task success. Beyond the in-domain setting, HYSET further supports zero-shot/few-shot transfer, generalizing to held-out tools/categories and unseen domains with minimal supervision.

AI 总结：研究针对精确等变架构复用复杂的问题，提出生成器对齐表示接口GARI，通过特定原则和残差形式化行为，实例化为GARI-Net，经实验验证其能支持变换一致性和泛化，为硬等变架构提供可移植诊断补充。

链接：https://arxiv.org/abs/2607.25988

机构：Tongji University（同济大学）

作者：Weitao Li, Gong Cheng

英文摘要：Exact-equivariant architectures typically encode prescribed group actions in specialized operators, which can complicate their reuse with generic backbones and across data modalities. We introduce the Generator-Aligned Representation Interface (GARI), a representation-level design principle that exposes selected transformation generators to a generic sequence backbone through aligned canonical and generator-induced views. We formalize the resulting behavior using a probe-specific soft-equivariance residual defined over declared data and transformation distributions. This framework distinguishes representation consistency from task robustness and exact equivariance, and localizes residual mismatch to interface construction, shared stream processing, and terminal fusion. We instantiate the interface as GARI-Net, which constructs generator-indexed streams, converts them into a common interaction frame, processes them with shared parameters, repairs ordering-induced context mismatch, enables cross-stream information exchange, and aggregates them using inter-stream discrepancy. Direct Equivariance Error (DEE) provides a frozen-checkpoint diagnostic of the prescribed representation relation under known token or voxel actions. Experiments on genomic sequences, images, and three-dimensional point clouds examine sequence reversal, planar rotations and reflections, and controlled axial transfer. Across these settings, the same interface principle supports task-relevant transformation consistency and generalization to declared held-out probes without requiring group-specific redesign of the sequence backbone. GARI therefore provides a portable diagnostic complement to hard-equivariant architectures: it makes generator structure accessible, learnable, and measurable, while finite-probe evidence remains distinct from certification of exact equivariance over a continuous group.

AI 总结：研究如何通过锐度感知最小化（SAM）提高泛化能力，针对其“小”扰动依赖几何结构的问题，在SAM两阶段引入矩阵感知几何结构，结合逐层谱内扰动与Muon等外更新，实验表明该组合在ViT-Small/16和ResNet-50上验证准确率最佳。

链接：https://arxiv.org/abs/2607.26001

机构：University of Bath（巴斯大学）

作者：Wenzhi Zhong, Edward Milsom, Michael Murray

英文摘要：Sharpness-Aware Minimization (SAM) aims to improve generalization by encouraging insensitivity to small, worst-case parameter perturbations. However, the notion of a "small" perturbation is inherently geometry-dependent: while existing SAM variants have explored a wide range of choices, a clear perspective on which geometries are most effective in practice remains elusive. Recent work on matrix-aware optimization, particularly the Muon optimizer, suggests that respecting the matrix structure of hidden-layer weights can lead to strong empirical performance. Motivated by this, we study matrix-aware geometry in both stages of SAM: we introduce a layerwise spectral inner perturbation for matrix-valued hidden-layer parameters and combine it with either AdamW/SGDW or Muon in the outer update. Across ImageNet-1K experiments on ViT-Small/16 and ResNet-50, we find that the combination of a spectral inner step with a Muon outer step performs consistently strongly, achieving the best validation accuracy on both models among the evaluated methods.