机器学习学术速递[7.13]

AI 总结：研究大语言模型知识蒸馏有效性背后机制，提出统一方法，通过交互分解输出分数，发现共同机制是交互稀疏化，不同方法性能差异源于处理复杂交互能力，进而提出CIP损失函数，实验证明其能提升多种KD方法性能。

链接：https://arxiv.org/abs/2607.08776

作者：Qingzhuo Wang, Ruiyang Qin, Zhenxin Qin, Wen Shen, Zhihua Wei

英文摘要：Despite the success of knowledge distillation (KD) in Large Language Models (LLMs), the underlying mechanism behind its efficacy remains unclear. In this paper, we propose a unified approach to explore the common mechanism of various KD methods using interactions. Specifically, we decompose the output score of the LLM into the sum of numerous interactions. Each interaction represents a nonlinear relationship involving a set of input variables (e.g., words). Based on the decomposed interactions, we discover that the common mechanism underlying various KD methods is the sparsification of interactions, i.e., student models retain fewer interactions for inference while suppressing other interactions to zero effects. Furthermore, we discover that the performance variance across different KD methods arises from their capabilities in handling complex interactions. A KD method typically yields better performance if it enables the student model to achieve higher sparsity of complex interactions. Motivated by these insights, we propose a plug-and-play loss function called Complex Interaction Penalty (CIP) to explicitly enforce the sparsity of complex interactions during the distillation process. Extensive experiments demonstrate that integrating CIP consistently improves the performance of diverse KD methods on both in-domain and out-of-distribution benchmarks.

AI 总结：研究MoE模型推理时内存效率问题，提出StickyMoE方法，通过惩罚相邻token间专家切换，使专家表示和路由决策共同适应。实验表明该方法能大幅降低专家切换率，在质量-局部性方面优于事后微调。

链接：https://arxiv.org/abs/2607.08780

机构：BrainChip Inc.（脑芯片公司）

作者：Ali Kayyam

英文摘要：Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices. Existing remedies are either system-level (caching heuristics) or post-hoc (router fine-tuning), leaving the root cause unchanged during pretraining. We propose StickyMoE, a differentiable routing consistency loss that penalises abrupt expert switches between adjacent tokens, encouraging the router to maintain the same expert assignment across semantically coherent spans. StickyMoE requires no architectural changes, adds a single hyperparameter lambda, and unlike post-hoc methods, allows expert representations and routing decisions to co-adapt from the first training step. Experiments on small-scale MoE language models show that StickyMoE reduces the expert switch rate by up to 60% with less than 4% perplexity degradation, Pareto-dominating post-hoc fine-tuning on the quality-locality frontier. Routing temporal locality is most efficiently instilled at training time.

AI 总结：研究针对混合专家模型服务中专家放置问题，提出Director系统，通过预测驱动的在线专家放置、轻量级预测器或量化副本及在线迁移模块，结合多项式时间运行的优化器，有效降低端到端延迟，实验证明其对流行MoE模型延迟降低显著。

链接：https://arxiv.org/abs/2607.08782

作者：Qianli Liu, Kaibin Guo, Zicong Hong, Peng Li, Fahao Chen, Haodong Wang, Jian Lin, Song Guo

英文摘要： Expert parallelism has become the prevailing paradigm to serve Mixture-of-Experts (MoE) models. Its efficiency depends on the communication and computation latencies of the GPUs, which are linked to the placement of experts in the GPUs. Existing works for optimizing expert placement focus on leveraging past requests' expert activation patterns. However, they demonstrate deficiencies facing diverse and rapidly changing request patterns, calling for an online, proactive approach. Implementing such an approach requires addressing several challenges: the uncertainty associated with incoming requests' expert activation, the cost of expert migration, and the NP-hard complexity in optimization. Therefore, we present Director, a new distributed MoE serving system that minimizes end-to-end latency via prediction-driven, online expert placement. Director uses either a lightweight cascaded predictor or a low-bit quantized replica for expert activation patterns of incoming requests. An online migration module then enacts the changes with near-zero downtime by executing migrations in compute-bound phases, keeping disruption bounded. At its core, a relaxation-based expert placement optimizer operates under capacity constraints, runs in polynomial time, and achieves a $(1+\epsilon)$ approximation ratio. Finally, we implement a prototype and demonstrate, through extensive experiments, a reduction in end-to-end latency of $11\sim55\%$ for popular MoE models (e.g., Mistral, DeepSeek and Qwen) compared to existing work.

AI 总结：针对流形值测量在机器学习任务中的问题，提出LieBN框架用于李群上的黎曼批量归一化，利用左右不变度量，在多种几何结构上实例化并经实验验证有效。

链接：https://arxiv.org/abs/2607.08783

机构：Department of Information Engineering and Computer Science, University of Trento（信息工程与计算机科学系，特伦托大学）； Computing and Mathematical Sciences, Caltech（计算与数学科学系，加州理工学院）； School of Artificial Intelligence and Computer Science, Jiangnan University（人工智能与计算机科学学院，江南大学）

作者：Ziheng Chen, Yue Song, Rui Wang, Xiao-Jun Wu, Nicu Sebe

英文摘要：Manifold-valued measurements are prevalent in various machine learning tasks. Recent advances have extended Deep Neural Networks (DNNs) to operate on manifolds, accompanied by normalization techniques tailored to different geometries, collectively referred to as Riemannian normalization. However, most existing Riemannian normalization methods are either designed for specific manifolds or fail to effectively normalize manifold-valued sample distributions. To address these limitations, we propose LieBN, a framework for Riemannian Batch Normalization (RBN) over Lie groups. Our approach leverages the theoretically convenient left- and right-invariant metrics, which naturally exist in every Lie group, and provides theoretical guarantees for controlling the Riemannian mean and variance. We instantiate LieBN across nine distinct geometries: four on the Symmetric Positive Definite (SPD) manifold, one on the group of rotation matrices, and four on the manifold of full-rank correlation matrices. Notably, among the SPD metrics, we introduce a novel right-invariant metric and extend three existing Lie group structures via matrix power deformation. Extensive experiments on different manifolds validate the effectiveness of our framework. The code is available at this https URL.

AI 总结：研究针对时间序列推理中不同模型能力互补及特性差异问题，提出基于图的TSRouter动态路由框架，通过构建异构图并将路由设为候选评分问题来选择最优模态-模型对，在多任务评估中性能显著提升，还具备零样本泛化等优势。

链接：https://arxiv.org/abs/2607.08940

机构：University of Maryland, College Park（马里兰大学帕克分校）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）； MBZUAI（Mohamed Bin Zayed University of Artificial Intelligence）

作者：Fangxu Yu, Tao Feng, Dehai Min, Lu Cheng, Ge Liu, Tianyi Zhou

英文摘要：Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, their capabilities are complementary: LLMs process time series as text sequences and thus preserve exact numerical understanding, but struggle with global patterns, whereas VLMs efficiently capture these patterns by visualizing time series but may lose fine-grained details. Moreover, models vary significantly in task-specific expertise and inference costs. Dynamically selecting the most suitable modality and model for each query is therefore crucial, yet challenging because it requires modeling the complex interactions among tasks, queries, modalities, and models, which carry rich contextual signals. To this end, we introduce TSRouter, a graph-based dynamic routing framework. TSRouter constructs a heterogeneous graph of task, query, modality, and model nodes to contextualize the interactions among query characteristics, modality attributes, and model capabilities. TSRouter formulates routing as a candidate scoring problem, where each modality-model pair is evaluated based on user-defined performance-cost preferences to select the optimal candidate. Comprehensive evaluations on 4 distinct time series reasoning tasks reveal that TSRouter substantially outperforms diverse baselines with 16\% to 46\% relative improvements. Furthermore, TSRouter demonstrates robust zero-shot plug-and-play generalization to unseen models and novel tasks and preserves high performance while reducing computational overhead through cost-aware optimization. Our code is available at this https URL.

AI 总结：研究如何让Transformer清晰可读，提出用通道方差下限等方法，构建出最清晰可读的Transformer，使单元能分离检测与命名，编辑更局部，还揭示清晰度调节旋钮，质量与传统基线相当。

链接：https://arxiv.org/abs/2607.08946

机构：University of Washington（华盛顿大学）； School of Computer Science and Engineering（计算机科学与工程学院）

作者：Mark Oskin

英文摘要： A transformer can be built from operators that are legible by construction -- bounded, named units that read as fuzzy set operations rather than dense activations -- but legibility must be pressed for during training, and the pressure has a failure mode. A crispness penalty meant to sharpen a bounded operator into a decisive detector instead collapses it into a dead constant. An identity, E[v(1-v)] = mu(1-mu) - var, shows why -- the penalty is a variance-minimizer blind to the difference between a live detector and a constant -- and names the fix: a per-channel variance floor, the target legibility metric written as a loss, which recovers both legibility and quality. A learned per-unit fraction then retires the hand-set reserved-GELU partition of prior work: given the choice the model keeps no unit as pure GELU and routes 87% of its load-bearing computation through crisp operators. The result is the most legible transformer we have built -- 78% of its feed-forward operands and 50% of its attention value channels are crisp-and-contextual detectors, and per-head legibility rises from 18% in shallow layers to 78% in deep ones. Read in the correct rotated per-layer frame, these units separate a clean detection (what a unit responds to) from a harder naming (what its output decodes to); and because the objective makes each unit crisp and sparse, edits to them are far more local -- 50-184x in the deep layers where the edit sites concentrate -- and can target explicit conjunctions a single neuron cannot express. Finally, a between-unit decorrelation pressure exposes a legibility dial: it trades a circuit's reuse for independence at no quality cost, turning concepts into single, surgically editable units and a prediction into a short explanation read off a handful of named operations. Quality holds at parity with a conventional baseline throughout.

AI 总结：针对空间转录组学基因表达预测受成本和通量限制的问题，提出COAST框架，通过特定调制调节上下文特征，用Transformer编码器聚合斑点令牌，结合绝对与差分回归训练，实验证明该方法在多数据集上能有效提升预测效果。

链接：https://arxiv.org/abs/2607.09166

机构：School of Electrical Engineering, Korea University（韩国大学电气工程学院）

作者：Keunho Byeon, Sunhong Park, Jeewoo Lim, Jin Tae Kwak

英文摘要：Spatial transcriptomics enables profiling of spatial gene expression but is limited by high cost and low throughput, motivating prediction from H&E histopathology images. Existing context-aware methods mainly supervise absolute expression, while relative expression relationships between spots are rarely used explicitly. We propose COAST, a context-aware differential learning framework for spatial gene expression prediction. COAST conditions the local and global context features with type-specific modulation and aggregates the target and context spot tokens using a Transformer encoder to capture both fine-grained local patterns and slide-level structure. It is trained with a joint objective that combines absolute expression regression with signed differential regression between the target and context spots. Experiments on multiple spatial transcriptomics datasets show consistent improvements in correlation- and distribution-based metrics, demonstrating the effectiveness of context-aware differential learning for histology-based spatial gene expression prediction.

AI 总结：研究针对AI/ML中深度神经架构缺乏可解释性的问题，提出SAMPAT架构，它能学习连续可微函数且近似任意平滑函数，有完全可解释性，实验显示其性能良好，并可用于多种函数表示及优化模型类别选择。

链接：https://arxiv.org/abs/2607.09235

机构：Indian Institute of Technology, Delhi（印度理工学院德里分校）

作者：Jayadeva, Madhur Aswani

英文摘要：The current state of the art in AI/ML rests on deep neural architectures, which, in general, suffer from a lack of interpretability. Interpretability is crucial to gleaning insights while analyzing experimental data, where quantitative predictions may not be adequate for a scientist. We present a three layer neural architecture, SAMPAT (Smooth Approximation via Multivariate Polynomials and Analytic Transformations), that can provably learn a continuous, everywhere differentiable function, that can approximate any smooth function arbitrarily closely. SAMPAT's approximant can be expressed as a closed and compact algebraic, analytic expression, providing complete interpretability. Experiments on synthetic and benchmark datasets indicate that SAMPAT yields competitive performance with simpler representations. For many tasks, a two layer SAMPAT suffices. By imposing restrictions on the connectivity between neurons, SAMPAT may be used to provide a range of approximants, including regular and trigonometric polynomials, rational expressions, Gaussians, mixtures of Gaussians, as well as arbitrary combinations of the same; without restrictions, it learns a suitable structure. SAMPAT may be used to factorize polynomials and model nonlinear systems. With the addition of skip connections, a 4 to 6 layer SAMPAT is adequate to represent a substantive range of methods widely used in AI/ML, allowing the choice of a model's family, not just its parameters, to also be optimized as part of the learning process.

AI 总结：研究针对Lion在不同层参数有效规模差异问题，提出LionVote逐层学习率机制，通过特定诊断更新参数张量的复合水平，投票阈值源于多种因素，节奏有界且可选择。该机制在ViT-Tiny/CIFAR-100上提升了准确率，且适应值与架构、任务相关。

链接：https://arxiv.org/abs/2607.09266

机构：New York University（纽约大学）

作者：Kris Atallah (New York University, New York, USA)

英文摘要：Per-layer diagnostics reveal that, at the prescribed learning rate, Lion's effective scale is 2.6-2.8x too high for attention and MLP parameters and ~2x too high for normalization layers on ViT-Tiny/CIFAR-100; this 32% cross-layer-type disparity cannot be reproduced by a single global rate. The measurement comes from LionVote, a per-layer learning rate mechanism in which each parameter tensor maintains a compound level, a persistent integer updated every c epochs by two diagnostics (gradient direction stability and momentum health) resolved by a validation loss tiebreaker. Voting thresholds derive from geometric identities, the EMA time constant, and a noise-floor estimate; cadence is bounded structurally and selected by ablation. On ViT-Tiny/CIFAR-100, LionVote achieves 69.7% top-1 accuracy vs. Lion's 69.0% (p < 0.02, Welch's t-test) and AdamW's 68.8%. Per-layer adaptation value depends on both architectural heterogeneity and task; on uniform CNN architectures tuned SGD with cosine annealing remains dominant, and on ViT architectures gains are task-dependent.

AI 总结：马赫思维-4-闪是含3B激活参数的35B参数专家混合智能体模型，通过训练后优化及可扩展交互环境提升性能。其流程含三个阶段，在多个基准测试中成绩优异，以低推理成本领先或匹配数倍激活规模模型。

链接：https://arxiv.org/abs/2607.09375

机构：Li Auto Inc（理想汽车公司）

作者：Foundation Model Team (Li Auto Inc)

英文摘要：We present Mach-Mind-4-Flash, a 35B-parameter Mixture-of-Experts (MoE) agentic model with 3B activated parameters. Through post-training optimization alone without scaling pre-training compute, the model achieves performance on par with or surpassing that of 100B-parameter-class models. By introducing scalable agentic interaction environments for large-scale reinforcement learning, the model attains significant performance gains on real-world application tasks. Our pipeline comprises three stages: (1) a unified RL/OPD training infrastructure with dynamic multi-teacher scheduling and operator-level acceleration, delivering 17\% end-to-end training speedup; (2) multiple domain-specific RL experts trained in parallel across Reasoning, General, and Agent tracks, then fused into a single generalist via Multi-Teacher On-Policy Distillation (MOPD) -- a routed reverse-KL objective that eliminates the see-saw degradation of mixed-reward RL; (3) Hybrid Median-length Policy Optimization (HMPO), a single-stage token-efficiency method that compresses reasoning chains by 19--46\% with $\le$0.7 percentage-point accuracy loss. Mach-Mind-4-Flash scores 92.70 on AIME'26, 82.82 on IFBench, 80.74 on Behavioral-SafetyBench, 75.80 on BFCL-v4, 72.31 on BrowseComp-zh, and 84.20 on ClawBench -- leading or matching models with 10--30$\times$ its activated size at a fraction of the inference cost.

AI 总结：该研究提出新方法优化深度可微逻辑门网络和查找表网络连接，利用概率分布选最优连接，并行学习门类型等。在多个基准测试中表现优于固定连接网络，减少门数量，确保多层训练稳定，还提出LUT神经元描述，提升模型性能。

链接：https://arxiv.org/abs/2607.09399

机构：imec

作者：Wout Mommen, Lars Keuninckx, Matthias Hartmann, Werner Van Leekwijck, Piet Wambacq

英文摘要：We introduce a novel method for both partial and full optimization of the connections in deep differentiable logic gate networks (LGNs) and lookup table networks (LUTNs). Our training method utilizes a probability distribution over a set of connections per gate/lookup table (LUT) input pin, selecting the connection with highest merit, all whilst the optimal gate types or LUT-entries are learned in parallel. We show that the connection-optimized LGNs outperform standard fixed-connection LGNs on the Yin-Yang, MNIST Handwritten Digits and Fashion-MNIST benchmarks, while requiring only a fraction of the number of logic gates. We achieve 98.92% on the MNIST dataset with two layers of 8000 gates. With only one layer of 8000 gates, we obtain 98.45%, showing that our method requires almost 50 times fewer gates compared to fixed-connection LGNs. Training stability up to ten layers has been ensured by employing a high learning rate, straight-through estimators and trimming constant-output gate types. Additionally, we present a LUT neuron description that enables stable training with backpropagation, tested up to 6-layer deep networks. The model requires four times fewer trainable parameters and still achieves a higher accuracy compared to the fixed-connection LGN training algorithm. Our connection-training algorithm also works well for the LUTNs, achieving an accuracy of 98.88% for two layers of 2000 6-input LUTs.

AI 总结：针对时间序列预测中多样动态难以用单一机制处理的问题，提出门控线性框架，通过三种专门机制及三因式融合门实现互补线性基的自适应路由，实验显示其在精度、可解释性和参数规模上表现出色。

链接：https://arxiv.org/abs/2607.09537

机构：Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）

作者：Qitai Tan, Ruiwen Gu, Yilin Su, Mo Li, Xu Lin, Xiao-Ping Zhang

英文摘要：Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence. While recent deep learning models have improved accuracy, they typically force these diverse patterns through a single computational backbone governed by fixed algorithmic inductive biases (e.g., self-attention or spectral filtering). This single-mechanism approach often struggles with the profound heterogeneity of real-world series, where different variables and forecast horizons necessitate fundamentally different predictive treatments. To address this, we propose GatedLinear: a lightweight framework that frames forecasting as the adaptive routing of complementary linear bases. GatedLinear leverages a pool of three specialized mechanisms: a global trend-seasonal basis for smooth projection, a difference-based incremental basis for nonstationary drift, and a phase-aligned recurrence basis for explicit cyclic reuse. To dynamically orchestrate these distinct behaviors, we introduce a Tri-Factorized Fusion Gate that disentangles routing decisions into channel-specific preferences, horizon-aware offsets, and phase-indexed biases derived from known future time marks. This design allows the model to perform highly granular, point-wise soft routing across different predictive regimes without stacking computationally heavy neural modules. Experiments on standard benchmarks show that our method achieves state-of-the-art or highly competitive accuracy against recent complex foundational models, while offering explicitly interpretable routing patterns and operating with a substantially smaller parameter footprint.

AI 总结：研究线性表示在训练中如何学习，开发框架研究训练时概念方向对齐即“抽象”过程，在最小线性网络获精确解，扩展到非线性网络分析其影响，证明衰减定律，为抽象提供动力学理论，用于改进大语言模型线性探针泛化。

链接：https://arxiv.org/abs/2607.08843

作者：William W. Yang, Andrew M. Saxe, Peter E. Latham

英文摘要：In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space. In deep learning, this idea is known as the linear representation hypothesis and underpins many interpretability and control methods based on linear probes, from concept detection to activation steering. Yet while prior work has studied whether such directions should exist $\textit{after}$ training, the dynamics of how they emerge $\textit{during}$ training remain poorly understood. Here, we develop a framework to study the alignment of concept directions during training - a process we call "abstraction". In a minimal linear network setting, we obtain exact solutions for the full trajectory of abstraction. These solutions reveal key analytic principles governing abstraction: (i) data and target geometry jointly determine abstraction at the end-of-learning, (ii) abstraction improves with network depth, and (iii) initialization scale controls the maximum abstraction reached during training. Extending our theory to nonlinear networks, we analyze how the choice of nonlinearity affects abstraction dynamics: erf networks approximate the linear theory, while abstraction in ReLU networks depends less on target geometry and more on input geometry. Across both, we prove a striking attenuation law: both nonlinearities weaken abstraction in activations relative to preactivations. We find evidence for this law in open models (DINOv3, Gemma 4) and apply our theory to improve linear probe generalization in LLMs. Together, our results provide a dynamical theory of abstraction with implications for interpretability and control.

AI 总结：研究高维数据集降维和聚类问题，核心方法是将对称纳入谱嵌入的亲和核，通过分析具有对称的黎曼数据流形，证明相关图拉普拉斯算子收敛，在特定数据集验证后表明该方法能恢复数据内在几何，优于标准谱嵌入。

链接：https://arxiv.org/abs/2607.08987

机构：Tel Aviv University（特拉维夫大学）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； KTH Royal Institute of Technology（皇家理工学院）

作者：Yeari Vigder, Paulina Hoyos, David Thong, Joakim andén, Joe Kileel, Amit Moscovich

英文摘要：Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional structures. Although many datasets of practical interest exhibit invariance under symmetries such as rotations, standard spectral embedding methods do not account for this, treating symmetry-related data points as unrelated. Our approach to this problem is to incorporate the symmetries directly into the affinity kernels used for spectral embedding. We analyze the case of a Riemannian data manifold $M$ with symmetries given by a compact Lie group~$G$ and prove that, under suitable conditions, graph Laplacians constructed from three types of invariant kernels converge pointwise to explicit second-order differential operators on the quotient space $M/G$. Our analysis implies improved convergence rates, as the effective dimension drops according to the dimension of the group. We validate our approach on datasets with $\mathrm{SO}(2)$ or $\mathrm{SO}(3)$ symmetry, and show that $G$-invariant spectral embedding recovers the intrinsic geometry of the data, in contrast to standard spectral embedding, which fails to do so even in the limit of infinite data.

AI 总结：研究对比学习中InfoNCE损失用于相似性搜索的泛化，通过加托微分引入新连续性界，量化泛化性能，证明随着k增长，InfoNCE损失中k个负样本平均效应可使泛化误差稳定。

链接：https://arxiv.org/abs/2607.09405

机构：School of Mathematics, University of Bristol（布里斯托大学数学学院）

作者：Nick Whiteley

英文摘要：Similarity search is a primary application of embedding models trained by contrastive learning. For one of the most popular contrastive learning loss functions, InfoNCE, we show that the population risk with $k$ negative samples is $O(1/k)$ close to an expected cross-entropy which quantifies deviation between i) a softmax similarity search over unseen data using the learned embedding function, and ii) an idealised softmax search over the same data but using similarity implicitly represented in the positive sample generator. This complements existing interpretations of InfoNCE in the $k\to\infty$ limit which are phrased in terms of mutual information, and alignment versus uniformity in embeddings. To quantify generalisation performance, we introduce a new continuity bound for the InfoNCE loss, obtained via Gâteaux differentiation. The bound preserves the structure of averaging over negative samples present in the loss function and features an ``inverse temperature'' parameter which can be tuned to account for the algorithmic temperature. For embedding functions which are Lipschitz in a parameter, this yields a simple demonstration that the averaging effect of $k$ negative samples in the InfoNCE loss carries over to stabilisation of the generalisation error as $k$ grows.

AI 总结：研究针对EEG解码，开发了含多尺度时间卷积输入层和Transformer编码器块的对比预训练模型CoCoT，在广泛基准解码任务中表现出色，优于单任务解码模型，证明对比学习构建EEG基础模型可行，还给出架构设计考量。

链接：https://arxiv.org/abs/2607.09543

机构： Sigma Nova Paris（巴黎西格玛诺瓦公司）； Goethe University Frankfurt（法兰克福歌德大学）

作者：Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian, Yassir Bendou, Richard Gao

英文摘要：Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications. Many recent large-scale models converged on the approach of tokenizing raw EEG followed by masked reconstruction pretraining. However, this recipe has been shown to be suboptimal for data, like EEG, with high noise amplitude and information confined to limited dimensions such as narrow frequency bands. Building on this insight, we develop a novel contrastive-pretrained EEG model with multiscale temporal convolution input layers and Transformer encoder blocks (CoCoT). CoCoT matches or beats state-of-the-art reconstruction-pretrained EEG models on extensive benchmark decoding tasks with heterogeneous electrode configurations. Furthermore, CoCoT trained from scratch outperforms previous single-task decoding models and even rivals pretrained models, showcasing the architecture's flexibility and data efficiency. Through systematic ablations, including model architecture and pretraining objective, we demonstrate the viability of contrastive learning for building EEG FMs while suggesting key architectural design considerations, prompting further investigations in alternative large-scale pretraining strategies.

AI 总结：研究针对强化学习中探索难的问题，提出提示驱动的探索策略（PDE），利用视觉-语言模型对轨迹视频推理，从弱策略轨迹中优化提示，实现后验采样，能让强化学习从零奖励起步学习成功策略并提升样本效率。

链接：https://arxiv.org/abs/2607.08837

机构：Massachusetts Institute of Technology（麻省理工学院）； MIT-IBM Computing Research Lab（麻省理工学院-IBM计算研究实验室）； Improbable AI Lab（英普罗巴布尔人工智能实验室）

作者：Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong

英文摘要：Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large language models (LLMs) and vision-language-action (VLA) models offer a pathway: they condition the policy on a natural language prompt, and since the rollout follows from it, modifying the prompt induces global changes. The challenge is finding prompts that induce useful global changes. With a weak policy that rarely succeeds, reward is too sparse to select on. Our idea is to refine prompts from the rollouts themselves: a vision-language model (VLM) reasons over the rollout video, diagnoses how the policy responded, and rewrites the prompt to elicit better behavior next time. This procedure realizes posterior sampling, a classical RL exploration framework, at the level of prompts: the VLM maintains an implicit distribution over useful prompts and updates it from observed rollouts. We call this strategy Prompt-Driven Exploration (PDE). Across manipulation and reasoning tasks, PDE enables RL to learn successful policies even from zero-reward starts, and improves sample efficiency more broadly. Our website is available at this https URL.

AI 总结：研究在物理机器人上训练强化学习智能体减少跌倒问题，提出对PPO改进的SafeExplorer算法，核心是无偏策略梯度估计器，还添加加速学习组件，实验表明该算法大幅减少训练时间跌倒且奖励表现良好。

链接：https://arxiv.org/abs/2607.08925

机构：McGill University（麦吉尔大学）； Mila（米拉）； Technical University of Munich（慕尼黑工业大学）； Université de Montréal（蒙特利尔大学）

作者：Elham Daneshmand, Majid Khadiv, Glen Berseth, Hsiu-Chin Lin

英文摘要：Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do. A standard mitigation hands control to a separate recovery policy whenever the agent leaves a designer-specified safe region (a subset of state space it should stay within), but the resulting mixed-policy rollouts silently bias every on-policy update, and the importance-sampling correction that would remove this bias is ill-defined whenever the recovery policy is deterministic. We address this bias with a drop-in modification of proximal policy optimization (PPO). Its core is an unbiased policy-gradient estimator that uses the score function only at safe timesteps and never evaluates the recovery policy's density, so it stays valid even when the recovery policy is deterministic, exactly where importance sampling breaks, and it empirically dominates importance sampling even when the recovery policy is stochastic. Because the recovery policy still makes credit assignment slow near the safe-region boundary, two further components accelerate learning: a closed-form value for recovery-triggering states when dynamics and recovery are deterministic, and an imitation loss that copies recovery actions only when recovery succeeds. On a three-environment, five-seed benchmark, the resulting algorithm reduces training-time falls by factors of 233x, 48x, and 26x on HalfCheetah, Ant, and Unitree Go1 over standard PPO, while matching or exceeding PPO's final reward, and on Ant, where the recovery policy is unreliable, it is the only method that reaches 80% of the best final reward.

AI 总结：研究具有部分观测动作的随机线性博弈问题，提出TOFU-POV算法，通过估计潜在动作子空间等操作，使遗憾为$\sqrt{T}$且与内在维度相关，还设计了秩自适应算法，实验证明该算法能改进自然基线。

链接：https://arxiv.org/abs/2607.08971

机构： Arizona State University（亚利桑那州立大学）； GE Vernova（通用电气 Vernova）； Google（谷歌）

作者：Gautam Dasarathy, Vineet Gattani, Lalit Jain

英文摘要：The stochastic linear bandit, where actions are represented as vectors and rewards are linear, is a central paradigm for sequential decision making. We study a partially observed variant of this problem in which the learning agent only sees a random subset of coordinates for each action. Such partial observability arises naturally in settings like recommendation and healthcare, where full action descriptions can be expensive or even impossible to obtain. In general, this makes sublinear regret information-theoretically impossible. However, we show that this barrier can be overcome when the action vectors have low intrinsic dimension. We propose an algorithm, TOFU-POV, that estimates the latent action subspace using the masked actions, imputes current actions using an epoch-wise frozen representation, and runs OFUL in the resulting low-dimensional coordinates. Our theory shows that TOFU-POV enjoys a $\sqrt{T}$ regret that scales with the intrinsic action subspace dimension as opposed to the ambient dimension and quantifies the interaction between these quantities and the missingness, decision set size, and subspace conditioning. We also devise a rank-adaptive algorithm that does not require the knowledge of the intrinsic dimension. We complement these guarantees with a lower bound based on a novel product construction that separates usual reward-learning uncertainty from a missingness-dependent cost intrinsic to partial observation. Synthetic and real data experiments support our theory and show that TOFU-POV can substantially improve upon natural baselines in this challenging problem.

AI 总结：研究从成对比较中进行固定置信度前\(k\)项识别的主动学习问题，刻画下界结构为鞍点问题并开发渐近最优算法，构造自适应比较分配算法并证明其渐近最优，最小化比较预期数量。

链接：https://arxiv.org/abs/2607.08979

作者：Motti Goldberger, Nils Rudi

英文摘要：We study the active learning problem of fixed-confidence top-$k$ identification from noisy pairwise comparisons. In this problem, an algorithm sequentially chooses pairs of items to compare, observes the outcomes, and stops when it can return the set of top-$k$ items with error probability at most $\delta$. The objective is to design such a $\delta$-correct procedure that minimizes the expected number of comparisons (the sample complexity). This problem falls within the broader literature on fixed-confidence pure exploration in bandit models, where a common target is asymptotic optimality: the algorithm's expected sample complexity matches the information theoretic lower bound as $\delta \to 0$. Asymptotically optimal procedures have been developed for a range of fixed-confidence pure-exploration problems, however to the best of our knowledge, for top-$1$, or more generally top-$k$ identification from pairwise comparisons under latent utility models an asymptotically optimal algorithm has not been established. In this setting, we develop such an algorithm. We characterize the structure of the lower bound and formulate it as a saddle-point problem. This structure enables a computationally efficient primal-dual procedure that learns the asymptotically optimal comparison allocation online. We then construct an adaptive comparison-allocation algorithm that tracks the allocation learned by the primal-dual procedure and prove it is asymptotically optimal.

AI 总结：研究在稀疏奖励游戏中普通AlphaZero的局限性，对比多帧变体及AZAL，发现普通AlphaZero虽表现出色但无法保持最优轨迹，AZAL能显著提高预言一致性，在啃咬和四子棋游戏中均有改进。

链接：https://arxiv.org/abs/2607.08984

机构：California Institute of Technology（加州理工学院）

作者：Brent Kong, Tejas Ram, Tony Yue Yu

英文摘要：AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervision. We find that vanilla AlphaZero achieves strong play across both domains but cannot preserve the exact trajectories required for optimal play: in Connect Four, it fails to maintain the optimal line of play, while in Chomp, it fails to consistently restore the $g=0$ invariant. On rectangular Chomp boards, multi-frame inputs alone do not remove this gap. Nevertheless, AZAL substantially improves oracle consistency across multi-seeded full-game traces and sampled-state evaluations. On Chomp, AZAL reaches perfect full-game oracle consistency on 10x11 and high but not complete consistency on 9x10; on Connect Four, AZAL improves oracle-match rate and delays the first oracle mistake, but does not reach perfect play.

AI 总结：研究用于大语言模型路由的相关感知上下文博弈问题，提出耦合奖励混合与解耦预测混合两种利用替代奖励的算法，经理论分析和实验评估，相比基线方法提高了样本效率和精度 - 成本权衡。

链接：https://arxiv.org/abs/2607.09015

机构：The Pennsylvania State University（宾夕法尼亚州立大学）

作者：Ajay Narayanan Sridhar, Ronak Singh, Mehrdad Mahdavi, Vijaykrishnan Narayanan

英文摘要： We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large language model (LLM) routing. Unlike classical contextual bandits that rely solely on bandit feedback and assume conditional independence across arms, our setting allows context-dependent inter-arm correlations and auxiliary reward information that may be noisy or misspecified. We propose algorithms that leverage such surrogate rewards through two complementary designs. A coupled reward-mixing approach pools true and surrogate rewards to accelerate learning when surrogate signals are reliable, while a decoupled prediction-mixing approach maintains separate estimators for bandit feedback and surrogate rewards and adaptively combines their predictions. This decoupling yields robustness to surrogate misspecification, recovering regret guarantees comparable to reward-only bandit methods in the worst case, while achieving improved regret when surrogate predictions are sufficiently informative. We provide theoretical regret analyses for both approaches and evaluate them on LLM routing benchmarks under varying accuracy versus cost trade-offs. The results demonstrate improved sample efficiency and consistently better accuracy-cost trade-offs compared to standard contextual bandit baselines and strong static routing methods.

AI 总结：研究针对强化学习用于视觉-语言-动作模型后期训练时样本效率低的问题，提出事后诸葛亮式学习方法，通过对失败轨迹重标记，让策略联合原始与重标记轨迹训练，在分布外任务上显著提升样本效率并优于基线。

链接：https://arxiv.org/abs/2607.09042

机构：Massachusetts Institute of Technology（麻省理工学院）； MIT-IBM Computing Research Lab（麻省理工学院-IBM计算研究实验室）； Stanford University（斯坦福大学）； University of California, San Diego（加利福尼亚大学圣地亚哥分校）

作者：Iris Xu, Sunshine Jiang, John Marangola, Nitish Dashora, Richard Li, Thomas Liu, Zexue He, Yuheng Zhi, Alex Pentland, Pulkit Agrawal, Zhang-Wei Hong

英文摘要：Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, making sample efficiency a central concern. Manipulation tasks typically provide only sparse rewards, so a weak policy fails almost every rollout early in training and has little to learn from, even when those failures execute coherent behavior. Such a failure, however, is a success at a different task. We present Learning from Hindsight (LfH), which brings hindsight relabeling to RL post-training of VLAs by scoring failed rollouts against the tasks they actually achieved. A single vision-language model relabels both the instruction and the reward, proposing a hindsight instruction for a group of failed rollouts and scoring how well each satisfies it, and the policy trains on the relabeled and original rollouts jointly. Because VLAs generalize across language, relabeling in language lets the policy learn more from the same trajectories. On out-of-distribution LIBERO-PRO tasks, where standard RL improves only slowly, LfH achieves $5\times$ improvement in sample efficiency, and outperforms a dense progress-reward baseline. The gains hold across VLA backbones and on a physical Franka robot.

AI 总结：研究风险感知通用效用马尔可夫决策过程，聚焦熵风险度量，提出基于蒙特卡洛树搜索的方法，可解决该过程并达任意精度，实验表明此方法在多种任务的GUMDPs中优化风险感知行为时成功。

链接：https://arxiv.org/abs/2607.09298

作者：Pedro P. Santos, Fábio Vital, Alberto Sardinha, Francisco S. Melo

英文摘要：We study general-utility Markov decision processes (GUMDPs) with risk-aware objectives. In this framework, an agent aims to optimize a risk measure of the distribution of objective values, where the objective function depends on the frequency of visitation of states induced by the agent's policy. First, we motivate, propose, and formalize risk-aware GUMDPs, which enable agents and decision makers to trade off expected performance by risk aversion while benefiting from the rich set of objectives that can be cast under the framework of GUMDPs. We focus our attention on the entropic risk measure (ERM). Second, we show how we can solve risk-aware GUMDPs with ERM objectives by resorting to online planning techniques. In particular, we propose an approach based on Monte Carlo Tree Search (MCTS) to provably solve risk-aware GUMDPs up to any desired accuracy. Third, we provide a set of experimental results showcasing that our approach is successful when optimizing for a spectrum of risk-aware behaviors in the context of GUMDPs under diverse tasks (standard MDPs, maximum state entropy exploration, imitation learning, and multi-objective MDPs).

AI 总结：研究针对离线强化学习中轨迹规划器的问题，提出捷径轨迹规划（STP）框架，将捷径模型作为轨迹生成器，单阶段训练条件捷径轨迹模型，支持可调推理，用增强可行性感知校正的评论家选候选计划，在多任务基准测试中性能强且简化训练管道。

链接：https://arxiv.org/abs/2607.09336

机构：The University of Tokyo（东京大学）

作者：Guanquan Wang, Yoshimasa Tsuruoka

英文摘要：Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher--student distillation pipeline that increases training cost and may introduce instability. We propose Shortcut Trajectory Planning (STP), an offline model-based reinforcement learning framework that incorporates shortcut models as efficient trajectory generators. STP trains a conditional shortcut trajectory model in a single stage, supports adjustable one-step and few-step inference through step-size conditioning, and selects candidate plans using a critic augmented with feasibility-aware correction. Across standard D4RL benchmarks, including locomotion, navigation, manipulation, and dexterous control tasks, STP achieves strong performance while simplifying the training pipeline for fast generative planning.

AI 总结： 针对量子器件调谐中参数串扰致学习不稳定问题，提出用在线学习动作空间分解表示的方法，框架QADAPT借此高效学习共享策略，实现零样本泛化及收敛步骤数恒定，为大规模量子处理器快速校准提供可扩展途径。

链接：https://arxiv.org/abs/2607.09422

机构：University of Oxford（牛津大学）

作者：Edwin De Nicolo, Rahul Marchand, Cornelius Carlsson, Pranav Vaidhyanathan, Natalia Ares

英文摘要：Cooperative multi-agent reinforcement learning is well suited to problems with large parameter spaces and exploitable local structure, such as the tuning of electrostatically-defined quantum-dot arrays. However, if parameter cross-talk is strong, a non-stationary environment from the perspective of any individual agent can destabilize learning - the same effect that plagues manual tuning of such systems. We propose using a factored representation of the action space, learned online, to decouple agents and minimize their interference. Our framework, QADAPT, uses this factorization to efficiently learn shared policies based on local measurements and rewards. With this modular strategy, we achieve zero-shot generalization to unseen quantum device sizes and maintain an approximately constant number of convergence steps to reach target regimes. This work provides a scalable route toward the rapid calibration of large-scale quantum processors.

AI 总结：针对金融异常检测的类不平衡问题，提出语义帕累托深度Q网络框架，合成交易特征，优化向量奖励，映射帕累托前沿，经实验验证可打破零召回陷阱，提升少数类召回率，为金融异常发现提供新途径。

链接：https://arxiv.org/abs/2607.09641

机构：A3Data（A3数据公司）

作者：Cláudio Lúcio do Val Lopes, Lucca Machado da Silva

英文摘要：Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortive data resampling, we propose the Semantic Pareto-DQN, a multi-objective reinforcement learning framework. Our approach synthesizes heterogeneous transaction features into cohesive natural-language narratives, encoded by large language models, thereby producing a robust, scale-invariant state representation. The agent optimizes a vectorial reward that explicitly decouples financial efficacy, operational friction, and semantic discovery. By mapping the continuous Pareto frontier, the system dynamically navigates the asymmetric costs of missed anomalies versus false positives. Empirical evaluations across E-Commerce fraud and UCI Credit datasets show that semantic Pareto-DQN successfully shatters the zero-recall trap. It achieves superior minority-class recall compared to scalarized baselines, providing an alternative to trade bounded operational friction for financial anomaly discovery.

AI 总结：研究通过奖励传输在流匹配中实现属性控制，训练时用最优传输耦合将噪声空间坐标与分子奖励对齐，推理时改变坐标引导生成分布，实验表明可对logP和QED进行有效控制，且该接口与其他方法互补，明确了耦合级对齐不存在的情况。

链接：https://arxiv.org/abs/2607.08781

机构：University of Notre Dame（圣母大学）； Carnegie Mellon University（卡内基梅隆大学）

作者：Kehan Guo, Yili Shen, Yujun Zhou, Yue Huang, Chujie Gao, Shiyi Du, Xiangliang Zhang

英文摘要：The coupling in flow matching -- the rule pairing noise vectors with data points -- is typically treated as a computational choice. We show that this coupling can instead serve as an alignment interface: by matching noise and data according to a target molecular property, it embeds controllable structure directly into the learned flow field. Building on this view, we introduce Reward Transport, which uses optimal transport coupling at training time to align a scalar noise-space coordinate with molecular rewards; at inference, varying this coordinate steers the generated distribution without requiring an oracle, reward model, gradient guidance, or additional computation. In the coupling-preserving limit, thresholding this coordinate recovers the Cross-Entropy Method's truncated reward distribution, providing a principled, continuously adjustable distribution-level control knob. Empirically, on ZINC-250K and GuacaMol, sweeping the scalar induces monotone control of logP and consistent QED control over its operating range; most tellingly, the same knob produces opposite structural responses for different targets, growing molecules for logP but shrinking them for QED, which rules out a generic size bias. The interface is complementary to classifier-free guidance and conditional flow matching, while a negative result under epsilon-prediction diffusion clarifies where coupling-level alignment is structurally absent. Code: this https URL

AI 总结：研究针对蛋白质设计中可变长度生成的关键问题，引入广义泊松流（GPFlow）框架，通过最小化负对数似然学习速率函数，经多模态评估验证其可变长度生成质量，在多种设计任务中表现出色，提升了蛋白质设计的灵活性与适应性。

链接：https://arxiv.org/abs/2607.09039

作者：Chaoran Cheng, Zhanghan Ni, Yanru Qu, Yuxin Chen, Ruihan Guo, Jiajun Fan, Ge Liu

英文摘要： The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- and flow-based generative models typically require the protein length to be specified before sampling, limiting their flexibility in exploring the feasible design space. To address this limitation, we introduce Generalized Poisson Flow (GPFlow), a variable-length generative framework that learns the rate function of an inhomogeneous generalized Poisson process by minimizing its negative log-likelihood. We establish population-level guarantees for recovering the joint multimodal distribution and derive an upper bound on the KL divergence between the data and generated distributions. We comprehensively evaluate GPFlow across structure and sequence design, motif scaffolding, and peptide co-design, spanning Euclidean, categorical, and Riemannian modalities to fully validate its variable-length generation quality. In unconditional design, GPFlow improves structural designability and achieves the best distributional fitness for sequence design compared to their corresponding fixed-length baselines, while perfectly recovering the length distribution. In conditional motif scaffolding, GPFlow ranks first on 10 of 16 structure-based design tasks with significantly more unique successes and also achieves more passed tasks in sequence-based design. In peptide co-design, GPFlow remains competitive even without access to a native-length oracle.

AI 总结：研究变分量子电路与扩散模型集成，通过多实验发现量子核心在FID上与经典控制相当但未证明参数效率优势，还识别出基于分数的NCSN的结构故障及角度嵌入失败问题，提供了公平比较协议和机理说明。

链接：https://arxiv.org/abs/2607.09108

机构：NextITS Co., Ltd.（NextITS有限公司）

作者：Jaeuk Kim, Sanghoon Yoo

英文摘要：We study the integration of variational quantum circuits (VQCs) into diffusion models through a squeeze-and-excitation (SE) channel-modulation scaffold that isolates the quantum contribution. Using a role-matched classical control and multi-seed significance testing across DDPM and latent diffusion on MNIST and CIFAR-10, with a score-based NCSN study on MNIST, we find that quantum cores achieve comparable mean FID to the classical control across DDPM and latent diffusion, while paired sampling-seed tests for EfficientSU2 detect no statistically significant difference. Although the quantum cores use $4.5$--$9\times$ fewer core parameters than the role-matched control, parameter-matched classical controls attain comparable mean FID, so the experiments do not establish a quantum parameter-efficiency advantage. We further identify a structural failure in score-based NCSN: the unbounded score target, proportional to $1/\sigma$, drives angle-embedding inputs far beyond the $2\pi$ period of rotation gates, causing phase aliasing and collapse of the quantum modulator. A bounding transformation, $\theta \leftarrow \pi \tanh(\cdot)$, maps inputs to the non-aliasing domain and substantially improves both quantum cores. Since all circuits are classically simulated at a few-qubit scale, we do not claim quantum advantage. Instead, the study provides a fair-comparison protocol for quantum-enhanced generative models and a mechanistic account of when and why angle embeddings fail.

AI 总结：研究3D分子生成问题，提出KRONOS潜自回归扩散框架，联合建模分子图拓扑和几何，引入混合训练策略。实验表明其在自回归方法中无条件生成性能领先，与扩散模型竞争，单一架构可支持两种生成范式。

链接：https://arxiv.org/abs/2607.09277

作者：Federico Ottomano, Gaopeng Ren, Yingzhen Li, Kim E. Jelfs, Alex M. Ganose

英文摘要：Three-dimensional (3D) molecule generation has been dominated by diffusion models, which achieve strong generation quality but typically require the molecular size to be specified a priori. Recent autoregressive approaches have substantially narrowed the performance gap while naturally supporting variable-length generation and conditioning on partial molecular context. However, balancing unconditional and context-conditioned generation remains challenging. We introduce KRONOS, a latent autoregressive diffusion framework that generates molecules in the latent space of a pre-trained autoencoder, jointly modeling molecular graph topology and geometry, while retaining the flexibility of autoregressive generation. We further introduce a mixed training strategy inspired by Fill-in-the Middle (FIM) paradigm, enabling both unconditional and fragment-conditioned molecular generation within a single left-to-right autoregressive model. Experiments on QM9 and GEOM-Drugs demonstrate that KRONOS achieves leading unconditional generation performance among autoregressive methods, while remaining competitive with diffusion models. Moreover, fragment-conditioned generation is achieved with negligible impact on unconditional generation performance, demonstrating that both generation paradigms can be supported within a single architecture.

AI 总结：研究贝叶斯和乘法权重更新的遗憾问题，提出基于信息核算恒等式的方法，给出累积遗憾的精确自适应分解，该演算涵盖多种学习和博弈场景，揭示有利情况的自界属性。

链接：https://arxiv.org/abs/2607.08789

作者：Akshay Balsubramani

英文摘要： Bayesian and multiplicative-weights updates reweight experts, models, or actions from sequential feedback. We show that the regret of any such update obeys an exact information-accounting identity. On each round, the learner's excess loss to any chosen comparator is the sum of an immediate payment for the uncertainty exposed by the round and a reduction in the information distance from the learner's current weights to the comparator. The cumulative payment defines a pathwise uncertainty clock, the \emph{intrinsic time} of the realized sequence. Summing one-step balances yields two exact adaptive decompositions of cumulative regret, one for each natural way of composing the update across rounds. Because the decompositions are exact rather than upper bounds, favorable stochastic or low-noise regimes appear as self-bounding properties of the realized intrinsic time, not as slack in worst-case analyses. The same calculus covers Hedge, optimistic and side-information variants, continuous priors, boosting, online convex optimization, contextual bandits, and repeated games: the pathwise account is the same in every case.

AI 总结：研究多任务贝叶斯优化的陷阱与补救措施，发现其在简单情况下也会误估跨任务相关性，将失败归因于任务标准化和边际似然问题，提出三种补救措施，在简单实例上有效果，复杂实例中仍存在问题。

链接：https://arxiv.org/abs/2607.09073

机构：Meta（元）

作者：Carl Hvarfner, Sam Daulton, Max Balandat, Eytan Bakshy

英文摘要：Bayesian optimization routinely warm-starts a target experiment with data from related source tasks, and the multi-task Gaussian process is the textbook surrogate for the job. We revisit this default in a controlled setting and find that it misestimates the cross-task correlation even in the simplest non-trivial case, affinely related source and target tasks, where a working transfer learning method should obviously succeed. We trace the failure to two independent structural mechanisms. Per-task standardization, the textbook fix for the affine slice ambiguity, propagates a finite-sample alignment error into the recovered correlation. The marginal likelihood itself identifies the correlation only at a per-sample rate that a Gaussian process at non-overlapping designs further dilutes. We propose three conservative remedies that follow from the analysis: promoting per-task means and scales to model parameters, restricting the task covariance to non-negative correlations, and co-locating part of the source and target designs. Across synthetic multi-task problems and surrogate-based hyperparameter tuning transfer, these remedies recover the target-only baseline on the simple instances, while the broader failure persists on harder instances and across most rank-based and latent-context variants.

AI 总结：研究非凸优化中无调度方法，通过李雅普诺夫分析给出最坏情况收敛速率分析，还将无调度梯度下降建模为非自治动力系统，证明其在微小扰动下可避免严格鞍点，解释了该方法性能良好的原因。

链接：https://arxiv.org/abs/2607.09167

机构：KAIST（韩国科学技术院）； Natural Science Research Institute（自然科学研究所）； Department of Mathematical Sciences（数学科学系）

作者：Jiseok Chae, Donghwan Kim

英文摘要：Schedule-Free methods have attracted growing interest for alleviating the burden of designing and tuning a learning rate scheduler, while matching and sometimes even outperforming optimizers with tuned schedulers. Despite their strong empirical results, their convergence theory in nonconvex optimization, where modern machine learning objectives typically arise, has remained largely unexplored. In this paper, we provide worst-case analyses of Schedule-Free gradient descent and Schedule-Free stochastic gradient descent, in their standard form and without auxiliary modifications or restrictive conditions, for smooth but possibly nonconvex objectives. Based on a Lyapunov analysis derived from the continuous-time limiting ordinary differential equation associated with these methods, we show that Schedule-Free gradient descent and Schedule-Free stochastic gradient descent achieve the optimal worst-case convergence rates attainable among first-order methods. We further formulate Schedule-Free gradient descent as a nonautonomous dynamical system and prove strict-saddle avoidance under an arbitrarily small one-time perturbation. These theoretical results provide a better understanding of the strong performance that Schedule-Free methods demonstrate.

AI 总结：研究针对深度学习在惯性传感器分类任务中依赖大规模数据集的瓶颈，通过系统实证评估学习曲线收敛率，提出统一框架和经验公式，引入定量稳定点指标，提供可推广框架，优化数据效率，为惯性传感应用记录活动规划提供指南。

链接：https://arxiv.org/abs/2607.09402

机构：The Autonomous Navigation and Sensor Fusion Lab, the Hatter Department of Marine Technologies, University of Haifa（海法大学自主导航与传感器融合实验室，海洋技术哈特学院）

作者：Ofir Kruzel, Itzik Klien

英文摘要：Deep learning models dependency on large-scale inertial datasets presents a significant bottleneck in inertial sensor-based classification tasks, such as human activity recognition and smartphone location recognition. In these domains, data collection requires massive recording campaigns that are complex, time-consuming, and difficult to scale. Currently, data-driven guidelines for determining the minimum sample size required to reach a desired accuracy level do not exist. To address this gap, this study presents a systematic empirical evaluation of learning curve convergence rates in inertial classification. We introduce a unified framework that analyzes classification performance under both binary and multi-class scenarios, and derive an empirical formula to estimate performance relative to dataset size. Testing across six diverse, real-world datasets totaling 102.7 hours of inertial measurements demonstrates that accuracy follows a consistent logarithmic growth pattern, regardless of task complexity. Leveraging this finding, we propose a quantitative stability point metric, defined as the sample size required for the learning curve to stabilize within a predefined mean absolute percentage deviation of its asymptotic maximum. Our analysis reveals that models often reach practical stability with substantially fewer samples than traditional heuristics suggest. Ultimately, we offer a generalizable framework to extrapolate total data requirements from small-scale pilot studies, optimizing the tradeoff between recording effort and model reliability. These findings shift the prevailing paradigm from maximizing data volume toward optimizing data efficiency, offering concrete, data-backed guidelines for planning recording campaigns in inertial sensing applications.

AI 总结：研究针对通用机器学习原子间势训练数据集受限问题，提出自适应多教师路由方法，通过校准预训练教师、估计结构-教师对可靠性来生成伪标签，提升模型性能和动力学鲁棒性，有效构建高保真uMLIPs数据系统。

链接：https://arxiv.org/abs/2607.09456

机构：Fudan University（复旦大学）； Shanghai Innovation Institute（上海创新研究院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Suzhou Laboratory（苏州实验室）

作者：Mingxiang Luo, Xinnan Mao, Lu Wang, Lei Bai, Feng Ding, Yuqiang Li

英文摘要：Universal machine learning interatomic potentials (uMLIPs) bridge quantum-mechanical accuracy and large-scale molecular dynamics, but the cost of high-accuracy calculations such as r$^2$SCAN limits training to datasets that remain small relative to the open materials space. Strong average benchmark performance also does not guarantee reliable energy--force predictions for every structure. We propose Adaptive Multi-Teacher Routing (ATR), which reformulates high-fidelity data construction as a structure-wise decision problem under uncertainty. Using a small set of real r$^2$SCAN labels, ATR calibrates multiple pretrained uMLIP teachers and combines structural descriptors, teacher identity, and inter-teacher disagreement to estimate the reliability of each structure--teacher pair. It selects high-confidence predictions for pseudo-label generation and rejects structures for which no teacher is sufficiently reliable. With real r$^2$SCAN labels for only 0.2\% of candidate structures, ATR distils 2.89 million traceable r$^2$SCAN-level pseudo-labels for pretraining. On held-out r$^2$SCAN structures and the MP-r$^2$SCAN benchmark, a lightweight CHGNet trained on the ATR-generated dataset consistently outperforms the baseline and non-routed controls. Finite-temperature molecular dynamics further shows that ATR improves dynamical robustness across multiple material systems, maintaining stable trajectories where baseline simulations undergo catastrophic structural collapse. These results establish active rejection as an effective mechanism for converting multiple pretrained uMLIPs into a scalable and reliable data-construction system for high-fidelity uMLIPs.

AI 总结：研究少比特整数量化问题，提出带符号对称量化方法，通过有原则的符号选择规则放置额外可表示值，保持对称量化运行时特征，理论分析其在量化误差上有条件最优，实证验证在模型上有效果提升。

链接：https://arxiv.org/abs/2607.08779

机构：AMD（超威半导体公司）

作者：Ian Colbert, Eashan Dash, Pablo Monteagudo-Lago, Juan Amboage, Srinidhi N, Giuseppe Franco, Nicholas J. Fraser, Arun Ramachandran

英文摘要：The signed integer alphabet contains one more negative representable value than positive. Yet, by convention, the standard symmetric integer quantizer fixes its scale to be strictly positive, which assigns this extra representable value to the negative tail and can force clipping of positive outliers. In this work, we show that, at few-bit precision, such clipping is a non-trivial source of quantization error. Asymmetric quantization addresses this problem with a zero point, shifting the grid toward the observed data range; however, this flexibility is well-known to carry a runtime penalty. For example, in this http URL on an AMD EPYC(TM) "Turin" CPU, a 4-bit symmetric format uses up to 9% less memory with up to 2.45$\times$ higher throughput than its asymmetric counterpart. We highlight signed symmetric quantization as a third option that retains the runtime profile of symmetric quantization without the penalty of the asymmetric format: our signed absmax grid places the extra representable value on the dominant-outlier tail through a principled and lightweight sign selection rule while keeping the zero point at zero. Our theoretical analysis offers two main results. First, we establish the signed absmax grid as conditionally bound-optimal on $\ell_2$ quantization error, and show that the condition holds for 88-99% of weight groups across pre-trained large language models (LLMs) at low bit widths. Second, we show that negating the scale of a standard symmetric quantizer is analytically equivalent to a unit zero point shift on the same signed integer alphabet. We empirically validate our proposal on models from the Qwen3, Qwen3.5, and Llama3 families, and observe improvement in perplexity and downstream few-shot accuracy over the standard unsigned symmetric quantizer at no extra inference cost

AI 总结：研究大语言模型推理成本挑战，提出含稀疏张量核层等的三层矩阵存储格式，设计联合稀疏张量核与CUDA核的SpMM内核，实现了在现代GPU上超越密集矩阵乘法，取得显著加速。

链接：https://arxiv.org/abs/2607.08786

机构：National University of Singapore（新加坡国立大学）； Zhejiang University（浙江大学）

作者：Tao Lu, Haoyu Wang, Zonghui Wang, Keshen Xiang, Jiaheng Zhang, Wenzhi Chen

英文摘要：With the growing deployment of large language models (LLMs), LLM inference cost has become a key challenge. Pruning techniques that introduce sparsity into weight matrices can accelerate inference. However, maintaining model quality typically limits pruning to moderate unstructured sparsity (around 50\%). At these sparsity levels, none of the existing GPU kernels for sparse matrix multiplication (SpMM) can outperform their dense counterparts. This paper proposes an efficient GPU inference method for LLMs with moderate sparsity. We propose a three-layer matrix storage format comprising: (i) a Sparse-TC layer enabling sparse tensor cores to accelerate SpMM; (ii) a Slot-Filling layer using parallel differential distance for matrix compression while supporting low-cost on-chip decoding; (iii) a lightweight Residual Layer ensuring correct SpMM computation. Building on this format, we design a SpMM kernel that jointly utilizes sparse tensor cores and CUDA cores. This design enables an efficient execution pipeline and overlaps on-chip computation with memory access. Evaluations show that our work is the first to outperform dense matrix multiplication on modern GPUs equipped with high-bandwidth memory (HBM). It achieves up to 1.64x kernel-level speedup over SpInfer (EuroSys'25, Best paper) and up to 1.41x end-to-end speedups over FlashLLM (VLDB'24). Our source code: this https URL.

AI 总结：研究针对扩散大语言模型服务的收敛异质性问题，提出BlockServe框架，集成块粒度调度、混合状态执行及计算感知准入控制器，在五个基准测试中实现高吞吐量，确立块粒度调度为高吞吐量离线dLLM推理基础。

链接：https://arxiv.org/abs/2607.08930

作者：Yuanjie Zhu, Liangwei Yang, Ke Xu, Weizhi Zhang, Shanghao Li, Zihe Song, Philip S. Yu

英文摘要：Efficient serving of diffusion large language models (dLLMs) is hindered by convergence heterogeneity: when batching multiple requests, different sequences converge at different rates, causing faster requests to stall behind slower stragglers and introducing compute bubbles and tail latency. We present BlockServe, a continuous batching framework that integrates block-grained scheduling -- immediately evicting completed requests at block boundaries -- with mixed-state execution that extends dual cache and parallel decoding to heterogeneous batches via gather-scatter indexing. Furthermore, a compute-aware admission controller expands effective batch capacity through token-budgeted refill. On Dream and LLaDA across five benchmarks, BlockServe achieves 1.9--10.6$\times$ throughput over Fast-dLLM with comparable generation quality, establishing block-grained scheduling as a foundation for high-throughput offline dLLM inference.

AI 总结：研究大语言模型中如何在保留模型质量时减少计算，提出灵敏度感知阈值处理方法SATS及轻量级令牌路由框架，经实验评估，SATS在匹配稀疏度时优于基线，令牌路由有更好的质量-吞吐量权衡，改进方法可提升大语言模型权衡效果。

链接：https://arxiv.org/abs/2607.08991

机构：Santa Clara University（圣塔克拉拉大学）； Sogang University（西江大学）

作者：Bishmoy Paul, Youngmin Yi, Hoeseok Yang

英文摘要：Efficient inference in Large Language Models (LLMs) requires deciding where computation can be reduced while preserving model quality. We study this problem through multilayer perceptron (MLP) activation sparsification and token-level conditional routing. We first propose Sensitivity-Aware Thresholding for Sparsity (SATS), a threshold calibration method to choose layerwise gate thresholds using a local MLP output sensitivity proxy rather than calibrating thresholds directly from activation percentiles. While SATS retains the existing mechanism of sparsifying MLP activations by thresholding gate activations, it replaces percentile-based calibration with a sensitivity-aware selection rule. We then introduce a lightweight token routing framework that dynamically selects between a base path and a modified path on a per-token basis, rather than applying the modified computation uniformly to all tokens. We evaluate both methods on multiple recent open-weight LLMs. Our results show that SATS improves over the threshold-based sparsification baseline at matched actual sparsity and that token routing yields a more favorable quality-throughput trade-off than static activation modification baselines. Overall, our results suggest that improved threshold calibration and token routing can improve the quality-throughput trade-off in LLMs.

AI 总结：研究大语言模型中缓解KV缓存读取瓶颈的块稀疏注意力方法，以DeepSeek的NSA为代表分析其块选择问题。通过累积量展开指出现有方法局限，提出COBS方法，在32k RULER基准上提升了NSA基线分数，缩小与密集注意力差距，且减少了KV缓存读取流量。

链接：https://arxiv.org/abs/2607.09052

机构：MatX

作者：Alexander Tian, Aditya Ghai, Sanjit Neelam, Zaal Vasania, Akshay Mishra

英文摘要：Block sparse attention is a hardware friendly way to alleviate the key-value (KV) cache read bottleneck in large language models (LLMs). However, it is not prevalent among leading open-weight LLMs, which rely instead on dense attention or fine-grained selection, thereby motivating our analysis. We study DeepSeek's Native Sparse Attention (NSA) as a representative method, whose three-branch design lets us isolate block selection, the most challenging and consequential stage. We formalize selection and reduce it to ranking blocks by a single quantity, the attention mass: the sum of a block's attention scores. We show that if selection retrieves the blocks with the largest attention mass, block sparse attention can match the quality of dense attention. However, computing the exact attention mass requires reading every key, so the problem of block selection ultimately reduces to approximating this mass from a compact summary instead of the full keys. Via a cumulant expansion, we show why existing methods falter: their selection strategies attempt to estimate the attention mass, but are confined to a first-order approximation. Therefore, we propose COBS (Cumulant Order Block Sparse Attention), an attention method that builds on NSA, incorporating a novel selector that stores a compressed second-order statistic per block. On the 32k RULER long-context retrieval benchmark, COBS raises the NSA baseline's mean score from 0.2999 to 0.8195, approaching dense attention at 0.9040 and closing about 86% of the gap, while using only 1.21x the KV cache read traffic of the NSA baseline and 15.15x less read traffic than dense. The same model preserves short-context behavior and attains lower position-wise negative log-likelihood (NLL) than dense attention in our comparison.

AI 总结：研究针对边缘设备资源有限及测量延迟难问题，提出EvoLP框架预测模型推理延迟，该预测器可在网络压缩中自进化提升精度，实验表明其优于现有方法，融入模型压缩框架可有效指导压缩并满足延迟约束。

链接：https://arxiv.org/abs/2607.09063

机构：School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）； HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University（南洋理工大学惠普-南洋理工数字制造联合实验室）； HP Inc.（惠普公司）

作者：Shuo Huai, Hao Kong, Shiqing Li, Xiangzhong Luo, Ravi Subramaniam, Christian Makaya, Qian Lin, Weichen Liu

英文摘要：Edge devices are increasingly utilized for deploying deep learning applications on embedded systems. The real-time nature of many applications and the limited resources of edge devices necessitate latency-targeted neural network compression. However, measuring latency on real devices is challenging and expensive. Therefore, this letter presents a novel and efficient framework, named EvoLP, to accurately predict the inference latency of models on edge devices. This predictor can evolve to achieve higher latency prediction precision during the network compression process. Experimental results demonstrate that EvoLP outperforms previous state-of-the-art approaches by being evaluated on three edge devices and four model variants. Moreover, when incorporated into a model compression framework, it effectively guides the compression process for higher model accuracy while satisfying strict latency constraints. We open source EvoLP at this https URL.

AI 总结：综述大模型绿色发展，涵盖资源高效架构与软硬件协同设计，回顾高效模型构建、训练部署策略、节能硬件等进展，探讨其在关键领域应用，讨论挑战与方向，为大模型可持续发展提供路线图。

链接：https://arxiv.org/abs/2607.09084

机构：Pengcheng Laboratory（鹏城实验室）； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Peking University（北京大学）

作者：Linhui Xiao, Guiping Cao, Mingyue Guo, Xianchao Guan, Fan Yang, Ming Tao, Xin Li, Yuxin Peng, Yaowei Wang

英文摘要：The rapid expansion of large-scale AI models has led to significant performance breakthroughs across diverse domains, yet it has also raised critical concerns regarding computational costs, energy consumption, and environmental sustainability. This survey provides a comprehensive overview of the green development of large models, emphasizing resource-efficient architectures and full-stack hardware-software co-design. We systematically review recent advances in efficient model construction, including attention operator optimization, linear-complexity architectures, and model sparsification and merging, as well as training and deployment strategies such as data-efficient learning, parameter-efficient fine-tuning, and computational compression. Beyond algorithmic improvements, we explore energy-efficient AI hardware, including mainstream AI chips, memory optimization, cross-platform deployment, and sustainable infrastructure. Furthermore, we examine how large models are being applied to sustainability-critical domains such as DeepSeek, remote sensing interpretation, national-scale infrastructure, and global initiatives. Finally, we discuss key challenges and future directions, highlighting the need for continual learning paradigms, memory-centric hardware, and standardized evaluation protocols. This survey aims to offer a holistic roadmap toward sustainable, scalable, and socially responsible development of large models. Paper homepage: this https URL

AI 总结：研究大型语言模型微调成本高的问题，提出Super和Supra方法，利用剪枝显著性信号，结合Wanda分数与LoRA，通过预算分配规则保持参数预算，在算术实验中取得高准确率，证明简单排序可为PEFT提供支持。

链接：https://arxiv.org/abs/2607.09287

机构：KAUST（沙特阿卜杜拉国王科技大学）； ISTA（奥地利科学技术研究所）； Yandex Research（Yandex 研究院）

作者：Ivan Ilin, Philip Zmushko, Peter Richtárik

英文摘要：Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 2023] computed from a calibration pass. We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA while preserving a matched trainable-parameter budget through a simple budget-splitting rule. In single-seed Math17K arithmetic experiments on Llama-3.2-1B and Meta-Llama-3-8B, the best Super/Supra variants achieve the highest average accuracy among the tested schedule-selected adapter configurations. We also include a PaFi-style magnitude-only support as a closest training-free sparse baseline and find that low-score supports under both magnitude and Wanda-style orderings can be effective. These results suggest that simple pruning-inspired orderings can provide useful fixed sparse supports for PEFT, especially when combined with low-rank adapters.

AI 总结：研究物联网系统多变量时间序列异常检测问题，提出FedKAD框架，通过轻量级滑动窗口库普曼表示学习正常时间动态，经联邦训练优化共享表示，实验表明其检测性能良好且适用于资源受限的边缘设备。

链接：https://arxiv.org/abs/2607.08978

机构：University of Technology Sydney（悉尼科技大学）； FPT University（越南邮电大学）； Hanoi University of Science and Technology（河内科技大学）

作者：Tung-Anh Nguyen, Van-Phuc Bui, Anh Tuyen Le, Kim Hue Ta, Minh Thuy Le, J.Andrew Zhang, Xiaojing Huang

英文摘要：Distributed IoT systems generate multivariate time-series streams for monitoring physical assets, servers, and embedded sensing platforms. Detecting abnormal temporal behavior is critical for fault diagnosis, predictive maintenance, and security. However, practical IoT anomaly detection is hindered by decentralized and non-IID data, limited bandwidth, and the constrained computation and memory of edge devices. This paper proposes FedKAD, a resource-efficient federated Koopman anomaly detection framework for distributed IoT multivariate time series. Unlike deep-learning-based anomaly detectors that require training and communicating large neural models, FedKAD learns normal temporal dynamics through lightweight sliding-window Koopman representations. Federated training is formulated as a low-rank consensus problem, where raw sensor streams and local reduced dynamics remain on device while only compact subspace variables are exchanged with the server. To optimize the shared representation under orthonormality constraints, we develop a federated Stiefel-ADMM algorithm and provide convergence and stationarity analysis under partial client participation. During inference, each client detects anomalies locally by measuring the prediction residual between observed future trajectories and the learned Koopman dynamics. Experiments on four widely used multivariate time-series anomaly detection benchmarks show that FedKAD maintains or improves detection performance compared with federated deep-learning baselines. More importantly for IoT deployment, FedKAD provides up to $2.1\times10^3$ faster training, $80\times$ lower communication, and $79\times$ lower inference latency than neural baselines, confirming its suitability for resource-constrained edge devices.

AI 总结：研究大语言模型安全表示，引入激活引导的对抗后缀攻击方法，如Activation-Guided GCG和Soft-GCG，发现安全表示分布特点，不同规模模型的抗性不同，结果阐明安全机制编码及破解方式，为设计对齐策略提供指导。

链接：https://arxiv.org/abs/2607.08883

作者：Ege Çakar, Hannah Guan, Kayden Kehe

英文摘要：Behavioral alignment in large language models often masks fragile internal safety representations. Recent work suggests that refusal behavior is mediated by low-dimensional directions in activation space. This raises questions about how such representations are structured, localized, and accessed by optimization. We study adversarial suffix attacks as a probe of representational alignment. We introduce Activation-Guided GCG, which replaces output-based objectives with losses that directly target a model's internal refusal direction. Across several objective variants, we find that suppressing refusal globally across all layers and positions is more effective than targeting a single layer-position pair. This suggests that safety representations are distributed across the forward pass rather than causally localized to a single site. We further introduce Soft-GCG, a continuous relaxation of discrete suffix optimization using Gumbel-Softmax. Soft-GCG achieves a 33 $\times$ speedup over standard GCG while improving attack success rates. Evaluating across model scales, we find that smaller models remain vulnerable while larger models resist both activation- and suffix-based attacks at our compute-constrained settings, consistent with larger and better safety trained models being harder to jailbreak. Together, our results clarify how safety mechanisms are encoded and can be broken in contemporary models. These insights provide concrete guidance for designing more robust and representation-aware alignment strategies.

AI 总结：研究对抗模型训练者在深度前馈神经网络中植入统计上不可检测的后门，此后门可提供基于不变性的对抗样本，揭示了模型训练者与使用者间的权力不对称，且无后门时多项式时间内无法生成此类样本。

链接：https://arxiv.org/abs/2607.09532

机构：University of Ottawa（渥太华大学）； Bocconi University（博科尼大学）； Massachusetts Institute of Technology（麻省理工学院）

作者：Andrej Bogdanov, Alon Rosen, Neekon Vafa

英文摘要：We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users.

AI 总结：研究针对现实数据集中的缺失数据问题，提出模式感知图神经网络，采用四种编码策略，在七个UCI数据集上实验，相比基线方法有显著改进，揭示了注意力机制在有模式信息时非关键，强调区分模式比特定任务优化更重要。

链接：https://arxiv.org/abs/2607.08915

机构：San Jose State University（圣何塞州立大学）

作者：Minett Tran, Taehee Jeong

英文摘要： Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that missingness occurs randomly. However, missingness patterns might provide additional information. We propose pattern-aware graph neural networks that explicitly encode which features are missing alongside observed values. We used four encoding strategies -- learned embeddings, frozen random embeddings, statistical features, and hierarchical representations -- across seven UCI datasets with naturally occurring missingness. Our Pattern-aware methods achieve substantial improvements over baselines, with an average improvement of 17\% in balanced accuracy and 22\% in F1-macro across all datasets. The benefits vary significantly by dataset: annealing shows dramatic improvement (+80\% balanced accuracy), while hepatitis and soybean show minimal gains (+4--5\%). Notably, even simple random pattern embeddings perform comparably to learned embeddings (0.650 vs 0.663 balanced accuracy), suggesting that distinguishing between patterns may be more important than task-specific optimization. Our ablation study reveals that attention mechanisms, while helpful, are not critical when pattern information is available -- simple mean aggregation with pattern awareness achieves 0.640 balanced accuracy compared to 0.645 for attention-based variants.

AI 总结：研究针对晶体性质预测，提出多级图提示学习框架，包含节点级和图级软提示，能捕获潜在特征。该框架轻量级且与现有GNN编码器无缝集成，实验表明显著提升模型性能，还实现跨属性知识转移。

链接：https://arxiv.org/abs/2607.08996

作者：Shrimon Mukherjee, Kishalay Das, Partha Basuchowdhuri, Pawan Goyal, Niloy Ganguly

英文摘要：Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter size and makes their performance heavily dependent on domain expertise. Added to this, explicitly incorporating all chemical and structural features, that might influence a specific crystal property into the GNN encoder, is a challenging task. In this work, we propose a soft prompt learning framework that captures latent features essential for property prediction, which are not explicitly provided to the GNN. We introduce a novel multilevel graph prompt learning framework comprising both node-level and graph-level soft prompts. At the node level, we capture the local chemical semantics of different atom types, while at the graph level, we encode the global structural symmetry of the crystal graph. Our proposed prompt learning framework is lightweight and seamlessly integrates with any existing GNN encoder. Extensive experiments on popular benchmark datasets show that incorporating prompt learning significantly improves (3\% - 15\%) the performance of state-of-the-art GNN models in crystal property prediction tasks. Furthermore, the learned soft prompts enable cross-property knowledge transfer, enhancing prediction performance for properties with limited training data. Code is available at this https URL

AI 总结：研究利用变分图自动编码器检测潮流解可行性的问题，核心方法是提出VGAE，主要贡献为用IEEE 118节点系统评估AI驱动求解器所提供解的有效性。

链接：https://arxiv.org/abs/2607.09122

机构：Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR)（加泰罗尼亚大学与研究资助管理局（AGAUR））； Departament de Recerca i Universitats of the Generalitat de Catalunya（加泰罗尼亚自治区研究与大学部）

作者：Ferran Bohigas-Daranas, Hamid Latif-Martinez, Eduardo Prieto-Araujo, Pere Barlet-Ros, Oriol Gomis-Bellmunt

英文摘要：Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention has been paid to the solution feasibility, which can be obtained by traditional solvers. This paper presents a Variational Graph Autoencoder (VGAE) that detects the power flow solution feasibility, using the IEEE 118-bus case, to assess the validity of the solutions provided by AI-driven solvers.

AI 总结：研究用图神经网络近似介数和接近中心性，将其作为节点排序问题，以精确中心性值监督，用肯德尔tau秩相关评估。通过混合分布训练等方法，在不同图拓扑上取得较好结果，证明其可提高结构转移能力，同时指出接近中心性对拓扑敏感这一挑战。

链接：https://arxiv.org/abs/2607.09372

机构：Center for Nonlinear and Complex Systems, Università degli Studi dell’Insubria（非线性与复杂系统中心，因苏布利亚大学）； Data Science Institute, Hasselt University（哈塞尔特大学数据科学研究所）

作者：Samra Sana, Giorgio Mantica, Saul Imbrici

英文摘要：Graph Neural Networks (GNNs) provide a learning-based framework for approximating graph quantities that are expensive to compute exactly. This paper investigates GNNs for scalable approximation of betweenness and closeness centrality, formulated as a node-ranking problem. Exact centrality values are used as supervision, and ranking quality is evaluated using Kendall's tau rank correlation. We study whether message-passing GNNs can learn transferable structural representations across different graph topologies rather than only fitting the distribution used during training. On unseen Erdos renyi graphs, the proposed models achieve tau = 0.851 for betweenness and tau = 0.894 for closeness. A large-scale betweenness model trained on graphs with N = 5,000 nodes achieves tau = 0.938, demonstrating scalability. Mixed-distribution training on Erdos renyi, Barabasi-Albert, and Gaussian Random Partition graphs improves betweenness transfer across graph families. In contrast, closeness centrality remains more sensitive to community-structured graphs and shows reduced transfer to real-world topologies. Finally, GNN inference achieves up to a 97.7x speedup over exact computation. These results show that mixed-distribution training can improve structural transfer in GNN-based centrality approximation, while identifying closeness centrality's sensitivity to topology as an open challenge.

AI 总结：研究低秩矩阵填充问题，核心方法是将图正则化纳入RTRMC框架得到GR-RTRMC，利用矩阵行列内在关系，主要贡献是提高矩阵填充在行列强相关场景下的准确性与鲁棒性。

链接：https://arxiv.org/abs/2607.09546

机构：Royal Meteorological Institute of Belgium（比利时皇家气象研究所）

作者：Benoît Loucheur, P.-A. Absil, Michel Journée

英文摘要：We address the low-rank matrix completion problem by incorporating graph regularization into the existing Riemannian Trust-Region Matrix Completion (RTRMC) framework. The latter uses the geometry of the low-rank constraint to remodel the problem as an unconstrained optimization problem on a single Grassmann manifold. Our approach, named Graph-Regularized RTRMC (GR-RTRMC), exploits the inherent relationships between rows and columns of the matrix. By using these relationships, we aim to improve the accuracy and robustness of matrix completion, particularly in scenarios where the underlying data exhibits strong correlations between rows or columns.

AI 总结：研究持续学习中遗忘问题，提出将遗忘建模为任务间干扰，据此推导IGFA方法，该方法无重放、无Fisher，任务对齐时共享方向，冲突时保护方向，在不同任务情况表现良好，能实现无损保留或转移成本。

链接：https://arxiv.org/abs/2607.09202

机构：VARTA Microbattery GmbH（瓦尔塔微电池有限公司）

作者：Julius Störk

英文摘要：Continual learning commonly relies on post-hoc mechanisms such as replay, elastic regularization, or distillation. This work argues that forgetting should instead be modeled directly as interference between tasks. In the frozen-feature regime, forgetting from learning a new task is exactly the interference energy induced on the old task. In deep networks, the same quantity is recovered through path-averaged curvature with minimal additional forward passes. When task supports are disjoint, forgetting can be eliminated structurally and when task supports overlap in conflicting directions, a non-zero distortion floor is unavoidable. The same geometry optimally merges models through task-aware orthogonalization. From this analysis we derive Interference-Gated Functional Allocation (IGFA), a replay-free, Fisher-free method that shares directions when tasks align and protects them when they conflict. Across benchmarks, IGFA achieves lossless retention when tasks are structurally separable and moves unavoidable cost from irreversible forgetting into deferred but recoverable plasticity when they are not. It matches the strongest replay-free structural baselines on dissimilar-task streams and improves on unconditional projection when similarity makes transfer worth preserving.

AI 总结：研究大语言模型中模型遗忘的不对称泛化问题，提出SUITE评估协议和训练语料库，解决现有基准测试的不足，在此基础上引入JensUn++算法，实现更好的遗忘 - 保留效用权衡。

链接：https://arxiv.org/abs/2607.09236

机构：Tübingen AI Center, University of Tübingen（图宾根大学图宾根人工智能中心）

作者：Amit Peleg, Naman Deep Singh, Naama Pearl, Bibhabasu Mohapatra, Matthias Hein

英文摘要：Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety. Yet existing benchmarks measure it unreliably. They miss knowledge that resurfaces under paraphrased or indirect queries, a failure we call under-forgetting, and lack the semantic, syntactic, and lexical probes needed to verify that unrelated knowledge is preserved, a failure we call over-forgetting. Both failures reflect an asymmetric generalization problem. Forget evaluation must cover diverse query formulations of the same target facts, testing whether forgetting holds beyond exact training prompts. Retain evaluation must probe a far larger and implicitly defined set, namely every fact disjoint from the forget target. The retain set thus defines the effective forget set, yet current datasets provide no fine-grained annotation of this forget-retain boundary. We address this with SUITE, an evaluation protocol and training corpus that captures forget-retain structure for real-world factual domains. Methods trained on SUITE improve substantially, showing that training data is as important as algorithmic design. Building on the obtained insights, we introduce JensUn++, an unlearning algorithm that achieves the best forget-retain utility trade-off across three LLMs, in both sequential and joint unlearning settings. Code and datasets are available at this https URL

AI 总结：研究针对联邦持续学习评估难的问题，提出HERO异构感知基准库，通过分离任务划分等构建基准流，在CIFAR-100等上评估FCL方法，揭示方法行为变化等问题，还进行案例研究，发布多种资源支持可重复及设置感知的FCL评估。

链接：https://arxiv.org/abs/2607.08784

机构：VinUniversity（文大教育集团）

作者：Thinh T. H. Nguyen, Le-Tuan Nguyen, Minh-Duong Nguyen, Nhi Trinh, Anh Tran Nam Nguyet, Dung D. Le, Kok-Seng Wong

英文摘要： Federated continual learning (FCL) evaluates how distributed clients learn from changing data streams while retaining previously learned knowledge. Existing evaluations are difficult to compare because they often change datasets, task splits, client data splits, task orders, backbones, memory assumptions, and reporting rules simultaneously. We introduce \textbf{HERO}, a heterogeneity-aware benchmark library for FCL. HERO builds benchmark streams by separating three choices that are often coupled, namely the task split, the client data split, and the client task sequence. In HERO-Core, the main comparable benchmark, $\alpha$ controls client data skew and $\rho$ controls task-order mismatch. We evaluate representative FCL methods on CIFAR-100 and TinyImageNet using final average accuracy, average forgetting, and bottom-10\% client accuracy. We also include a graph-based Domain-IL portability case study on OGB-MolPCBA, where scaffold-domain granularity changes the input distribution while the prediction task remains fixed. Our results show that method behavior changes across easy and heterogeneous settings, that average accuracy can hide weak bottom-client performance, that task-order mismatch favors different strategies from synchronized evaluation, and that the same HERO interface can expose domain-shift difficulty beyond image-based FCIL. HERO releases benchmark streams, configurations, method implementations, and reporting scripts to support reproducible and setting-aware FCL evaluation.

AI 总结：针对数据产品定价难题，引入含全球9大数据市场16147个数据产品元数据的DaDaDa数据集，用于训练定价模型、建立价格基准及数据产品分类与检索等，实验证明其在数据产品定价、分类和检索方面有效。

链接：https://arxiv.org/abs/2607.08785

机构：ZJU（浙江大学）

作者：Qiheng Sun, Hongwei Zhang, Junxu Liu, Xiaokai Mao, Jinfei Liu, Kui Ren, Haibo Hu

英文摘要：High-quality data drives machine learning advances across industries. Recognizing the value of data, data transactions are increasingly common, giving rise to many data marketplaces, e.g., AWS Marketplace, Databricks, and Datarade. However, determining the appropriate prices for data products remains a significant challenge due to the unique properties of data products. Traditional pricing methods in economics can be categorized into the cost approach, the income approach, and the sales comparison approach. The cost approach fails in data pricing due to near-zero marginal cost from data replication, and the income approach fails due to inherently unpredictable data revenue. The sales comparison approach remains viable, yet its application is hindered by the absence of standardized pricing benchmarks for data products across marketplaces. To address this challenge, we introduce \texttt{DaDaDa}, the first dataset for data product pricing, containing metadata for 16,147 data products from 9 major data marketplaces worldwide. \texttt{DaDaDa} enables the training of pricing models, thereby establishing price benchmarks for new data products. In addition, \texttt{DaDaDa} can be utilized for other important tasks in data markets, such as data product classification and retrieval. Experiments and a retrieval prototype demonstrate the effectiveness of \texttt{DaDaDa} for pricing, classification, and retrieval of data products. The dataset and code are available at this https URL.

AI 总结：研究针对算法公平性方法多孤立单轴评估的局限，提出FairSelect工具包，支持多模型架构等评估。通过合成与真实临床数据集验证，发现公平干预相互作用方式复杂，该工具包能系统识别策略，兼顾临床机器学习中群体公平与模型性能。

链接：https://arxiv.org/abs/2607.08953

作者：Nick Souligne, Isabella Mixton-Garcia, Vignesh Subbian

英文摘要：Algorithmic fairness methods are increasingly used to identify and mitigate bias in machine learning models, yet most approaches are evaluated in isolation and along single demographic axes. This limits practical guidance for selecting fairness strategies, where disparities may arise across intersectional subgroups and across multiple stages of the modeling lifecycle. This work presents FairSelect, a toolkit for systematically evaluating fairness mitigation strategies applied individually and in combination across preprocessing, inprocessing, and postprocessing stages. FairSelect supports multiple model architectures, intersectional subgroup evaluation, and comparison of fairness utility tradeoffs across baseline, single method, and multi level configurations. The framework was validated using synthetic clinical datasets designed to represent specific bias mechanisms and a real-world replication of two-year stroke risk prediction among patients with atrial fibrillation. Synthetic experiments showed that targeted fairness methods generally reduced intended subgroup disparities, while combined strategies produced larger average fairness improvements with modest utility tradeoffs. In the clinical prediction task, mitigation effects were highly variable, with some combinations improving both fairness and predictive performance while others were ineffective or counterproductive. These findings demonstrate that fairness interventions interact in nonadditive and context dependent ways. FairSelect provides a practical framework for systematically identifying fairness strategies that improve subgroup equity while preserving model performance in clinical machine learning.

AI 总结：研究在分布转移下时态知识图谱预测问题，借助合成TKG生成器编码时间和结构属性，评估七种预测架构，发现其鲁棒性依赖信号，循环和周期性规律在平稳时可恢复，结构突变暴露模型适应性局限，增进对TKG模型的理解。

链接：https://arxiv.org/abs/2607.09232

机构：Data and Web Science Group, University of Mannheim（曼海姆大学数据与网络科学组）； SAP Signavio（思爱普公司 Signavio）

作者：Konrad Özdemir, Julia Gastinger, Lukas Kirchdorfer, Heiner Stuckenschmidt

英文摘要： Temporal knowledge graphs (TKGs) represent evolving relational systems, whose underlying data-generating processes often change over time. Yet, TKG forecasting models are commonly evaluated only on empirical benchmark datasets that provide limited insight into the models' robustness to such distribution shifts. Recognising this issue, we study TKG forecasting under controlled shift environments using a synthetic TKG generator that encodes three temporal and structural properties -- recurrence, homophily, and periodicity -- as data-generating mechanisms. This allows us to evaluate seven forecasting architectures under stationary and shifting regimes. Our experiments suggest that robustness in TKG forecasting is highly signal-dependent. Recurrence-based and periodic regularities are largely recoverable under stationary conditions, and simple memory-based baselines can be competitive when recurrence dominates the data. However, structural breaks reveal limitations in model adaptivity, with shifts in latent entity-community structure posing the strongest challenge in our study. Overall, our findings improve the understanding of the capabilities and limitations of current TKG models confronted with temporal distribution shifts.

AI 总结：针对罕见病诊断因症状相似易延迟且机器学习算法应用受法律隐私限制的问题，提出基于Synthea框架的图形用户界面SYNRARE，可生成与常见疾病患者有可定义差异的合成电子健康记录，用于机器学习算法基准测试。

链接：https://arxiv.org/abs/2607.09404

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

作者：Nicolai Dinh Khang Truong, Richard Röttger

英文摘要：Motivation: Rare disease (RD) diagnosis is frequently delayed due to the similarities in symptoms to common disease variants. Machine Learning Algorithms applied to Electronic Health Records show promise for accelerating the diagnosis; however, legal and privacy concerns pose significant barriers. To address these issues, Synthetic Data Generation is an alternative method for obtaining Electronic Health Records and can be applied with any Machine Learning algorithm for benchmarking and development purposes. Despite the availability of Synthetic Data Generation algorithms, support for generating a subset of patients that differ in a definable degree from the majority to simulate patients with RD is often lacking. Results: We present SYNRARE, a graphical user interface based on the Synthea framework that enables easier modification and generation of synthetic Electronic Health Records of RD patients, which differ only to a definable degree from patients with common diseases, thereby enabling the benchmarking and testing of algorithms under controlled technical conditions. SYNRARE enables researchers to rapidly benchmark their Machine Learning algorithms across any scenario. Availability and implementation: SYNRARE, including detailed instructions for installing, is available at this https URL.

AI 总结：针对元宇宙平台带来的欺诈等新挑战及现有数据集局限性，提出TSAI-MetaFraud基准数据集，整合多类信息与欺诈场景，定义多项基准任务并进行基线评估，为元宇宙生态系统相关研究提供基准。

链接：https://arxiv.org/abs/2607.09528

机构：tsai-unb（tsai - 新不伦瑞克大学）

作者：Refat Ishrak Hemel, Ehsan Hallaji, Roozbeh Razavi-Far

英文摘要：The emergence of metaverse platforms has created virtual economies that introduce new challenges related to fraud, bot activity, and illicit financial behavior. Despite growing interest in trustworthy metaverse analytics, existing datasets typically focus on user behavior, authentication, or financial transactions in isolation, limiting the development and reproducible evaluation of multimodal fraud detection methods. To address this gap, we present TSAI-MetaFraud, a multimodal, multi-task benchmark dataset for fraud analytics in virtual economies. TSAI-MetaFraud integrates behavioral, transactional, and graph-structured information while incorporating realistic fraud and automated bot scenarios. We define benchmark tasks including transaction fraud detection, cross-modal node classification, temporal link prediction, and weakly supervised fraud detection, and provide baseline evaluations using machine learning models and graph neural networks. By jointly capturing behavioral activity, financial interactions, and relational structure within a unified virtual economy, TSAI-MetaFraud provides a benchmark for advancing multimodal learning, graph mining, fraud analytics, and trustworthy AI in emerging metaverse ecosystems.

AI 总结：针对阿尔茨海默病前驱期转化预测问题，提出iLENS框架，基于专家混合模型，利用大语言模型合成信息指导专家路由，具备竞争力的预测性能，能为决策提供透明且基于生物学的原理。

链接：https://arxiv.org/abs/2607.08778

机构：University of Pennsylvania（宾夕法尼亚大学）； Yale University（耶鲁大学）

作者：Farica Zhuang, Seong Woo Han, Zixuan Wen, Shu Yang, Yize Zhao, Li Shen

英文摘要：Alzheimer's Disease (AD) is a complex neurodegenerative disorder that continues to impact millions of people worldwide. Predicting AD conversion during the prodromal stage remains critical for disease understanding and patient care. As such, survival models are widely used for AD risk prediction, yet they are typically static predictors with limited interpretability and no capacity for natural language reasoning. In this work, we propose iLENS, an interpretable large language model (LLM) guided framework based on mixture-of-experts (MoE) for survival prediction in AD conversion. Our approach uses LLM to synthesize structured neuroimaging measurements and unstructured information to guide expert routing. Our framework demonstrates competitive predictive performance and capability in patient subtyping. Furthermore, our framework provides transparent, biologically grounded rationales for its routing decisions, bridging the gap between high-performance survival analysis and interpretable clinical decision support.

AI 总结：研究相互依赖的电力通信网络中组件关键性排序问题，基于改进隐含相互依赖模型开发机器学习代理模型，能从结构特征预测故障严重性并排序，在IEEE 118母线系统上表现良好，支持两阶段工作流程。

链接：https://arxiv.org/abs/2607.08918

作者：Sohini Roy, Xheni Hylviu

英文摘要：Cyber-physical power systems are vulnerable to cascading failures caused by tight interdependencies between power and communication infrastructures. Evaluating these failures over large N-k contingency sets with a high-fidelity simulator is computationally prohibitive for resilience planning. Using the previously published Modified Implicative Interdependency Model (MIIM) as the ground-truth cascade simulator, this paper develops a machine-learning surrogate that predicts contingency severity from leakage-free structural features and derives a component-criticality ranking for prioritized hardening analysis. On the IEEE 118-bus system, the Gradient Boosting surrogate achieves Spearman correlations of 0.849 for per-contingency severity prediction and 0.853 for per-component criticality ranking, while remaining stable across three independently sampled datasets. MIIM-derived component criticality itself reproduces only to a Spearman of approximately 0.85 under the present sampling pipeline, and the surrogate operates at this empirical ceiling to within sampling variation. Topological centrality measures on the full interdependent network provide meaningful baselines (Spearman 0.60-0.69), and feature ablation shows that the surrogate's advantage is driven primarily by inter-layer dependency information. These results support a two-stage workflow in which the surrogate rapidly ranks candidate components and MIIM is reserved for selective verification.

AI 总结：研究针对仓库运营中SOP执行问题，提出Eluna智能体系统，它是图形引导多智能体框架，采用非对称情节蒸馏方法，在基准测试和生产应用中，微调模型表现出色，匹配或超教师模型，击败基线，在票务处理应用达94%专家一致性。

链接：https://arxiv.org/abs/2607.08960

机构：Amazon.com, Inc. Fulfillment Technologies and Robotics（亚马逊公司履约技术与机器人部门）

作者：Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu, P Aditya Sreekar, Kaiwen Liu, Chuanneng Sun, Jorge Marchena Menendez, Matthew Bales, Tianyu Yang, Shahnawaz Alam, Rose Yu, Baoyuan Liu, Kristina Klinkner, Shervin Malmasi

英文摘要：Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access. To meet production latency and accuracy needs, we use asymmetric episodic distillation where a strong teacher is improved through episodic error memories, then a smaller student is fine-tuned on the corrected trajectories with memory stripped, internalizing corrections without inference-time overhead. On a 13-task benchmark and two production applications, our fine-tuned models match or exceed their teacher, beat all larger off-the-shelf baselines, and reach 94% expert agreement on the ticket processing application.

AI 总结：针对大规模网约车匹配中等待控制问题，提出EXHOLD两阶段框架，第一阶段学习决策模型分配司机-订单对层级，第二阶段求解等待时间调度，经实验验证能提升市场效率和体验，已在巴西生产系统部署。

链接：https://arxiv.org/abs/2607.09090

机构：Didichuxing Co. Ltd（滴滴出行科技有限公司）

作者：Xu Liu, Kai Wan, Zihao Lu

英文摘要：In large-scale ride-hailing, hold control is a critical mechanism for improving passenger-driver experience. By selectively delaying certain driver-order pairs, the system waits for better opportunities, reduces cancellations, and mitigates wasted driver effort. However, existing industrial hold strategies often rely on heuristic thresholding over multiple predictive models, which can be brittle under non-stationary traffic and hard to optimize for multi-objective experience signals. We propose EXHOLD, a deployable two-stage framework decoupling experience-aware pair assessment from hold-time execution. In Stage I, we learn a decision model assigning each driver-order pair to discrete, interpretable experience tiers by optimizing a unified objective that aggregates satisfaction signals across the matching funnel. In Stage II, we solve for a monotone hold-time schedule via constrained optimization over empirical quantiles. This explicitly enforces service guardrails bounding the unnecessary holding of promising matches while maximizing overall experience improvement. We evaluate EXHOLD through randomized A/B experiments in DiDi's production system in Brazil. Results show consistent gains in marketplace efficiency and experience: EXHOLD increases trip completion and driver income, significantly reduces passenger cancellations, and improves funnel efficiency. Ablations and behavioral analyses confirm both stages are essential and that the policy makes calibrated decisions under spatiotemporal heterogeneity. EXHOLD is currently deployed, serving production traffic in Brazil.

AI 总结： 该研究针对医疗保健人工智能模型部分观测数据问题，提出特征充分性分析（FSA），通过估计缺失变量分布来评估数据充分性，经案例研究验证其能进行患者特定评估、提供特征排序方法等，助力医疗人工智能系统部署。

链接：https://arxiv.org/abs/2607.09165

作者：Qingchu Jin, Felistas Mazhude, Jamie B. Rabb, Robert S. Kramer, Douglas B. Sawyer, Raimond L. Winslow

英文摘要：Achieving early and timely diagnosis and treatment for disease is a major challenge. Recent applications of machine learning (ML) algorithms trained on patient data have shown promise in many different settings for predicting the patient health state. A challenge often faced when applying these ML algorithms is that at any given time, not all clinical variables (features) needed as input to perform prediction tasks are available. We define the concept of full-feature-capacity (FFC) to refer to prediction performance when such algorithms make use of all features on which they were trained. We then introduce Feature Sufficiency Analysis (FSA) - an analysis for determining whether a subset of all clinical features needed by an AI model is sufficient to achieve FFC. FSA estimates the underlying distributions of missing variables conditioned on features that are available. FSA provides a patient-specific assessment of whether the existing set of measured features achieves FFC. If yes, then there is no need to acquire further inputs and a ML-based prediction. We provide two case studies: prediction of need for postoperative prolonged ventilation in patients recovering from heart surgery; 10-year mortality prediction in an outpatient cohort. We also demonstrate that FSA also provides a clinically interpretable feature-ranking methodology based on prediction sufficiency, identifies intrinsically hard-to-predict patient populations, and has the potential to perform cost-aware optimization for clinical data acquisition. FSA provides a generic computational approach for determining whether incomplete clinical information is sufficient to support trustworthy AI-assisted clinical decision-making, thereby facilitating the prospective deployment of healthcare AI systems across diverse clinical settings.

AI 总结：研究在桌面角色扮演游戏开发中，通过构建数据集，将机器学习用于从怪物属性预测等级，经多种模型比较和评估，发现基于树的集成模型表现优，能近似设计师判断，可辅助怪物平衡及系统设计。

链接：https://arxiv.org/abs/2607.09196

机构：AGH

作者：Jolanta Śliwa, Jakub Adamczyk

英文摘要：Designing balanced adversaries is a central but labor-intensive task in tabletop role-playing game (TTRPG) development. In systems such as Pathfinder, each monster is described by many numerical attributes that jointly determine its power, summarized as an ordinal level. We investigate whether machine learning can support designers by predicting this level from a monster's attributes, framing the task as tabular ordinal regression. We introduce what is, to our knowledge, the first dataset built specifically for TTRPG monster-level prediction, derived from publicly available Pathfinder Second Edition data. Using it, we compare classical regression models with rounding schemes, dedicated tabular ordinal regression algorithms, and neural networks with ordinal-aware losses. To mirror real design workflows, we evaluate all models under chronological and expanding-window protocols with several complementary metrics. Results show that tree-based ensembles outperform linear models and neural approaches, achieving near-perfect ordinal ranking and high predictive accuracy. Explainable AI analyses, such as feature importance and error distributions, show that the model is aligned with human intuition and follows patterns grounded in game rules. Together, these results show that machine learning can reliably approximate designer judgments and serve as an effective computer-aided tool for monster balancing and broader TTRPG system design.

AI 总结：针对断裂弹性域实时结构健康监测，提出物理信息深度神经网络框架，不依赖有限元训练数据，通过专用编码策略从边界条件和断裂几何预测位移场，以局部惩罚项施加无牵引力条件，用数值示例证明可行性。

链接：https://arxiv.org/abs/2607.09382

机构：PROMES-CNRS, Université Perpignan Via Domitia (UPVD)（法国国家科学研究中心佩皮尼昂大学多姆itia分校能源与过程系统优化实验室）； LAAS-CNRS, Université de Toulouse (UT)（法国国家科学研究中心图卢兹大学航空航天系统实验室）

作者：Rodolphe Barlogis, Ferhat Tamssaouet, Quentin Falcoz, Stéphane Grieu

英文摘要：This work aims to develop a fast and physically consistent surrogate model for real-time structural health monitoring of fractured elastic domains. We propose a physics-informed DeepONet framework that predicts displacement fields from both boundary conditions and fracture geometry, using a dedicated encoding strategy for the latter and without relying on finite-element-generated training data. The traction-free condition on the fracture boundary is imposed weakly through a localized penalty term. The presented numerical example focuses on one representative fracture geometry, demonstrating the feasibility of the formulation and laying the groundwork for extensions to surrogate modeling across diverse fracture geometries.

AI 总结：研究电动汽车车载自适应电池功率预测问题，通过将预训练模型转换为可适应版本，结合在线和离线适应策略，提升预测性能，在线和离线技术分别使平均绝对误差降低7.49%和14.88%，凸显车载适应在实际场景中的优势。

链接：https://arxiv.org/abs/2607.09400

机构：FZI Research Center for Information Technology, University of Tübingen Germany（弗赖堡大学信息科技研究中心）

作者：Avik Bhatnagar, Anton Paule, Tobias Schuermann, Sebastian Reiter, Oliver Bringmann

英文摘要： Adaptive power management in Electric Vehicles (EVs) requires accurate power prediction. Although deep learning models have emerged as highly effective for time-series forecasting in this domain, their performance is prone to degradation when exposed to data with distributions different from the training data. We introduce a novel approach that enables on-device learning in resource-constrained EV systems to continuously adapt pretrained battery prediction models to new, unseen data. We leverage existing pretrained models by transforming them into adaptable versions that retain critical hyperparameter knowledge from their initial training. We comprehensively investigate both online and offline model adaptation strategies. Our results demonstrate significant improvements in forecasting performance across various models and time horizons, achieving mean absolute error reductions of up to 7.49\% and 14.88\% with online and offline adaptation techniques, respectively. This study highlights the substantial benefit of on-device adaptation, resulting in enhanced battery power predictions than unadapted model deployments in real-world EV scenarios.

AI 总结：研究大语言模型介导监督中规范模糊性问题，引入NL-PAC框架，利用固定模型阈值解码法则定义相关内容，通过有限样本置信界认证风险，在Qwen模型审计中得出特定提示有正证书等结果，该保证有特定局限性。

链接：https://arxiv.org/abs/2607.08961

机构：Özyeğin University（奥泽金大学）

作者：Berkay Anahtarci

英文摘要：Large language models increasingly provide labels, evaluations, and feedback for tasks specified in natural language. When a specification admits multiple readings but the supervision channel does not reveal which is operative, additional labels reduce sampling error without resolving the resulting identification problem. We introduce Natural Language PAC (NL-PAC), a framework that uses a fixed model's thresholded decoding law to define admissible labels and candidate targets. The probability that multiple labels are admissible equals the diameter of the pointwise-admissible target class, and under target-blind supervision every learner incurs worst-case risk of at least half this diameter, at every sample size; the exact randomized minimax risk over this class is attained by a data-independent strategy. Finite-sample confidence bounds make these quantities certifiable from held-out unlabeled inputs. In a frozen Qwen~2.5--3B audit, one prespecified prompt yields a positive model-relative certificate, whereas a paraphrase and exact-rule controls yield zero. A held-out bridge audit finds that supplied candidate reading clauses fail the admissibility condition needed to transfer the certificate to coherent readings. The guarantee is specific to the audited model, prompt, threshold, and input distribution; extending it to human interpretations requires external validation.

AI 总结：研究加法激活引导从聊天到智能体的转移，通过匹配信息设计进行研究，发现转移真实但重新缩放，确定了加法特定机制，定位了重新缩放位置，指出智能体部署对引导拒绝绕过影响不可预测。

链接：https://arxiv.org/abs/2607.09156

作者：Lucas Pinto

英文摘要：Additive activation steering (injecting a scaled residual-stream direction during generation) is calibrated almost entirely in single-turn chat, yet the models it targets are increasingly deployed as tool-using ReAct agents. We present the first systematic chat-to-agent transfer study of additive steering, coupling behavioral measurement with a representation read-out in a matched-information design: the same items rendered as plain chat or as a ReAct tool-use episode, with matched-norm random-direction controls and the transcript re-encoded every turn to exclude KV-cache contamination. Transfer is real but rescaled, and the right description is a dissociation: the injected direction reaches the late layers at near-full strength in every setting and model tested (install-site agent-over-chat ratios 0.83-1.16 across three families), while the behavioral coupling is reset per model and context. On Qwen2.5-7B a refusal bypass vector amplifies in the agent (T = 1.45, CI [1.20, 1.78], N = 300); across a powered uniform-protocol distribution the coupling spans amplification (Gemma-2-9B T = 2.00) to attenuation (Yi-1.5-9B T = 0.43, CI [0.29, 0.60]), with no universal constant and a single clean attenuator against a universal sign. Directional ablation of the same axis does not amplify (T = 0.93, CI including 1) while additive injection amplifies (T = 1.50), a 20.1-point gain difference (CI [13.4, 26.8]) that identifies an additive-specific mechanism. Two pre-registered instruments converge to localize the rescaling to the ReAct format scaffold, before any tool observation, rather than to the observation boundary where a dilution account would predict it. The safety implication is immediate and unpredictable: agentic deployment amplifies steering-based refusal bypass by up to 2.00x on some models while others attenuate, so a deployment cannot assume a given model is safe under additive steering.

AI 总结：研究语言模型中信息分配定律，通过单行中心化恒等式等方法，揭示宏观类别结构与令牌内上下文方差占比，理论上说明权重衰减影响，证明二元类别下限，表明定律在多方面成立及预训练中类别份额变化规律。

链接：https://arxiv.org/abs/2607.09487

机构：NYU Shanghai Leonard N. Stern School of Business, New York University（纽约大学上海纽约大学斯特恩商学院）

作者：Bruno Abrahao

英文摘要： Within-class variance in language-model representations is commonly read as incomplete neural collapse. We argue it is allocated information storage, and that the allocation obeys a law. A one-line centering identity voids a family of simplex equiangular-tight-frame claims, including our own earlier ones; in dimensionless variance shares across 14 models, macro-category structure carries only 4-12% of representational variance and within-token context carries 79-91%, stable across a 100x parameter range. On the theory side, token-level weight decay penalizes a category in proportion to its type count, not its occurrence mass, reducing next-token prediction to an imbalanced K-class problem whose optimum orders category norms by type count. A converse floor, proved for binary categories, forces within-category dispersion to be at least proportional to the conditional mutual information I(token; context | category). The law holds: identity dispersion, not total variance, tracks this information across every tested model and partition, under a model-free estimate and even across models, where one model's information predicts another's dispersion; and over pretraining the category share overshoots, decays, and partially recovers, because the information it must carry never left.

AI 总结：研究指出机器学习模型解释存在准确性与可解释性权衡非根本性的观点，引入罗生门解释范式，提出RashomonLLM工作流程，经实验验证其在多任务中显著优于基线，提升业务性能并奠定消费者信任基础。

链接：https://arxiv.org/abs/2607.09502

机构：Scheller College of Business, Georgia Tech（舍勒商学院，佐治亚理工学院）

作者：Pan Li

英文摘要：Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off. We argue that this trade-off is not fundamental, but an artifact of treating explanation and prediction as separate objectives; when properly coupled, they become complementary, so that equipping a model to explain itself improves, rather than degrades, its accuracy. We introduce the Rashomon Explanation paradigm, which builds a set of faithful, prediction-guiding explanations rather than a single one, and prove that this set is generally non-empty and that explanation fidelity bounds the performance of the models it guides. To explore this set, we propose RashomonLLM, an Explanation-Prediction-Reflection agentic workflow that generates explanations in natural language by iteratively aligning them with predictions, and we prove it converges and recovers the full set. Across customer-churn classification, clinical survival regression, and industrial click-through prediction on large-scale live-streaming logs, RashomonLLM significantly outperforms state-of-the-art prediction and XAI baselines on both accuracy and explanation quality, with gains driven by explanation fidelity and robust to distribution shifts, temporal splits, and seeds. Our framework thus advances business performance while laying the groundwork for consumer trust.