机器学习学术速递[6.19]

AI 总结：通过精确最小二乘线性近似，测量训练后 Transformer 各前馈块的线性可恢复性，发现其高度异质且非单调，是学习得到的属性而非架构决定，并可用于压缩和诊断。

链接：https://arxiv.org/abs/2606.19379

机构：Independent Research（独立研究）

作者：Stuart Whipp

英文摘要：Transformer feed-forward networks (FFNs) are often treated as nonlinear stores of computation, yet how nonlinear a trained FFN block actually is has rarely been measured. We treat each FFN as a position-wise input-to-output map and split it into the exact least-squares linear approximation plus a residual. The held-out variance the closed-form linear map explains defines a block's linear recoverability (R^2_lin), an optimiser-free measure of its linearity. Across all twelve blocks of GPT-2, Pythia-160m, and llama-160m, R^2_lin is highly heterogeneous and non-monotone with depth, ranging from near-linear (>0.99) to strongly nonlinear (<0.3) between adjacent blocks, and is not set by the activation function: same-width GELU models GPT-2 and Pythia-160m have sharply different profiles, so recoverability is a learned property of individual trained blocks, not an architectural one. A low-rank bilinear probe of the residual recovers only a few points of R^2, with gain uncorrelated with residual nonlinearity: the unrecovered computation is not a single position-wise product but higher-order or distributed structure. The measurement also serves as a targeted compression signal: recoverable blocks admit large single-layer replacements (GPT-2's early FFN at 8x fewer parameters for +0.77 perplexity), while low-recoverability blocks flag where this is unsafe. It further exposes a methodological pitfall: trained linear baselines can badly under-converge on ill-conditioned transformer activations, so we report the exact closed-form least-squares ceiling throughout.

AI 总结：提出概念流模型（CFM），用层次化概念决策树替代扁平瓶颈，通过逐步缩小预测范围减少信息泄露，在保持预测性能的同时提升可解释性。

链接：https://arxiv.org/abs/2606.19489

机构：Fraunhofer Institute for Open Communication Systems（弗劳恩霍夫开放通信系统研究所）； Freie Universität Berlin（柏林自由大学）

作者：Ya Wang, Adrian Paschke

英文摘要：Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space. Recent approaches leverage vision-language models to generate concept embeddings, reducing the need for manual concept annotations. However, these models suffer from a critical limitation: as the number of concepts approaches the embedding dimension, information leakage increases, enabling the model to exploit spurious or semantically irrelevant correlations and undermining interpretability. In this work, we propose Concept Flow Models (CFMs), which replace the flat bottleneck with a hierarchical, concept-driven decision tree. Each internal node in the hierarchy focuses on a localized subset of discriminative concepts, progressively narrowing the prediction scope. Our framework constructs decision hierarchies from visual embeddings, distributes semantic concepts at each hierarchy level, and trains differentiable concept weights through probabilistic tree traversal. Extensive experiments on diverse benchmarks demonstrate that CFMs match the predictive performance of flat CBMs, while substantially mitigating information leakage by reducing effective concept usage. Furthermore, CFMs yield stepwise decision flows that enable transparent and auditable model reasoning with hierarchical class structures.

AI 总结：本文证明链式思维Transformer能以多对数开销高效模拟Word RAM算法，包括排序和Dijkstra算法，优于模拟图灵机的二次开销。

链接：https://arxiv.org/abs/2606.19697

机构：Allen Institute for AI（艾伦人工智能研究所）； ETH Zürich（苏黎世联邦理工学院）

作者：Yanhong Li, Anej Svete, Ashish Sabharwal, William Merrill

英文摘要：The increasing popularity of \emph{reasoning} models -- language models that output a series of reasoning or thought tokens before producing an answer -- is justified, in part, by theoretical results showing that chain-of-thought (CoT) transformers can simulate Turing machines, and thus perform arbitrary computation. However, the Turing machine, while suitable for complexity-theoretic analysis, is not convenient, intuitive, or efficient for discussing algorithms. Algorithms are typically designed and analyzed at a higher level of abstraction, captured by the \emph{Word RAM} model with random-access memory and unit-cost operations on $\bigO(\log n)$-bit words. As a result, Word RAM algorithms can be substantially more efficient than their Turing machine counterparts, raising the question: \emph{Can CoT transformers efficiently simulate Word RAM algorithms?} For instance, can they sort $n$ items in $\bigO(n \log n)$ steps or run Dijkstra's algorithm in $\bigO(E + V \log V)$ steps? We answer affirmatively, up to poly-logarithmic overhead. We first establish this for finite-precision transformers with poly-logarithmic width and rightmost unique hard attention, then strengthen the result to two more practical settings with finite width and log-precision: \emph{continuous} CoT, where reasoning takes the form of vectors rather than tokens, and a \emph{hybrid} architecture in which transformer layers sit atop a recurrent (linear RNN) layer. In all three cases, we find that CoT \emph{can} efficiently simulate any Word RAM algorithm with only a poly-logarithmic overhead in $n$. This overhead reduces to log-square when the Word RAM has a ``flat'' instruction set, and only logarithmic for multiplication-free flat instructions -- in stark contrast to known CoT simulations of Turing machines, which require quadratic overhead over Word RAM.

AI 总结：提出物理信息广度学习系统（PIBLS），通过无反向传播的最小二乘优化高效求解线性和非线性偏微分方程，比传统PINN快1-3个数量级且精度更高。

链接：https://arxiv.org/abs/2606.19754

机构：School of Computer Science and Engineering, South China University of Technology（华南理工大学计算机科学与工程学院）； Peng Cheng Laboratory（鹏城实验室）； School of Future Technology, South China University of Technology（华南理工大学未来技术学院）； School of Computer Science and Technology, Guangdong University of Technology（广东工业大学计算机科学与技术学院）； Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University（香港理工大学工业及系统工程学系）

作者：Zhiwen Yu, Derong Yang, Liujian Zhang, Kaixiang Yang, Peilin Zhan, Jianmin Lv, Jane You, C. L. Philip Chen

英文摘要：Partial differential equations (PDEs) play a central role in modeling complex physical, biological, and engineering systems. While traditional numerical solvers are robust, they often incur prohibitive computational costs due to mesh dependencies, whereas recent Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative but frequently suffer from slow convergence and optimization instability. To bridge this gap, this article proposes the Physics-Informed Broad Learning System (PIBLS), a novel backpropagation-free framework that reformulates PDE solving as a direct least-squares optimization. We improved an algorithm within this framework to handle nonlinear PDEs efficiently and provide a rigorous mathematical proof establishing the universal approximation property of PIBLS for these equations. Experiments on linear and nonlinear PDEs demonstrate that PIBLS is one to three orders of magnitude faster than conventional PINNs while achieving significantly higher solution accuracy. This framework provides a computationally efficient paradigm for scientific machine learning, offering a practical, high-speed alternative for real-time simulation and design optimization tasks.

AI 总结：提出在神经加性模型和神经基础模型中引入特征选择机制，通过特征选择层减少计算开销，并支持高维数据中的特征交互学习，性能优于或持平于现有GAM方法。

链接：https://arxiv.org/abs/2606.19850

机构：Yokohama National University, Kanagawa, Japan（神户国立大学，神奈川，日本）

作者：Yasutoshi Kishimoto, Kota Yamanishi, Takuya Matsuda, Shinichi Shirakawa

英文摘要：Deep neural networks (DNNs) exhibit attractive performance in various fields but often suffer from low interpretability. The neural additive model (NAM) and its variant called the neural basis model (NBM) use neural networks (NNs) as nonlinear shape functions in generalized additive models (GAMs). Both models are highly interpretable and exhibit good performance and flexibility for NN training. NAM and NBM can provide and visualize the contribution of each feature to the prediction owing to GAM-based architectures. However, when using two-input NNs to consider feature interactions or when applying them to high-dimensional datasets, training NAM and NBM becomes intractable due to the increase in the computational resources required. This paper proposes incorporating the feature selection mechanism into NAM and NBM to resolve computational bottlenecks. We introduce the feature selection layer in both models and update the selection weights during training. Our method is simple and can reduce computational costs and model sizes compared to vanilla NAM and NBM. In addition, it enables us to use two-input NNs even in high-dimensional datasets and capture feature interactions. We demonstrate that the proposed models are computationally efficient compared to vanilla NAM and NBM, and they exhibit better or comparable performance with state-of-the-art GAMs.

AI 总结：提出SEA-PINN架构，通过挤压-激励式注意力机制动态调整神经元重要性，实现稳定初始化，在20个基准问题中17个方差极小，无需傅里叶嵌入或周期激活即可达到与TSA-PINN相当的精度，并可作为轻量插件提升其他PINN性能。

链接：https://arxiv.org/abs/2606.19853

机构： Key Laboratory of Quark and Lepton Physics (MOE) & Institute of Particle Physics, Central China Normal University（华中师范大学夸克与轻子物理教育部重点实验室及粒子物理研究所）； Artificial Intelligence and Computational Physics Research Center, Central China Normal University（华中师范大学人工智能与计算物理研究中心）； Key Laboratory of Nuclear Physics and Ion-beam Application (MOE) & Institute of Modern Physics, Fudan University（复旦大学核物理与离子束应用教育部重点实验室及现代物理研究所）； Shanghai Research Center for Theoretical Nuclear Physics, NSFC and Fudan University（国家自然科学基金委员会-复旦大学上海理论核物理研究中心）； Northwest Institute of Nuclear Technology（西北核技术研究所）

作者：Yun-Fei Song, Long-Gang Pang, Fu-Peng Li, Jun-Jie Zhang

英文摘要：We introduce SEA-PINN, a novel architecture that incorporates a Squeeze-Excitation-like attention mechanism into physics-informed neural networks to dynamically recalibrate the importance of neurons across layers. A key feature of SEA-PINN is its highly stable initialization. On 17 out of 20 benchmark problems, SEA-PINN exhibit nearly negligible variance and significantly reduced initial loss, establishing a quasi-deterministic and favorable starting point for optimization. Notably, without employing Fourier feature embeddings or periodic activation functions, SEA-PINN attained competitive accuracy (83\% vs. 90\% improvement relative to FNN-PINN on the high-frequency case 7) as compared with TSA-PINN-a model specifically engineered for high-frequency problems via learnable frequencies in sinusoidal activations. Furthermore, integrating SEA-PINN into TSA-PINN boosted performance by 42.49\%. These results underscore SEA-PINN as a lightweight plug-in module that enhances nonlinear representation power, promotes more robust and efficient convergence, and strengthens the overall reliability of physics-informed learning.

AI 总结：研究发现组合性仅在特定稀疏网络和特定深度区间涌现，提出基于相似性的剪枝和深度预测方法，并用理论框架解释原因。

链接：https://arxiv.org/abs/2606.19941

机构：National University of Singapore（新加坡国立大学）； University of Twente（特温特大学）

作者：Dat H. Do, Rushi Shah, Duc V. Le, Dianbo Liu

英文摘要：Compositionality is believed to be the foundation for generalization, enabling models to reuse meaningful primitives in novel combinations. Yet, models trained with standard gradient-based optimization rarely, and often only weakly, exhibit compositional internal structure, and it remains unclear how or why such compositionality forms. In this work, we show that compositionality emerges in a narrow connectivity-depth sweet spot. Along the connectivity axis, compositionality only appears in some specifically sparse networks, heavily depends on which connections remain rather than on weights' sparsity alone. Along the depth axis, compositionality emerges within a narrow, target-dependent regime, peaking at specific depths, while both shallower and deeper networks fail. When either the depth or connectivity condition is violated, gradient descent silently converges to fractured solutions rather than compositional ones. To discover and exploit this emergence, we introduce (i) similarity-based pruning (SP) to recover compositional connectivity and (ii) a heuristic depth predictor to estimate where compositionality is most likely to appear. Finally, we support these empirical findings with a theoretical framework based on compositional sparsity, volume-ratio arguments, and feature-interference bounds, explaining why compositional solutions are reachable only in a narrow depth-connectivity regime.

AI 总结：提出Kolmogorov-Arnold储层计算（KARC），用显式基函数展开替代储层，结合KAN的表达能力和储层计算的闭式训练，在偏微分方程等基准上优于现有方法。

链接：https://arxiv.org/abs/2606.19984

机构：Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China（电子科技大学基础与前沿科学研究所）； Potsdam Institute for Climate Impact Research（波茨坦气候影响研究所）； Department of Physics, Humboldt University Berlin（柏林洪堡大学物理系）； Research Institute of Intelligent Complex Systems, Fudan University（复旦大学智能复杂系统研究所）； School of Physics, University of Electronic Science and Technology of China（电子科技大学物理学院）； Key Laboratory of Quantum Physics and Photonic Quantum Information, Ministry of Education, University of Electronic Science and Technology of China（电子科技大学教育部量子物理与光子量子信息重点实验室）； Non-classical Information Science Basic Discipline Research Center of Sichuan Province, University of Electronic Science and Technology of China（电子科技大学四川省非经典信息科学基础学科研究中心）

作者：Juntian Huang, Jurgen Kurths, Ying Tang

英文摘要：Reservoir computing offers a lightweight framework for forecasting dynamical systems but may struggle to capture long-range dependencies due to limited representational capacity. Conventional reservoir computing recurrently uses trainable reservoirs with hyperparameter sensitivity, while the next-generation reservoir computing removes recurrence at the cost of rapidly growing feature dimensions. Here, we develop Kolmogorov-Arnold Reservoir Computing (KARC), which replaces reservoirs with explicit basis-function expansions inspired by the Kolmogorov-Arnold representation theorem. We rigorously show that KARC is a lightweight design of Kolmogorov-Arnold networks (KANs), preserving the potential expressive capacity of KANs while admitting efficient closed-form training of reservoir computing. At comparable cost, KARC outperforms existing reservoir computing methods on challenging benchmarks including partial differential equations. It can also be integrated with generative diffusion models for text-to-image generation. This work thus establishes a principled bridge between reservoir computing and KANs, enabling efficient and high-fidelity dynamical system forecasting.

AI 总结：提出SLiR方法，通过斜率参数化和平移过程生成任意激活函数的线性松弛，在保持正确性的同时实现高效优化，验证属性数量比现有方法多7.8倍。

链接：https://arxiv.org/abs/2606.20292

机构：Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）； Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）

作者：Philipp Kern, László Antal, Erika Ábráham, Carsten Sinz

英文摘要：The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification methods rely on optimizable linear relaxations of activation functions. However, existing techniques depend on hand-crafted relaxations for each activation function. Extension to state-of-the-art activation functions therefore requires substantial manual effort. In contrast, our approach SLiR (Shifting-based Linear Relaxations) is broadly applicable, requiring only a Lipschitz constant or a set of critical points. SLiR parameterizes relaxations by their slope and computes the corresponding offset via a shifting procedure that ensures sound upper and lower bounds over the input domain, enabling efficient optimization while maintaining correctness. Our experiments show that SLiR produces tight relaxations across a wide range of practical activation functions and enables verification of up to 7.8x more properties compared to state-of-the-art methods.

AI 总结：针对物理信息神经网络训练不稳定、超参数敏感的问题，提出基于进化算法的两阶段优化策略，先低保真筛选再全训练，在三个PDE问题上显著降低误差。

链接：https://arxiv.org/abs/2606.20442

机构：HSE University（高等经济大学）； AXXX

作者：Fedor Buzaev (1), Dmitry Efremenko (1), Egor Bugaev (1), Andrei Ermakov (1 and 2), Denis Derkach (1), Daria Pugacheva (1 and 2), Fedor Ratnikov (1) ((1) HSE University, (2) AXXX)

英文摘要：Physics-Informed Neural Networks (PINNs) solve Partial Differential Equations (PDEs) by embedding physical laws into neural network training. However, their performance suffers from unstable convergence, training plateaus, and strong sensitivity to architectural and optimization hyperparameters due to the highly non-convex and multi-term structure of the physics-informed loss. In this setting, the outer-loop hyperparameter search is a noisy and black-box optimization problem over heterogeneous parameters, where classical local or gradient-based strategies are easily trapped in suboptimal regions. Evolutionary algorithms, with their population-based exploration and ability to handle mixed, non-differentiable search spaces, provide a more robust mechanism for discovering promising configurations. We propose and investigate a two-stage approach based on evolutionary algorithms that combines exploration and exploitation parts of PINNs training to improve solution accuracy and robustness under fixed computational budgets. In the first stage, we perform low-fidelity training runs with truncated epochs to rapidly screen candidate configurations, treating hyperparameter selection as a black-box outer-loop problem. In the second stage, only the most promising candidates are fully trained with standard gradient-based optimizers to refine the solution. Evaluated on three popular problems, namely Advection, Klein-Gordon and Helmholtz equations, our method consistently outperforms standard training and achieves significantly lower mean error within constrained computational resources.

AI 总结：提出李代数注意力机制，将token定义为矩阵李群元素，利用相对位姿的李代数范数作为注意力分数，无需学习核函数或表示论工具，适用于仿射全帧群等非紧致非阿贝尔群。

链接：https://arxiv.org/abs/2606.20547

机构：New Jersey Institute of Technology（新泽西理工学院）

作者：Przemyslaw Musialski

英文摘要：We place the attention token on the group: a token is an element $g_i$ of a matrix Lie group $G$ -- a bare transformation, with no feature payload and no external action $\rho(g)$ carrying it. To our knowledge this is the first attention construction whose tokens are bare matrix Lie group elements: their score is the closed-form algebra norm of the relative pose rather than a learned kernel, and it reaches the affine full-frame groups that every irrep- or surjective-exp-based method must exclude. We call it Lie-Algebra Attention. Once tokens are group elements, the rest follows with none of the usual representation-theoretic machinery. The relative geometry of a pair is canonical, $g_i^{-1} g_j$, so the pairwise invariant $w_{ij} = \log(g_i^{-1} g_j)$ is intrinsic rather than designed; equivariance under the diagonal $G$-action is tautological, and the cocycle condition holds automatically. The attention score is the negative squared algebra norm, $s_{ij} = -\|\log(g_i^{-1} g_j)\|_\lambda^2/\tau$: the canonical proximity kernel under a block-weighted Frobenius inner product, with no irreducible representations, spherical harmonics, Clebsch-Gordan products, or learned kernel. The construction applies to any matrix Lie group on a chosen logarithm chart containing the relative poses, including the non-compact non-abelian affine groups with scale and shear that no vector-token attention method reaches: neither the irrep tradition nor surjective-exp methods. Three sequence-completion experiments, on SE(2), SO(3), and Aff(2), bear this out: the closed-form score matches a learned MLP kernel on the same invariant and outperforms it on SE(2), using 50 to 80x fewer score parameters, while a vector-token baseline breaks invariance by five to twelve orders of magnitude.

AI 总结：针对潜在动作模型中固定容量瓶颈导致的权衡问题，提出FlexLAM，通过嵌套dropout实现变长潜在动作，在不增加架构或损失的情况下，在稀缺标签和低回报任务中优于固定容量模型，并支持推理时调整令牌预算。

链接：https://arxiv.org/abs/2606.19408

机构：University of Tsukuba（筑波大学）； The University of Tokyo（东京大学）

作者：Takanori Yoshimoto, Yang Hu, Naruya Kondo, Tatsuya Matsushima

英文摘要： Latent actions provide a compact interface between action-free video and downstream decision-making, yet existing Latent Action Models (LAMs) force every transition through a fixed-capacity bottleneck. We identify a bottleneck trade-off: overly tight codes can discard transition cues needed for action alignment, while overly loose codes preserve additional transition variation that must be resolved when alignment labels are scarce or narrowly distributed. FlexLAM replaces this fixed capacity with variable-length latent actions trained by nested dropout, yielding prefix-valid codes that capture compact transition structure first and add detail only when needed, without new architectures or losses. A single FlexLAM matches or surpasses separately trained fixed-capacity LAMs at every evaluated token budget under standard scarce-label supervision and under a low-return single-task alignment stress test, indicating that FlexLAM is not merely adjustable at inference time but learns a better latent-action interface at the same token budgets. The same model supports inference-time token-budget adjustment without retraining, and FlexLAM improves Ego4D transition reconstruction. These results suggest that variable-length latent actions are an architecture-free, drop-in upgrade to the fixed-capacity bottleneck in latent action models, latent-action world models, and video-pretrained action interfaces.

AI 总结：提出3D-DLP模型，通过自监督学习将场景级RGB-D或体素观测分解为3D潜在粒子，每个粒子编码解耦属性，实现可解释的逐粒子分割图，并支持场景操控和下游机器人操作。

链接：https://arxiv.org/abs/2606.19451

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

作者：Ellina Zhang, Madhaven Iyengar, Amir Zadeh, Chuan Li, Deepak Pathak, David Held, Tal Daniel

英文摘要：We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles. Building on the Deep Latent Particles (DLP) framework, each particle encodes disentangled attributes, including 3D keypoint position, bounding box dimensions, and appearance features, and represents a distinct entity in the scene. The model learns interpretable per-particle segmentation maps through an end-to-end self-supervised reconstruction objective. We demonstrate on both simulated and real-world datasets that the learned latent space is interpretable and controllable: by manipulating particle positions and decoding, we can generate novel scene configurations. Furthermore, we show that leveraging these compact 3D latent particles for downstream robotic manipulation improves performance over baselines that either lack explicit 3D information or rely on memory-intensive dense 3D inputs without object-centric structure. Code and videos are available at this https URL.

AI 总结：通过持续同调分析激活空间拓扑，发现对齐过程中拓扑重组主要发生在训练早期，且不同对齐目标产生可区分的拓扑轨迹。

链接：https://arxiv.org/abs/2606.19542

机构：Imperial College London（伦敦帝国学院）

作者：Naman Malhotra, Jay Ambadkar, Abhinav Gupta, Kushal Kasivel, Abbas Schwarz, Kamillo Ferry, Anthea Monod

英文摘要：Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process. We study alignment dynamics using persistent homology by tracking the topology of activation spaces throughout fine-tuning. Across four transformer language models ranging from 1B to 7B parameters and three alignment objectives corresponding to helpful, harmless, and mixed training data, we find that the majority of topological reorganization occurs during the earliest stages of training. A dense checkpoint analysis reveals a transient peak in topological activity followed by rapid stabilization. We further show that different alignment objectives induce distinguishable topological trajectories, while instruction-tuned and pretrained models exhibit qualitatively different patterns of evolution. Our results suggest that persistent homology provides a complementary perspective on alignment, revealing representation-level changes that are not apparent from behavioral metrics alone.

AI 总结：提出从低层测量数据中直接学习高层结构因果模型的方法，利用低秩因果发现假设，证明低秩图观测诱导的潜变量形成因果抽象，并给出可辨识性结果及实用学习目标。

链接：https://arxiv.org/abs/2606.19594

机构：Mila - Quebec AI Institute（魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）

作者：Théo Saulus, Simon Lacoste-Julien, Dhanya Sridhar

英文摘要：Causal abstractions formalize when a high-level structural causal model (SCM) captures the interventional behavior of a lower-level SCM. Existing applications of this notion largely follow a hypothesis-testing paradigm: an expert proposes a candidate high-level model and then evaluates if the low-level system implements it. We study the complementary problem of learning a high-level model directly from low-level measurements. Our contributions leverage hypotheses from low-rank causal discovery, and can be summarized as follows: (1) we show that observations generated by a low-rank graph induce latents that form a causal abstraction, (2) we provide identifiability results about these latents, and (3) we propose a practical objective to learn this high-level SCM.

AI 总结：提出自适应分箱方法，通过特征级粗到细课程学习动态优化离散化，结合类别重建与顺序监督，在医疗表格数据上提升自监督学习性能。

链接：https://arxiv.org/abs/2606.19827

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

作者：Daehwan Kim, Haejun Chung, Ikbeom Jang

英文摘要：Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at this https URL.

AI 总结：提出SL-S4Wave框架，结合对比学习与基于结构化状态空间模型的编码器，通过多尺度子核全局卷积捕获多通道生理波形的局部和长程依赖，在心律失常检测等任务中优于现有方法。

链接：https://arxiv.org/abs/2606.19888

机构：Massachusetts Institute of Technology（麻省理工学院）； OpenEvidence, USA（OpenEvidence公司）； New York University（纽约大学）； Xi’an Jiaotong University（西安交通大学）； University of Toronto（多伦多大学）； Emory University（埃默里大学）

作者：Feng Wu, Harsh Deep, Eric Lehman, Sanyam Kapoor, Guoshuai Zhao, Rahul Krishnan, Gari Clifford, Li-wei H Lehman

英文摘要：Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, multichannel signal complexity, inherent noise, and limited labeled data. While recent self-supervised learning (SSL) methods, based on various encoder architectures such as convolutional neural networks, have been proposed to learn representations from unlabeled data, they often fall short in capturing long-range dependencies and noise-invariant features. Structured state space models (S4) excel at long-sequence modeling, but existing S4 architectures fail to capture the unique characteristics of multichannel physiological waveforms. In this work, we propose SL-S4Wave, a self-supervised learning framework that combines contrastive learning with a tailored encoder built on structured state space models. The encoder incorporates multi-layer global convolution using multiscale subkernels, enabling the capture of both fine-grained local patterns and long-range temporal dependencies in noisy, high-resolution multichannel waveforms. Extensive experiments on real-world datasets demonstrate that SL-S4Wave (1) consistently outperforms state-of-the-art supervised and self-supervised baselines in a challenging arrhythmia detection task, (2) achieves high performance with significantly fewer labeled examples, showcasing strong label efficiency, and (3) maintains robust performance on long waveform segments, highlighting its capacity to model complex temporal dynamics in long sequences that most existing approaches fail to efficiently model, and (4) transfers effectively to unseen arrhythmia types, underscoring its robust cross-domain generalization. We additionally evaluate SL-S4Wave on multiple EEG tasks, achieving superior performance over strong baselines, demonstrating generalizability of our approach beyond cardiac waveforms.

AI 总结：提出两种多模态对比学习架构MELT和SALT，通过位置绑定整合未配对地理数据，在四个下游任务中匹配最强双模态基线SATCLIP，但增加模态数未持续提升性能，表明位置编码器是主要瓶颈。

链接：https://arxiv.org/abs/2606.20167

机构：Computational Methods Lab, HafenCity University Hamburg（汉堡港城大学计算方法实验室）； Dept. of Operations & Technology, Technical University of Munich（慕尼黑工业大学运营与技术系；海尔布隆数据科学中心；慕尼黑数据科学研究所）； Heilbronn Data Science Center（波恩大学大地测量与地理信息研究所）； Munich Data Science Institute； Institute of Geodesy and Geoinformation, University of Bonn

作者：Jonathan Hecht, Lukas Arzoumanidis, Ziyue Li, Youness Dehbi

英文摘要：Spatial prediction tasks are often limited by a lack of high-quality labelled ground-truth observations. To overcome this challenge, self-supervised pre-training is a possible solution, with contrastive learning dominant for location encoders. Those approaches usually align geographic coordinates with just one additional modality. We propose two multimodal contrastive learning architectures: Multimodal Embedding via Location Tying (MELT) and Sequential Alternating Location Training (SALT). These architectures expand this framework beyond two modalities by utilising unpaired geospatial data. Both methods are technically viable and match the performance of the strongest two-modality baseline (SATCLIP) across four downstream tasks. However, increasing the number of modalities does not consistently improve performance, suggesting that the chosen location encoder is the main limitation - the contrastive objective reaches its peak early, regardless of modality diversity or pre-training volume. MELT provides more stable training than SALT and presents a stronger foundation for future scaling.

AI 总结： 提出一种结合自我对弈强化学习与少量人类演示的正则化方法，仅用30分钟人类数据即可训练出与人类协调的驾驶策略，训练时间仅15小时。

链接：https://arxiv.org/abs/2606.19370

机构：NYU Tandon School of Engineering（纽约大学坦登工程学院）； NYU Courant（纽约大学库朗数学科学研究所）； Princeton University（普林斯顿大学）； Centre for Robotics, Mines Paris（巴黎矿业大学机器人中心）； Valeo（法雷奥）

作者：Daphne Cornelisse, Julian Hunt, Zixu Zhang, Waël Doulazmi, Kevin Joseph, Jaime Fernández Fisac, Eugene Vinitsky

英文摘要：Self-play reinforcement learning has recently emerged as a way to train driving policies without any human data. It uses cheap, large-scale simulations to substitute expensive, large-scale human driving demonstrations. A key limitation of this approach is that policies trained through pure self-play can learn effective but alien driving conventions incompatible with people. Previous works attempt to mitigate such behavioral misalignments through extensive reward engineering and domain randomization, which are brittle and labor-intensive. Instead of completely discarding human demonstrations, our method treats them as a regularization objective on top of a minimal safe goal-reaching reward. Like the spice in a good stew, we find that a little human data goes a long way: our method uses only 30 minutes of human demonstrations, 2500x fewer than comparable imitation learning approaches. Resulting policies coordinate with held-out human trajectories and complete training in 15 hours on a single consumer-grade GPU. Videos and full source code are available at this https URL.

AI 总结：研究利用序列模型的上下文学习能力作为即时无更新世界模型，以消除传统内在好奇心方法中梯度下降的计算瓶颈，理论证明在非时间设置下可渐近收敛到真实学习进度。

链接：https://arxiv.org/abs/2606.19476

机构：Google – Paradigms of Intelligence Team（Google – 智能范式团队）； Google DeepMind

作者：Eric Elmoznino, Sangnie Bhardwaj, Johannes von Oswald, Rajai Nasser, Blaise Agüera y Arcas, João Sacramento, Rif A. Saurous, Guillaume Lajoie

英文摘要：Effective machine learning depends not only on how we model data, but also on what data we choose to collect. While large sequence models have revolutionized data modeling, the problem of automated data selection, or "intrinsic curiosity", remains a significant challenge. Classic approaches incentivize exploration by rewarding an agent based on its "learning progress", which measures how much a newly acquired observation improves a world model's predictive ability. However, evaluating these rewards traditionally requires expensive inner loops of gradient descent updates within each trajectory, rendering them computationally impractical at scale. In this work, we investigate whether the emergent in-context learning (ICL) capabilities of sequence models can eliminate this bottleneck by serving as immediate, update-free world models. Specifically, we evaluate whether an exploration policy can be trained to maximize learning progress, using solely the prediction errors and counterfactual context manipulations of an in-context learner. We first prove that in general Markov decision processes, this is in fact impossible in an unbiased way: the resulting intrinsic rewards either suffer from nuisance terms that bias their estimation of true learning progress, or they cannot be implemented using an in-context learner's prediction errors. Conversely, we prove a positive result for a broad subclass of non-temporal settings, encompassing active learning and Bayesian Experimental Design: here, ICL-derived rewards successfully bound and asymptotically converge to the true learning progress. We corroborate our theory with controlled experiments across continuous and symbolic environments, demonstrating that our ICL-driven framework successfully trains curious data-collection policies that explore optimally.

AI 总结：提出MGAR-WIES框架，通过语义图建模、注意力机制和自适应强化学习，解决Web环境中异构动态数据的语义理解与可扩展性问题，在准确率上达到80%。

链接：https://arxiv.org/abs/2606.19690

机构：Infinity Tech Group； Gainwell Technologies； Capital One； Sunnyvale, CA, USA（美国硅谷）； Department of Electronics and Communication Engineering（电子与通信工程系）； Sona College of Technology（Sona科技学院）； Independent Researcher（独立研究员）； Salem, India（印度塞拉姆）

作者：Navin Chhibber, Deepak Singh, Anokh Kishore, Nikita Chawla, K. Anguraj

英文摘要：From the past few years, web intelligent enhancement systems increasingly rely on heterogeneous and dynamic web data to deliver personalized, context-aware services. However, traditional machine learning, deep learning, and reinforcement learning models often struggle with semantic understanding, adaptability, and scalability in continuously evolving web environments. In this research, a Multi-Granular Attention-based Reinforcement Web Intelligent Enhancement System (MGAR-WIES) is proposed to address the challenges by integrating semantic graph modeling, attention mechanisms, and adaptive reinforcement learning. Initially, heterogeneous web data comprising structured, semi-structured and unstructured sources are collected and preprocessed for generating unified feature representations. These representations are transformed into a dynamic semantic graph, where entities and their relationships are modeled by using graph embeddings enhanced by attention mechanisms for capturing both local relevance and global contextual dependencies. Subsequently, an adaptive multi-agent reinforcement learning strategy leverages the attention-aware semantic states to optimize personalized web actions like content recommendation, navigation optimization, and service adaptation. Finally, the continuous online feedback is further integrated to update graph representations and learning policies in real time by ensuring sustained adaptability and performance. The proposed MGAR-WIES acheived better results in terms of accuracy (80%) when compared with existing approaches.

AI 总结：针对帧丢失导致性能下降的问题，提出OnDeFog，将DeFog机制与在线决策变压器结合，通过直接环境交互学习策略，在高丢帧率环境下优于ODT，在低奖励数据集上优于DeFog。

链接：https://arxiv.org/abs/2606.19721

机构：Yokohama National University（横滨国立大学）

作者：Daiki Yotsufuji, Kenta Nishihara, Shoma Shimizu, Kento Uchida, Shinichi Shirakawa

英文摘要：In challenging real-world reinforcement learning applications, communication delays or sensor failures often cause frame dropping, in which the agent cannot receive the dropped states and associated rewards. To address the performance degradation caused by frame dropping, the Decision Transformer under Random Frame Dropping (DeFog) was developed by incorporating additional mechanisms into the decision transformer to tackle frame dropping. Although DeFog can mitigate performance degradation in frame-dropping environments, since DeFog is an offline learning method, it struggles to effectively generalize to novel states not adequately represented in the training dataset. In this study, we propose OnDeFog, which integrates the mechanisms in DeFog with the online decision transformer (ODT), an online reinforcement learning method that learns policies through direct environmental interaction. Comprehensive experimental evaluation demonstrates that our proposed OnDeFog achieves superior performance compared to ODT in environments characterized by high dropping frame rate and outperforms DeFog on datasets containing a large amount of low-reward data.

AI 总结：提出贝叶斯流形课程（BMC）框架，将问题采样建模为流形结构赌博机问题，通过层次任务树和贝叶斯学习引导采样，平衡学习信号、多样性和实用性。

链接：https://arxiv.org/abs/2606.19750

机构：University of California, San Diego（加州大学圣迭戈分校）

作者：Darrien McKenzie, Nicklas Hansen, Xiaolong Wang

英文摘要：Reinforcement learning (RL) is a central approach for improving reasoning capabilities in large language models (LLMs), where training efficiency depends critically on how problems are sampled during optimization. Existing adaptive curriculum learning methods typically prioritize prompts of intermediate difficulty, treating problem selection as a standard bandit problem with independent arms and overlooking the structured, heterogeneous nature of the task space. In this work, we frame problem sampling as a manifold-structured bandit problem with endogenous non-stationarity: problems are related through the model's latent representation space, and sampling decisions can steer how learning signals evolve across that space. To operationalize this perspective, we introduce Bayesian Manifold Curriculum (BMC), a structure-aware framework that organizes problems into a hierarchical task tree and applies Bayesian learning to guide sampling. Empirically, we find that different sampling strategies induce non-trivial tradeoffs between productivity (learning signal), diversity (coverage of the task manifold), and utility (evaluation relevance). These results show that prioritizing difficulty alone is insufficient for strong downstream performance, highlighting the importance of incorporating structure and type-awareness into problem sampling.

AI 总结：研究基于累积前景理论（CPT）的竞争性双边匹配市场多智能体多臂赌博机问题，提出最优遗憾界算法并扩展到对抗性市场。

链接：https://arxiv.org/abs/2606.19883

机构：Indian Institute of Technology Bombay（印度理工学院班加罗尔）

作者：Ananya Kunisetty, Avishek Ghosh

英文摘要：We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model. To capture human preferences, we use cumulative prospect theory (CPT) that weighs the actions of the agent in a nonlinear fashion using a ($\alpha$-Hölder continuous) weight function. CPT has been widely used in behavioral economics and risk sensitive machine learning to emulate human preferences. We analyze the state-of-the-art learning algorithm with CPT weight distorted rewards and obtain a player optimal regret of $\mathcal{O}(K\log T \left(\frac{1}{\Delta}\right)^{2/\alpha})$, where $K$ denotes the number of arms, $T$ is the learning horizon, and $\Delta$ represents (suitably defined) players' minimum preference gap. Noticing the dependence on $\Delta$ to be sub-optimal, we further improve this regret by judiciously selecting the active set of arms during exploration, which removes the dependence on $K$ in the dominant term and achieves an improved (optimal) regret guarantees in the setting where the number of arms $K$ is significantly larger than the number of players $N$. In addition, we consider adversarial markets where the observed rewards of the agents may be corrupted. We propose and analyze algorithms for robust markets with CPT as risk sensitive measure in both settings where the total corruption budget is known and where it is unknown, and establish logarithmic player-optimal regret guarantees in both cases.

AI 总结：提出Connect the Dots框架，通过端到端强化学习训练LLM在长期任务中自我更新上下文并泛化到新领域，实验验证了跨域泛化能力。

链接：https://arxiv.org/abs/2606.20002

机构：Alibaba Group（阿里巴巴集团）

作者：Yanxi Chen, Weijie Shi, Yuexiang Xie, Boyi Hu, Yaliang Li, Bolin Ding, Jingren Zhou

英文摘要： This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuously exploring the environment, learning from its own experiences, and iteratively self-updating its context about the environment, thereby achieving progressively better performance on future tasks conditioned on the updated context. Major components of the CoD framework include: (1) algorithm design and infrastructure for end-to-end reinforcement learning (RL) with long rollout sequences interleaving solve-task and update-context episodes; (2) tasks and environments for incentivizing and eliciting the targeted meta-capability in LLMs during training, as well as for faithfully measuring progress during evaluation. We present proof-of-concept implementations of the CoD framework, including a GRPO-style RL algorithm with fine-grained credit assignment, as well as tasks and environments tailored to the targeted meta-capability (rather than domain-specific LLM capabilities or standard task-by-task RL). Empirical results validate the efficacy of end-to-end RL training in the CoD setting, and demonstrate the potential for out-of-distribution generalization -- within the training domains, across different domains, and from CoD to Ralph-loop settings -- of the elicited meta-capability. Our investigation of CoD connects several lines of prior works, and opens up new opportunities for advancing LLMs and AI agents. To facilitate further research and applications, we release our implementations at \url{ this https URL }.

AI 总结：提出VIMPO方法，通过KL正则化强化学习的最优条件导出策略隐含值函数，无需训练评论家，实现细粒度信用分配，在数学推理基准上优于GRPO。

链接：https://arxiv.org/abs/2606.20008

机构：UC Berkeley（加州大学伯克利分校）； Yale University（耶鲁大学）

作者：Zhewei Kang, Aosong Feng, Sergey Levine, Dawn Song, Xuandong Zhao

英文摘要：Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment. Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token. Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability. We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from the optimality conditions of KL-regularized reinforcement learning. For autoregressive generation, the resulting value recurrence can be written in terms of policy-reference log-ratios and anchored by the terminal condition that no future reward remains at the end of a trajectory. This gives a simple value loss that incorporates outcome-level verifiable rewards without training a critic. The same derivation also yields a critic-free actor advantage, allowing VIMPO to separate reward incorporation through the value loss from policy improvement through a PPO-style actor update. On mathematical RLVR benchmarks, VIMPO improves over GRPO across MATH-500, AIME 2024, AIME 2025, and OlympiadBench, with especially larger gains on competition-style evaluations. Under noisy rewards, VIMPO retains a consistent advantage over GRPO, suggesting that policy-implied value optimization can provide finer credit assignment while preserving the practical simplicity of critic-free training.

AI 总结：提出LLM作为中央策略控制器选择RL技能策略的层次化架构，在2v2对抗环境中达到与手工BT相当的胜率，且被感知为最类人。

链接：https://arxiv.org/abs/2606.20014

机构：Electronic Arts； KTH Royal Institute of Technology（皇家理工学院）

作者：Jannik Hösch, Alessandro Sestini, Florian Fuchs, Amir Baghi, Joakim Bergdahl, Konrad Tollmar, Jean-Philippe Barrette-LaPierre, Linus Gisslén

英文摘要：Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and \emph{``Flat''} RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

AI 总结：提出传感器运动世界模型（SMWM），通过逆动力学正则化端到端训练潜空间世界模型，防止表示崩溃并学习与行动对齐的紧凑表示，在2D和3D控制任务中实现竞争性规划性能。

链接：https://arxiv.org/abs/2606.20104

机构：Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； Department of Computer Science, Brown University（布朗大学计算机科学系）； ELLIS Institute（ELLIS研究所）； ETH Zürich（苏黎世联邦理工学院）

作者：Petr Ivashkov, Randall Balestriero, Bernhard Schölkopf

英文摘要： Perception for action suggests that representations of the world should be shaped not by visual fidelity alone, but by their relevance for actions. At the same time, latent JEPA-style world models advocate learning compact predictive states from high-dimensional observations to facilitate the prediction of future states, but end-to-end training of these models is nontrivial because representations may collapse if our only goal is to construct a latent state that is easy to predict. We introduce a sensorimotor world model (SMWM): a latent world model trained end-to-end with inverse dynamics regularization. This single regularizer addresses both issues: it prevents representation collapse and induces action-aligned representations. By forcing latent states to preserve information about the action underlying a transition, it biases the model toward the controllable degrees of freedom of the environment while discarding uncontrollable distractors. This yields stable latent world models trained from offline, reward-free trajectories, without frozen encoders, exponential moving averages, or complex latent regularizers. Empirically, SMWM learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.

AI 总结：提出一种基于分位数的集成方法，无需计数即可在有限时域MDP中实现最优方差依赖的遗憾界，为强化学习中的集成探索提供理论依据。

链接：https://arxiv.org/abs/2606.20107

机构：Google Research（谷歌研究院）

作者：Asaf Cassel, Aviv Rosenberg

英文摘要：Optimal Reinforcement Learning (RL) algorithms typically rely on carefully constructed count-based uncertainty estimates to drive exploration. Although theoretically sound, such estimates are hard to compute in practical settings and therefore offer limited insight for designing exploration heuristics. Meanwhile, ensembling has emerged as a practical approach, but remains without theoretical justification. Building on a recent ensemble-based method for Multi-Armed Bandits, we propose a quantile-based ensemble method for finite-horizon Markov Decision Processes (MDPs). Our simple count-free approach achieves optimal variance-dependent regret bounds, providing theoretical grounding for ensemble-based exploration in RL.

AI 总结：针对直接优势估计（DAE）在部分可观测域和高维观测下的局限性，本文扩展其理论框架并引入离散潜动态模型降低计算复杂度，在Arcade学习环境中验证了DAE的可扩展性和样本效率。

链接：https://arxiv.org/abs/2606.20411

作者：Hsiao-Ru Pan, Bernhard Schölkopf

英文摘要：Direct Advantage Estimation (DAE) has been shown to improve the sample efficiency of deep reinforcement learning algorithms. However, its reliance on full environment observability limits its applicability in realistic settings, and its requirement to model transition probabilities incurs substantial computational overhead for high-dimensional observations. In the present work, we address both limitations. First, we extend the theoretical framework of DAE to partially observable domains with minimal modifications. Second, we reduce its computational complexity by introducing discrete latent dynamics models that efficiently approximate transition probabilities. We evaluate our approach on the Arcade Learning Environment and find that DAE scales effectively with function approximator capacity while retaining high sample efficiency.

AI 总结：针对批量式轨迹蒸馏中跨批次证据缺失问题，提出边际优势累积（MAA）方法，通过差分信号构造、指数移动平均累积和语义身份合并，在16个设置中14个取得最佳结果，优化阶段token消耗减少约75%。

链接：https://arxiv.org/abs/2606.20475

机构：Alibaba International Digital Commerce Group（阿里巴巴国际数字商业集团）

作者：Mingyu Yang, Keye Zheng, Congchao Cheng, Yujie Liu, Xingkang Lu, Fan Jiang, Yefei Zheng

英文摘要：In batch-style trace distillation, the same memory operation may receive contradictory feedback across different batches. Existing methods lack a cross-batch, operation-level evidence accumulation mechanism, making it impossible to distinguish stably effective operations from accidental hits. This paper formalizes the requirement as two structural conditions, alignability and comparability, and proposes Marginal Advantage Accumulation (MAA). MAA constructs differential signals to make them comparable across batches, accumulates signed evidence per operation via EMA, and ensures cross-batch traceability through semantic identity merging. As a post-processing architecture, MAA achieves the best results in 14 out of 16 settings across 4 benchmarks and 4 target models, consistently outperforming existing batch-level distillation baselines and matching or surpassing online alternatives in most settings, while reducing optimization-phase token consumption by approximately 75%.

AI 总结：提出Emyx，一种140M参数的流匹配模型，通过轻量条件表示和稀疏连接降低复杂度，在酶设计基准上超越现有方法，训练仅需682 GPU小时。

链接：https://arxiv.org/abs/2606.19377

机构：Xyme

作者：Nicholas J. Williams, Ward Haddadin, Matteo P. Ferla, Constantin Schneider, Nicholas B. Woodall, Ruby Sedgwick, Christian D. Madsen, Andrew L. Hopkins, Edward O. Pyzer-Knapp

英文摘要： Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the underlying generative model. Current all-atom generators inherit expensive architectures from structure prediction, leading to high training costs and limited sample diversity. We argue that much of this complexity is unnecessary for generators, which condition on sparse geometric constraints rather than rich co-evolutionary signals. Emyx is a 140M-parameter conditional flow matching model that concentrates capacity within standard transformer blocks, replacing heavy embedding stacks with lightweight conditional representations and sparse connectivity. We additionally derive an exact reparametrisation of the flow matching interpolant into the EDM noise-level framework, bridging flow matching training efficiency with state-of-the-art sampling methods designed for diffusion models without retraining. Despite being the smallest model, Emyx outperforms both Proteína-Complexa and RFdiffusion3 against the AME enzyme design benchmark across success rate under strict evaluation requiring both global fold recovery and catalytic geometry accuracy, structural novelty, scaffold diversity, and geometric validity, while training in just $682$ GPU-hours, roughly $4\times$ less than RFdiffusion3.

AI 总结：提出kCGM方法，通过最小化生成与目标特征分布的最大均值差异（MMD）并加入KL正则化，在不牺牲有效性的前提下校准生成模型的特征分布，适用于多种生成模型。

链接：https://arxiv.org/abs/2606.19496

机构：Stanford University（斯坦福大学）

作者：Nathaniel L. Diamant, Brian L. Trippe

英文摘要：Generative models can produce individually plausible samples while deviating substantially from a target set in the distribution of key features. For example, a model pretrained on broad drug-like chemical space may generate molecules whose molecular features differ from those of a therapeutic class of interest, such as known antibiotics. Correcting such distributional miscalibration is challenging: direct finetuning on the target set can overfit and does not control which features are matched. To fill this gap, we introduce kernel Calibrating Generative Models (kCGM). kCGM minimizes a maximum mean discrepancy (MMD) between generated and target feature distributions using an unbiased score-function estimator, with KL regularization to remain close to the pretrained model. On a target set of 174 antibiotics, direct finetuning sacrifices chemical validity for feature-distribution matching, whereas kCGM improves target feature matching while increasing validity. We further demonstrate kCGM in protein and DNA generation tasks, showing it can adapt autoregressive, continuous-space diffusion, and discrete diffusion models using only feature-level supervision. Code is available at this https URL.

AI 总结：提出信息论框架，通过潜在混合建模和描述长度约束，生成与现有模式不同且保持全局结构一致性的新颖图数据。

链接：https://arxiv.org/abs/2606.19770

机构：Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）

作者：Itsuki Nakagawa, Kenji Yamanishi

英文摘要：We propose an information-theoretic framework for graph novelty generation, which aims to generate data that are distinct from existing patterns while preserving global structural consistency. Our approach embeds data into a latent space, models the latent distribution using finite mixture models, and generates novel samples by imposing explicit novelty and reliability conditions formulated in terms of description length. Specifically, novelty is enforced by requiring generated samples to be poorly explained by all existing mixture components, while reliability constrains their impact on the overall mixture structure under the Minimum Description Length (MDL) principle. We provide a theoretical analysis showing that, with appropriate threshold choices, the probabilities of misclassifying non-novel or unreliable samples converge to zero with explicit rates. Experiments on synthetic and benchmark graph datasets demonstrate that the proposed method enables principled novelty generation with quantifiable risk.

AI 总结：提出流映射模型，通过单一参数t在MMSE和感知质量间连续调节，实现逆问题的失真-感知权衡，无需额外监督或调参。

链接：https://arxiv.org/abs/2606.19802

机构：Rice University（莱斯大学）； NVIDIA Inc.（英伟达公司）

作者：Nicolas Zilberstein, Morteza Mardani, Santiago Segarra

英文摘要：Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images. Existing approaches either commit to a single operating point on this distortion perception (DP) frontier or require paired-data supervision, auxiliary models, or hyperparameter tuning of the sampler to access different points. We show that flow map models, a recent extension of flow matching for few-step sampling that learns an average field, implicitly define a one-parameter family of denoisers that continuously spans the DP frontier. The lookahead parameter t acts as a control knob between the MMSE and perceptual regimes. For Gaussian targets, we prove that varying t exactly recovers the optimal DP frontier; for natural images, we observe similar behavior empirically. Within a Plug-and-Play solver, the same mechanism extends to general inverse problems, where it controls a tradeoff between perceptual alignment and data consistency. Despite the lack of exact optimality guarantees in this setting, a single trained flow map spans the DP tradeoff, matching or exceeding specialized baselines at both extremes. Extensive experiments on CelebA ($128\times 128$) and AFHQ ($256\times 256$) across several linear and nonlinear inverse tasks validate our findings.

AI 总结：针对任意紧支撑分布，提出一种基于离散混合的分数近似方法，证明ReLU网络复杂度仅随上Minkowski维数d指数增长，打破环境维数诅咒，解释扩散模型在非光滑数据上的有效性。

链接：https://arxiv.org/abs/2606.19894

机构：Academy of Mathematics and Systems Sciences（数学与系统科学研究院）； Chinese Academy of Sciences（中国科学院）； Shanghai Institute for Mathematics and Interdisciplinary Sciences（上海数学与交叉科学研究院）； Huawei Technologies Co., Ltd.（华为技术有限公司）

作者：Xinhe Mu, Zaijiu Shang, Zhaoqi Zhou, Chuan Zhou, Qi Meng, Guiying Yan, Zhiming Ma

英文摘要：The remarkable success of score-based diffusion models has spurred significant efforts to establish their theoretical foundations. However, existing complexity bounds for score approximation rely heavily on restrictive assumptions like Lipschitz continuous densities or smooth manifold supports, which are routinely violated by the singularities, sharp boundaries, and disjoint clusters inherent to real-world perceptual data. This work establishes a universal score approximation theorem that works for any distribution supported on any compact set of upper Minkowski dimension $d$. Using a novel discrete-mixture formulation, we prove that the score function can be approximated with a ReLU network whose complexity grows exponentially only with $d$, thus breaking the exponential curse of ambient dimensionality. Combined with existing theories on accurately solving the backward diffusion SDE for arbitrary compact distributions, our work shows that diffusion models readily adapt to irregular, non-smooth data structures, explaining their competence in real-world generative tasks.

AI 总结：提出PepALD模型，结合自回归潜在扩散与化学嵌入，实现从头设计大环肽，并利用偏好优化提升亲和力，在生成质量和奖励优化上优于基线。

链接：https://arxiv.org/abs/2606.14510

机构：College of Computer Science, Sichuan University（四川大学计算机科学学院）； School of Mathematics, Sichuan University（四川大学数学学院）； School of Artificial Intelligence, Sichuan University（四川大学人工智能学院）； Lingang Laboratory（临港实验室）

作者：Junming Zhang, Siyu Yi, Wei Ju, Zhonghui Gu

英文摘要：Macrocyclic peptides are promising therapeutic candidates for intracellular targets, but their design requires simultaneous control over non-natural monomer chemistry, ring topology, membrane permeability, and target binding. Existing SMILES- or HELM-string generative models either operate in long atom-level sequence spaces or treat monomers as symbolic tokens with limited chemical grounding. We introduce PepALD, an Autoregressive Latent Diffusion (ALD) foundation model for \textit{de novo} macrocyclic peptide generation. The model represents HELM monomers with structured chemical embeddings, generates each residue through context-conditioned diffusion in chemically informed latent space, predicts R-group-aware ring closures during autoregressive generation, and aligns the denoiser to affinity rewards using winner-protected diffusion-adapted preference optimization. In silico experiments demonstrate PepALD's generation quality and reward-optimization performance against representative peptide generation baselines.

AI 总结：本文通过理论和实验证明，在U-Net和Diffusion Transformer架构中，扩散模型无需显式时间步嵌入也能达到全局最优，甚至在某些指标上超越有条件模型。

链接：https://arxiv.org/abs/2606.20416

机构：Independent Researcher, Lima, Peru（独立研究者，秘鲁利马）

作者：José A. Chávez

英文摘要：Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales. In this work, we challenge the necessity of these temporal signals by analyzing their impact on U-Net and Diffusion Transformer architectures. Beyond empirical evidence, we provide a theoretical framework demonstrating that, under certain conditions, the global minimizer of the diffusion training objective can be achieved without explicit timestep conditioning. Our findings reveal a surprising robustness when timestep embeddings are completely removed. Extensive ablation studies on the CelebA and CIFAR-10 datasets show that these time-agnostic models can maintain high structural fidelity and even surpass their conditioned counterparts in competitive metrics, including FID, precision, and recall. Our analysis suggests these architectures can implicitly infer noise scales from the corrupted input under specific assumptions, rendering explicit temporal conditioning redundant. This study challenges long-standing temporal conditioning paradigms and paves the way for more efficient and structurally focused generative architectures.

AI 总结：提出“计算可识别性”框架，通过有限计算搜索过程在指定误差容限内找到经验估计量，从而解决理论可识别性在有限样本、模糊图标准等实际场景中的不足。

链接：https://arxiv.org/abs/2606.19361

机构：New York University（纽约大学）

作者：Lucius E.J. Bynum, Rajesh Ranganath, Kyunghyun Cho

英文摘要： Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available. In causal identification, this information is often expressed in the form of a causal graph, and data are observed or collected for some subset of variables in the graph. Target queries may be for a single effect alone or for a class of effects in a given model. The derivation of an identification algorithm then defines mathematically the process by which the desired causal effect(s) can be uniquely determined, theoretically, in expectation. Identifiability in expectation, or 'theoretical identifiability,' generally assumes asymptotic properties, infinite data, or other mathematically idealized conditions. In this paper, we explore a fundamental distinction between this theoretical, idealized notion of identifiability and a proposed alternative that is computation-bound. The framework we propose - 'computational identifiability' - is to instead define a finite computational search procedure for an empirical estimator. If this process finds an estimator empirically, within a desired error tolerance, then identifiability is satisfied, conditional on the specified assumptions of the search (i.e., a prior distribution over the parameters) and conditional on the search procedure itself. Through several experiments, we demonstrate how this framework allows us to answer fine-grained, practical identification questions, such as identification with small finite samples, with ambiguous graphical criteria, with mixed observational-interventional data, and across counterfactual data and estimands. Code is available at this https URL.

AI 总结：将信息格学习（ILL）解释为概率图模型结构学习，通过投影到分区格上学习可解释规则，并建立与最大熵和因子图的联系。

链接：https://arxiv.org/abs/2606.19366

机构：Kocree, Inc.（Kocree公司）； AI Innovation Institute, Stony Brook University（石溪大学人工智能创新研究所）

作者：Haizi Yu, Lav R. Varshney

英文摘要：Information lattice learning (ILL) learns interpretable rules of a signal by alternately projecting the signal onto a partition lattice that encodes a hierarchy of abstractions and lifting selected rules back to the signal domain. When the signal is a probability mass function, we show the probabilistic rules learned by ILL admit a natural probabilistic graphical model (PGM) interpretation and develop this interpretation in detail. A partition in ILL induces a deterministic quotient variable, and a rule is the marginal law of that quotient variable. A rule set is therefore a collection of marginal constraints over interpretable abstractions. General lifting is the feasible family of all joint distributions satisfying those constraints, while special lifting chooses a maximum-ignorance reconstruction, implemented in ILL by an L2 uniformity principle closely related to maximum entropy. Under a Shannon-entropy lifting, the same constraints yield a log-linear factor graph whose factors are indexed by learned abstractions. The information lattice itself, however, is not a Bayesian network: its edges encode refinement and coarsening of abstractions, not conditional dependence. Thus ILL is best viewed as structure learning for interpretable constraint-based factor graphs over quotient variables. This view clarifies how ILL relates to graphical models and maximum entropy models, while suggesting new directions for inference, identifiability, and hybrid symbolic-probabilistic learning.

AI 总结：研究 AdamW 训练中 Weibull 权重尺度参数 λ 增长、过冲和松弛的原因，推导出三种力（对齐、注入、衰减）的分解，并在 Pythia-70M 模型上验证对齐力主导上升阶段，贡献 88-94%。

链接：https://arxiv.org/abs/2606.19367

机构：Independent Researcher（独立研究员）

作者：Tiexin Ding

英文摘要：Building on a two-parameter Weibull framework for diagnosing transformer weight distributions, we study why the Weibull weight-scale parameter $\lambda$ grows, overshoots, and then relaxes during AdamW training. We derive a leading-order three-force decomposition of the squared weight norm from the AdamW update: an alignment force measuring the correlation between weights and the adaptive update direction, an injection force from adaptive step magnitude, and a decay force from decoupled weight decay. On self-trained Pythia-70M models with ground-truth optimizer moments, alignment dominates the rise phase, contributing 88-94% of the absolute force budget across four random seeds and remaining robust to super-weight removal. Near saturation, alignment and decay approach balance, explaining the transition from weight-scale growth to relaxation. These force dynamics directly govern the squared-norm component underlying $\lambda(t)$; the remaining RMS-to-Weibull reconstruction offset is measurable and decomposes into bridge and integration components, totaling approximately 5-6% in densely sampled regions. To extend the analysis to real models where optimizer moments are unavailable, we introduce a spline displacement method that recovers the alignment force from sparse checkpoints with approximately 92-94% accuracy, about twice the naive two-point baseline. We further observe that the peak value of $\lambda(t)$ varies with training-data coherence in our experiments, suggesting a data-dependent component of weight-scale growth that we leave to a controlled follow-up study. Code and data are available at this https URL.

AI 总结：提出多元零膨胀高斯分布作为估计分布算法的采样分布，联合优化稀疏模式和活跃参数，无需手工设计稀疏算子，在Lunar Lander基准上收敛更快且最终回报更高。

链接：https://arxiv.org/abs/2606.19369

机构：University of Freiburg（弗莱堡大学）； FZI Research Center for Information Technology（FZI信息技术研究中心）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

作者：Andreas Faust, Sven Nitzsche, Juergen Becker

英文摘要： Estimation-of-distribution algorithms (EDAs) are a powerful class of evolutionary methods for black-box optimization, especially when little is known about the structure of the objective. Whereas classical evolutionary algorithms rely on hand-designed mutation and crossover operators, hard to devise for unknown problem structures, and a source of bias, EDAs sidestep operator design entirely: they fit a probability distribution to the best individuals and sample the next generation from it. EDAs are well established on continuous parameter spaces, but they have not previously been generalized to sparse ones, in which most coefficients of a good solution are exactly zero. Existing sparse black-box optimizers therefore reintroduce exactly what EDAs were designed to avoid: hand-crafted sparsity operators, bi-level schemes alternating between support set and active values, zeroing thresholds, and other baked-in assumptions. We close this gap by proposing multivariate zero-inflated Gaussian (ZIG) distributions as EDA sampling laws. A latent Gaussian model with separate indicator and value dimensions represents sparsity patterns, correlations among active parameters, and the interactions between the two, so sparsity patterns and active values are optimized jointly, hierarchy-free. We show that the latent parameters of this model are identifiable from observed samples, unlike in the missing-data settings where related constructions originate, and introduce practical amortized inversion-based estimators for them. The estimators accurately recover latent correlation structures, and on the Lunar Lander benchmark the resulting ZIG-EDA converges faster and reaches higher final returns than a dense Gaussian EDA, a hand-crafted sparse evolutionary algorithm, and an ad-hoc sparse EDA, while finding controllers with only a small fraction of parameters active.

AI 总结：本文发现 LayerNorm 的逆尺度方向是后最终归一化中心激活协方差矩阵的精确代数核，可仅从参数中读取死方向，无需前向或后向传播，并在 14 个预训练模型上验证了其有效性。

链接：https://arxiv.org/abs/2606.19491

机构：IIIT, Hyderabad（海得拉巴国际信息技术学院）

作者：Tejas Pradeep Shirodkar, P. J. Narayanan

英文摘要：Pretrained transformers sit near singular minima of the loss, where the Fisher information metric degenerates along dead directions: directions in parameter space along which the directional Fisher vanishes. Locating such a direction normally needs a forward pass and an eigendecomposition of activations, or a sampling-based complexity estimate; none returns a direction computable from the network's parameters alone. We give one, for LayerNorm transformers. The inverse-scale direction $\gamma^{-1}/\|\gamma^{-1}\|$ of the LayerNorm affine is an exact algebraic kernel of the post-final-norm centred activation covariance, for any input distribution, and induces a corresponding dead direction in parameter space. It is read from the LN scale parameter alone, with no forward or backward pass and no eigensolve: the cheapest dead-direction read, specific to LayerNorm. We test it on $14$ pretrained transformers ($9$ LayerNorm, $5$ RMSNorm; $160$M-$35$B; language and vision objectives). At random initialisation the predicted direction matches the measured bottom singular direction (one forward pass, direct SVD) to four decimal places on $9/9$ LayerNorm models, and is correctly absent on $5/5$ RMSNorm models, which lack the mean-subtraction projector that creates it. On the trained checkpoint the covariance eigenvalue along this direction deepens by ${\sim}10^3\times$ and further dead directions open; the random-init-to-trained gap is a one-forward-pass, per-checkpoint readout of singular structure along the predicted coordinate. Two consequences follow in closed form: the residual stream's smallest singular value is preserved block-to-block on $13/14$ transformers measured on their own input distribution, the one exception (Gemma$4$-$31$B) a genuine dead direction the same read pinpoints; and the kernel direction's presence classifies a transformer's normalisation from the parameters alone.

AI 总结：提出偏好帕累托探索（PPE）框架，通过预测-校正方法沿帕累托流形切线方向引导偏好，利用Krylov子空间方法避免Hessian计算，实现高效交互式多目标优化。

链接：https://arxiv.org/abs/2606.19521

机构：Department of Computer Science, TU Dortmund, Dortmund, Germany（多特蒙德工业大学计算机科学系，德国多特蒙德）； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习和人工智能研究所）

作者：Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz

英文摘要：In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a novel framework, Preference Pareto Exploration (PPE), which enforces the decision maker's preferences while accounting for the geometry of the Pareto set in an interactive exploration process. PPE is based on a predictor-corrector method that performs predictor steps tangential to the manifold of Pareto-optimal solutions, following the decision maker's preference. The subsequent corrector step results in a new trade-off reflecting this preference. To avoid explicit Hessian computations when characterizing the tangent space of the manifold, we employ a Krylov subspace method that relies solely on matrix-vector products. These products can be efficiently obtained via automatic differentiation, ensuring both efficiency and robustness throughout the optimization process. The method's functionality and performance are demonstrated using both toy problems and examples from deep learning.

AI 总结：提出一种凸限制方法求解非凸Lipschitz正则化训练问题，可全局最优求解，并作为预训练网络的后处理步骤，提升对抗鲁棒性和准确性。

链接：https://arxiv.org/abs/2606.19652

机构：Polytechnique Montréal, GERAD & Mila, Montréal, QC, Canada（蒙特利尔理工学院，GERAD & Mila，加拿大魁北克省蒙特利尔市）

作者：Chao Yin, Antoine Lesage-Landry

英文摘要：In this work, we introduce a training procedure for shallow neural networks that promotes robustness against adversarial attacks. We solve a non-convex Lipschitz-regularized training program by introducing a convex restriction that can be efficiently solved to global optimality. Our approach can be employed as a post-processing step by taking a pre-trained network as an initial solution to then solving the convex program whose optimal network is guaranteed to be no worse than the initial one. We illustrate the improvements of our training procedure with experiments using real world datasets for regression tasks under an adversarial setting. We show numerically that solving our proposed convex program yields networks with lower objective values on the Lipschitz-regularized program compared to existing methods. Additionally, we show that on certain datasets, networks obtained using our convex training program are both more accurate and robust with respect to adversarial attacks.

AI 总结：研究反向Fisher散度下梯度下降拟合高斯混合模型的全局收敛性，证明从任意初始化或随机初始化下学生分量收敛到最近教师分量，并给出全变差距离收敛条件。

链接：https://arxiv.org/abs/2606.19876

机构：Applied AI Institute, Moscow, Russia（莫斯科应用人工智能研究所）； AXXX, Moscow, Russia（莫斯科AXXX）

作者：Alexander Tyurin

英文摘要：The score matching problem is a central training objective in modern generative modeling, diffusion models, fitting unnormalized statistical models, and inverse problems. A standard approach is to minimize the forward Fisher divergence, where the expectation is taken with respect to the teacher distribution. However, recent results show that even in simple Gaussian mixture model settings, this objective can lead to undesirable and initialization-dependent convergence behavior. In this paper, we study an alternative objective: the reverse Fisher divergence, where the expectation is taken with respect to the student distribution. We analyze gradient descent (GD) for fitting Gaussian mixture models and show that this change in the objective leads to significantly better optimization properties. First, when the teacher distribution is a single Gaussian and the student is a Gaussian mixture model with fixed weights and identity covariances, we prove the global convergence of GD from arbitrary initializations. Second, we extend the analysis to the case where the teacher is also a Gaussian mixture model and prove global convergence guarantees under a global random initialization scheme and a $\widetilde{\Omega}(1)$-separation assumption on the target means. In particular, with high probability, each student component converges near its closest teacher component, and we provide conditions under which the student distribution converges in total variation distance. Our proofs rely on a new Lyapunov-based analysis of the gradient descent dynamics, showing that the reverse Fisher divergence has a much more favorable optimization landscape than the forward Fisher divergence.

AI 总结：提出分段多项式插值梯度下降（PPI-GD）方法，通过数据域等距点查询一阶预言构造多项式插值近似全梯度，在强凸和非凸损失下分析预言复杂度，证明在数据维数受限且损失足够光滑时优于多种GD变体。

链接：https://arxiv.org/abs/2606.19878

机构：Purdue University（普渡大学）

作者：Dongmin Lee, William Lu, Anuran Makur

英文摘要：Recent work on first-order optimizers for empirical risk minimization (ERM) has suggested that smoothness of ERM loss functions in the training data, rather than in the optimization parameters, can be leveraged to improve the oracle complexity of gradient descent (GD) methods. In this paper, we propose an inexact gradient method, piecewise polynomial interpolation-based gradient descent (PPI-GD), which approximates the full gradient in each iteration by querying the first-order oracle at equidistant points in the data domain to construct polynomial interpolants of the resulting gradient samples over appropriately sized patches of the data domain. We analyze the oracle complexity of PPI-GD for strongly convex and non-convex loss functions when the data space dimension is bounded by a polylogarithmic function of the number of training samples, and find it to outperform several GD variants in key regimes when the loss function is sufficiently smooth. Furthermore, our analysis extends several techniques from the error analysis of bicubic spline interpolants to the setting of $d$-variate tensor product polynomial interpolants which may be of independent interest in interpolation analysis.

AI 总结：研究损失函数可能非凸非光滑的对抗性赌博机优化，提出一种修改的赌博机优化算法，并分析扰动预算对遗憾的影响，将线性损失下的全局预算后行动扰动模型扩展到一般凸且β-光滑损失。

链接：https://arxiv.org/abs/2606.19891

机构：Department of Informatics, Kyushu University（九州大学信息学系）； RIKEN AIP（日本理化学研究所AIP）

作者：Zhuoyu Cheng, Kohei Hatano, Eiji Takimoto

英文摘要：We study adversarial bandit optimization in which the loss functions may be non-convex and non-smooth. In each round, the learner selects an action and observes only the loss incurred at that action. The loss consists of an underlying convex and $\beta$-smooth component and an adversarial perturbation that may be chosen after observing the learner's action. The perturbations are subject to a global budget controlling their cumulative magnitude over time. This framework extends the globally budgeted, post-action perturbation model from underlying linear losses to general convex and $\beta$-smooth losses. For this broader class, we establish expected regret guarantees that explicitly characterize the effect of the perturbation budget. To establish these guarantees, we modify a standard bandit optimization algorithm and develop an analysis that controls the additional regret caused by the perturbations. In the absence of perturbations, our results reduce to regret guarantees for the standard bandit convex optimization setting with $\beta$-smooth losses.

AI 总结：本文从信息论角度分析潜在思维链中的监督失效问题，提出轨迹监督和空间监督两个维度，并引入统一潜在探针（ULP）量化信息保真度，揭示了信息-性能绑定关系。

链接：https://arxiv.org/abs/2606.20075

机构：Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院，东方理工大学）； Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）

作者：Xinghao Chen, Chak Tou Leong, Wenjin Guo, Jian Wang, Wenjie Li, Xiaoyu Shen

英文摘要：Latent Chain-of-Thought (CoT) internalizes reasoning within continuous hidden states, offering a promising alternative to verbose discrete reasoning traces. However, robust latent reasoning remains difficult because outcome supervision provides weak learning signals and leaves latent trajectories prone to semantic drift. In this work, we analyze Latent CoT from an information-theoretic perspective and identify this failure as a dual collapse: gradient attenuation along the optimization path and representational drift in the latent space. We further decompose process supervision into two complementary dimensions: Trajectory Supervision, which injects dense stepwise reasoning signals, and Space Supervision, which preserves the semantic structure of the latent manifold. Our analysis shows that rigid geometric compression can collapse the reasoning space, whereas generative reconstruction provides a more flexible semantic anchor that better preserves information capacity. To measure these effects, we introduce the Unified Latent Probe (ULP), which quantifies the mutual information between latent trajectories and explicit reasoning steps. Experiments reveal a clear Information-Performance Binding: reasoning accuracy depends on the information fidelity preserved in the latent chain. These findings provide a principled framework for latent reasoning supervision and suggest shifting from geometric imitation toward mutual information maximization. Our code is available at \href{ this https URL }{this repository}.

AI 总结：通过有效维度d_eff解释量子视觉模型中纠缠结构增强泛化与量子噪声提升测试精度的现象，提出噪声形状核的谱分解与正则化机制。

链接：https://arxiv.org/abs/2606.20183

机构：RIKEN iTHEMS（日本理化学研究院iTHEMS）； RIKEN AIP（日本理化学研究院Advanced Institute for Photonics and Electronics）； South China University of Technology（华南理工大学）； Columbia University（哥伦比亚大学）

作者：Jian Xu, Delu Zeng, John Paisley, Qibin Zhao

英文摘要：Recent quantum vision models-quantum vision transformers and quantum convolutional networks-report two striking but unexplained empirical phenomena: (i) ansatze with more, or more uniformly distributed, entanglement generalize better, and (ii) injecting quantum noise can improve test accuracy rather than degrade it. These observations are currently treated as curiosities, discovered by grid search and explained, if at all, by hand. We show that both are manifestations of a single, measurable quantity: the \emph{effective dimension} $d_{\rm eff}$ of the (noise-shaped) quantum feature kernel. Working primarily with quantum-kernel vision models-a quantum feature map read out by a kernel classifier-we give a spectral account in which entanglement structure and quantum noise are two knobs that move $d_{\rm eff}$; in an overfitting regime, contracting $d_{\rm eff}$ acts as ridge-like regularization. We analyze the mechanism: an \emph{exact} decomposition of the depolarized kernel $K_p=(1-p)^2K+\tfrac{p(2-p)}{D}\mathbf{1}\mathbf{1}^\top$ with $d_{\rm eff}(K_p)\to1$, a contraction result (and its boundary) for amplitude damping, a kernel-machine capacity bound, and a capacity/alignment risk decomposition; the monotone contraction operative in our entangled experiments is verified empirically, not proven in general. Along the one-parameter depolarizing family the collapse is instead exact by construction; we use it only to confirm the kernel decomposition to machine precision and at up to $12$ qubits, not as evidence for $d_{\rm eff}$. Amplitude damping contracts $d_{\rm eff}$ and lifts test accuracy by up to $+13\%$ along an inverted-U sweet spot; the effect's sign flips between the over- and under-fitting regimes; noise injection matches an explicit spectral-filtering frontier. Our results organize two reported anecdotes into a single measurable principle for designing quantum-vision models.

AI 总结：本文证明，对于[-1,1]上的任意连续函数，存在一个固定权重和隐藏维度的ReLU递归神经网络，其时间演化可以均匀逼近该函数，并给出了收敛速率和极小极大下界。

链接：https://arxiv.org/abs/2606.20325

作者：Valentin Abadie, Clemens Hutter, Helmut Bölcskei

英文摘要：Classical approximation theorems ask for a new neural network whenever the target accuracy is improved. This paper studies the opposite possibility: can the network be chosen once and for all, and can accuracy be bought only by letting it run longer? We prove that this is possible for every continuous function on [-1,1]. More precisely, each such function is uniformly approximated by the time evolution of a single ReLU recurrent neural network with fixed weights and fixed hidden dimension. The mechanism behind the construction is a new intermediate model, the Turing machine with neural units (TMNU). This model retains the algorithmic freedom needed to implement polynomial approximation schemes, while remaining rigid enough to be simulated by RNNs with explicit bounds on hidden dimension and weight magnitude. The resulting convergence rates reflect the underlying polynomial approximation rates. We complement the construction with minimax lower bounds showing that runtime is not merely a proof artifact, but an unavoidable resource in this fixed-network approximation paradigm.

AI 总结：本文分析表格表示下相位设置中时序差分学习的方差，证明其方差降低机制是通过有效聚合更多独立轨迹，并比较了TD、MC和DAE的方差界限。

链接：https://arxiv.org/abs/2606.20357

作者：Hsiao-Ru Pan, Bernhard Schölkopf

英文摘要： We analyze the variance of temporal difference (TD) learning using the phased setting with tabular representation, and show that one of the mechanisms behind its ability to reduce variance is by effectively aggregating over a larger number of independent trajectories. Based on this insight, we demonstrate that (1) the variance of TD is asymptotically bounded from above by Monte Carlo (MC) estimators, and (2) shorter horizon updates incurs less variance for a fixed number of samples. Beyond TD, we show that Direct Advantage Estimation (DAE), a method for estimating the advantage function, can be seen as a type of regression-adjusted control variate, which achieves a tighter bound on the variance compared to TD in the large-sample limit. Finally, we numerically illustrate the behaviors of these estimators with carefully designed environments.

AI 总结：针对SGD偏好平坦极小值但欧氏锐度不具重参数化不变性的问题，提出基于Fisher信息矩阵的黎曼锐度，证明其不变性，并导出SGD稳态分布集中于平坦极小值，PAC-Bayes界联系泛化性能。

链接：https://arxiv.org/abs/2606.20469

机构：Gauhati University（高哈蒂大学）

作者：Md Sakir Ahmed, Kumaresh Sarmah, Hemen Dutta

英文摘要：A widely held intuition in deep learning is that stochastic gradient descent (SGD) implicitly favors flat minima and that flat minima generalize better, but standard Euclidean measures of flatness such as the trace or maximum eigenvalue of the loss Hessian are not invariant under reparametrizations that preserve the network function, which undermines the theoretical foundations of this narrative. In this study we resolve this issue by grounding flatness in the Riemannian geometry of the statistical manifold induced by the Fisher Information Matrix (FIM). We define Riemannian sharpness mathematically and prove that it is invariant under smooth, function-preserving reparametrizations, which directly addresses the critique of Dinh et al. in the paper ``Sharp minima can generalize for deep nets''.We note that this invariance is a property of the true FIM; the diagonal empirical estimator used in practice (and in all experiments below) inherits invariance only approximately, and exact invariance under arbitrary reparametrizations would require structured estimators such as K-FAC. We formalize the gradient noise of mini-batch SGD as having a covariance structure proportional to the FIM, derive the stationary distribution of the resulting stochastic differential equation, and then show that the probability mass is exponentially concentrated at Riemannian-flat minima. A PAC-Bayes generalization bound controlled explicitly by SR formally links this geometric bias to test performance. Our experiments on MNIST and CIFAR-10 confirm that SR reliably tracks generalization in ways that Euclidean sharpness does not, and that its scaling with $\eta/B$ matches the theoretical predictions. Together these results provide a rigorous, reparametrization-invariant account of why flat minima generalize.

AI 总结：针对云LLM推理中提示词预填充阶段能耗高的问题，提出SPSD边缘端管道，利用4比特量化小语言模型压缩用户提示，在保持响应质量非劣效的前提下，平均节省99.9个输入token，每调用净节能70-270 uWh。

链接：https://arxiv.org/abs/2606.19364

机构：Indian School of Business（印度管理学院）

作者：Abhinit Sen, Ajeet Kumar, Manaranjan Pradhan

英文摘要：The prefill stage of Large Language Model (LLM) inference is a growing contributor to cloud-scale energy cost. Many consumer-support and conversational prompts contain social scaffolding: politeness markers, apologetic preamble, repetition, and rapport-building language that is important for human communication but carries low marginal information for machine reasoning. We call this discrepancy the Social-Semantic Gap. We present SPSD (Sentiment Preserving Semantic Distillation), an edge-based pipeline that compresses user prompts using a 4-bit quantised Small Language Model before transmission to a cloud-deployed LLM. Evaluation on a 248-prompt corpus using Gemma-2-2B-Instruct (Q4_K_M) as the SLM and Llama-3.1-8B-Instruct as the cloud evaluation model yields a mean input token saving of 99.9 tokens per distilled call, with all 146 distilled calls yielding positive savings. Response quality, assessed by blind LLM-as-judge scoring across 121 pairs, is non-inferior to the raw path within a pre-specified 1-point margin on a 15-point rubric; the judge awarded 43 percent ties, 28 percent distilled wins, and 29 percent raw wins. Cosine similarity is mixed: mean 0.682, median 0.712, with 54.1 percent of pairs above the 0.70 reference threshold. Safety-critical domains are conservatively routed to passthrough via rule-based gates. Per-call net energy saving is estimated at 70-270 uWh under stated assumptions. SPSD shows that on-device prompt distillation can reduce cloud LLM input-token cost while preserving response quality within a practical non-inferiority margin.

AI 总结：针对3D MRI扩散模型Med-DDPM，分析其在三代NVIDIA架构上的内核级性能瓶颈，提出TF32 Tensor Core激活和3D channels-last布局优化，实现SM周期和动态指令减少100倍，Tensor Core利用率提升至9.98倍，IPC提升7%。

链接：https://arxiv.org/abs/2606.19365

机构：Fairleigh Dickinson University（费尔利·迪金森大学）； The University of Colorado at Colorado Springs（科罗拉多大学科罗拉多斯普林斯分校）； Northeastern University（东北大学）

作者：Jeeho Ryoo, Yongchan Jung, Muhammad Ali Khaliq, Weidong Zhang, Jiatong Han, Byeong Kil Lee

英文摘要： Diffusion models have become essential for high-fidelity 3D MRI synthesis, yet their deployment remains constrained by substantial GPU resource demands arising from hundreds of U-Net evaluations per sample and a highly heterogeneous kernel behavior. This paper performs a comprehensive performance analysis of the state-of-the-art medical diffusion model, Med-DDPM, across three generations of NVIDIA architectures to study kernel-level runtime breakdowns, instruction-mix characteristics, memory system utilization, warp-level activities, and profiler priority-score estimates. We show that training is overwhelmingly dominated by cuDNN convolution and implicit-GEMM kernels, with inefficiencies arising from memory-access patterns, tensor-layout conversions, and limited Tensor Core utilization. Guided by these insights, we evaluate two architecture-aware optimizations TF32 Tensor Core activation and a 3D channels-last layout and demonstrate that they reduce SM cycles by up to 100x, cut dynamic instructions by 100x, raise Tensor Core utilization from 1.45 to 9.98x, and increase IPC by 7% on A100, all without degrading synthesis quality.

AI 总结：针对边缘设备上LLM LoRA微调的内存瓶颈，提出四种互补技术（量化、检查点、softmax近似、logits掩码），在Llama-3.2 3B和Qwen-2.5 3B上实现高达26倍和28倍的峰值内存降低。

链接：https://arxiv.org/abs/2606.19528

机构：GitHub

作者：Hassan Dbouk, Matthias Reisser, Prathamesh Mandke, Likhita Arun Navali, Christos Louizos

英文摘要：Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

AI 总结：提出MergeProbe，通过训练初期信号预测LoRA适配器的可合并性，在MERGE-PEFT基准上实现最佳平均和最差保留性能。

链接：https://arxiv.org/abs/2606.19549

机构：Sichuan University（四川大学）； University of Electronic Science and Technology of China（电子科技大学）

作者：Lin Tang, Wei Zhang, Jing Li, Hongyu Chen, Ming Zhao, Yuxuan Wang

英文摘要：Low-rank adaptation (LoRA) makes it cheap to train many domain- and task-specific language model adapters, but whether two adapters can be merged is usually discovered only after both have been fully trained and evaluated. This late feedback is costly: adapters that are strong in isolation can interfere destructively once their updates are combined. We ask whether this outcome can be anticipated. We formalize adapter mergeability as the degree to which an adapter preserves its single-task utility after merging, and show that it can be forecast from signals measured in the first few percent of training -- chiefly how the low-rank updates and their gradients align across tasks and how much they disturb shared representations. We package these signals into MergeProbe, a lightweight predictor that estimates pairwise and set-level retention and turns the estimate into a concrete decision: merge directly, reweight, prune, or route. On MERGE-PEFT, a five-domain benchmark spanning math, code, science, instruction following, and safety, MergeProbe attains the best average and worst-case retention among strong interference-aware merge baselines while adding far less deployment overhead than full task routing. This turns LoRA merging from a post-hoc engineering step into an anticipatory measurement problem.

AI 总结：针对实际应用中常见的少类数据集，提出基于数据属性的分类难度度量，实现比传统方法快6-29倍的模型选择，并扩展模型族至更小规模，在移动机器人等场景中提升效率。

链接：https://arxiv.org/abs/2606.19712

机构：Nokia Bell Labs（诺基亚贝尔实验室）

作者：Bryan Bo Cao, Abhinav Sharma, Lawrence O'Gorman, Michael Coss, Shubham Jain

英文摘要：While much effort has focused on developing and benchmarking high-performance neural networks, less attention has been given to how dataset properties, known to practitioners, can guide efficient model selection. Neural models are typically evaluated on datasets with thousands of classes, yet many real-world applications involve fewer than ten. To address this understudied but common setting, we develop a measure of classification difficulty based on data-side properties and show how it enables more efficient model selection for few-class datasets, where traditional approaches are less effective. We term this phenomenon "few-class distinctiveness". Our metric allows comparison of models and datasets 6 to 29$\times$ faster than repeated training and testing. Leveraging this insight, we extend scaled model families below the smallest published models, achieving greater efficiency at similar accuracy, for example models up to 42% smaller than YOLOv5-nano for a mobile robot task. Targeting resource-constrained applications, we demonstrate few-class model selection across mobile robot, drone, and IoT scenarios, highlighting practical gains in efficiency without sacrificing performance.

AI 总结：提出ADaPT，通过令牌级双过程框架解耦效率与正确性信号，引入模式选择令牌控制快慢推理，实现推理时效率-性能权衡的精确连续控制，在降低推理成本的同时保持强推理能力。

链接：https://arxiv.org/abs/2606.19919

机构： School of Data Science, Fudan University（复旦大学数据科学学院）； Shanghai Institute of Artificial Intelligence for Education, East China Normal University（华东师范大学上海智能教育研究院）； College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）； Ant Group（蚂蚁集团）

作者：Tingyun Li, Zishang Jiang, Jinyi Han, Xinyi Wang, Sihang Jiang, Han Xia, Zhaoqian Dai, Shuguang Ma, Fei Yu, Jiaqing Liang, Yanghua Xiao

英文摘要：Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability. We identify the root cause as sequence-level coupling between efficiency incentives and correctness optimization, which implicitly penalizes long but correct reasoning trajectories. To address this issue, we propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training. ADaPT introduces a mode-selection token to control fast and slow reasoning, applying efficiency-related rewards exclusively to this token to avoid penalizing correct long reasoning while encouraging efficiency when appropriate. Moreover, ADaPT enables precise and continuous control over the efficiency-performance trade-off at inference time: by adjusting the generation probability of the mode-selection token, a single trained model can smoothly move along the efficiency-performance Pareto frontier. Extensive experiments demonstrate that ADaPT significantly reduces inference cost while maintaining strong reasoning performance across multiple benchmarks.

AI 总结：针对Tsetlin Machine推理，提出一种领域专用RISC-V微处理器架构，通过指令精简和数据路径简化，在保持可编程性的同时实现高达98%的执行时间减少和29.7倍能耗降低。

链接：https://arxiv.org/abs/2606.19964

机构：CoDA Laboratory, Indian Institute of Technology Roorkee（科达实验室，印度理工学院德里分校）； Microsystems Research Group, Newcastle University（微系统研究组，新castle大学）

作者：Chanda Gupta, Sanidhya Bhatia, Shaurya Priyadarshi, Himani Panwar, Rishad Shafik, Sudip Roy

英文摘要：Tsetlin Machine (TM) is a logic-based machine learning approach that relies on simple bitwise operations and finite-state automata, which makes it attractive for edge AI deployments. Recent work has focused on co-processor and accelerator designs based on Tsetlin Machines (TMs). Although these designs achieve high performance, they typically depend on tightly coupled interfaces, microcode-style programming, and external host processors, limiting flexibility and ease of programming. In this work, we present a domain-specific RISC-V microprocessor architecture and design flow tailored for TM inference. Leveraging the modular structure of RISC-V, we design a reduced instruction subset processor that retains programmability while targeting improved performance and lower energy consumption for TM workloads. Instruction profiling is employed to guide instruction reduction, followed by datapath and control path simplifications tailored to TM inference. Both the baseline RV32IM core and the proposed reduced core are evaluated across multiple datasets and compared with Binarized Neural Networks (BNNs), which serve as a hardware-efficient baseline due to their reliance on bitwise operations during inference. Results show that TM achieves comparable or higher accuracy (e.g., up to 88.18% on CIFAR-2 compared to 60.0% for BNN) while reducing execution time by up to 98% across multiple datasets. Furthermore, the proposed design achieves an average $29.7\times$ reduction in energy consumption, demonstrating its effectiveness for programmable and efficient edge AI systems.

AI 总结：提出AIR框架，基于SVD和反向信号影响度量，通过单次交替最小二乘扫描实现权重矩阵的低秩近似，在参数保留≤60%时困惑度比SVD-LLM(W)改善>18%，并减少90%校准数据。

链接：https://arxiv.org/abs/2606.19993

机构：Fraunhofer HHI（弗劳恩霍夫研究所）

作者：Nico Harder, Daniel Becking, Karsten Mueller, Wojciech Samek

英文摘要：We present Activation- and Influence-Aware Ranks (AIR), an SVD-based LLM compression framework that guides each weight matrix's low-rank approximation with a backward-signal influence metric. Starting from the activation-aware optimum of SVD-LLM(W), AIR runs a single closed-form alternating least squares (ALS) sweep that integrates influence element-wise under a monotone-descent guarantee. AIR is layer-local and composes orthogonally with end-to-end methods: alone it exceeds ACIP, and AIR+LoRA outperforms it further. AIR improves perplexity over SVD-LLM(W) by >18% at <=60% parameter retention, matches its quality with ~90% less calibration data, and turns parameter savings into FLOP, peak-memory, and per-token latency gains.

AI 总结：提出StreamKL，首个融合GPU原语，通过在线公式和逐块重计算将注意力蒸馏的内存和IO成本从O(N_QN_K)降至O(1)，实现高达43倍前向和14倍反向加速。

链接：https://arxiv.org/abs/2606.20005

机构：Shanghai Jiao Tong University（上海交通大学）； Huawei（华为）； Fudan University（复旦大学）

作者：Guangda Liu, Yiquan Wang, Chengwei Li, Wenhao Chen, Jing Lin, Yiwu Yao, Danning Ke, Wenchao Ding, Jieru Zhao

英文摘要： Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, model compression, continual learning, and sparse-attention LLM training. However, existing approaches materialize both attention distributions before computing the KL reduction, incurring $O(N_QN_K)$ memory and IO costs that become prohibitive at long context lengths. We present StreamKL, the first fused GPU primitive for attention KL divergence that eliminates this quadratic materialization. StreamKL derives a novel online formulation for the coupled two-distribution KL reduction, enabling a single one-pass forward kernel that streams query-key tiles through on-chip SRAM. For the backward pass, StreamKL recomputes attention probabilities tile-by-tile, avoiding storage of quadratic intermediates. We further design and implement efficient GPU kernels with dedicated optimizations. Experiments show StreamKL delivers up to $43\times$ and $14\times$ speedups over baseline methods in the forward and backward passes, respectively. Most importantly, StreamKL reduces the extra HBM footprint of attention distillation from $O(N_QN_K)$ to $O(1)$, enabling long-context distillation on a single GPU.

AI 总结：针对上下文密集型智能体场景，提出UltraQuant方法，通过4位KV缓存压缩、旋转量化和代码本量化，结合AMD GPU优化，在长上下文多轮任务中延迟降低3.47倍，吞吐量提升1.63倍。

链接：https://arxiv.org/abs/2606.20474

机构：Advanced Micro Devices（超威半导体）； University of California, Los Angeles（加州大学洛杉矶分校）； Purdue University（普渡大学）

作者：Inesh Chakrabarti (1 and 2), David Limpus (1 and 3), Aditi Ghai Rana (1), Bowen Bao (1), Spandan Tiwari (1), Thiago Crepaldi (1), Ashish Sirasao (1) ((1) Advanced Micro Devices, (2) University of California, Los Angeles, (3) Purdue University)

英文摘要：Context-heavy agents place unusual pressure on the key-value (KV) cache: long prefixes are reused across many short turns, while concurrency determines whether the serving system can keep GPUs utilized. We study 4-bit KV-cache compression for this setting, using TurboQuant-style rotation and codebook quantization as a quality anchor and vLLM FP8 KV caching as the deployment anchor. We report three contributions. First, we frame 4-bit KV caching around multi-round agent workloads where task quality, cache residency, and serving throughput must be measured jointly. Second, we describe the practical design choices needed to make the 4-bit path robust, including asymmetric K/V treatment, Walsh-Hadamard rotation, QJL removal, and block-scale variants. Third, we present serving optimizations on AMD GPUs, including optimized decode-attention kernels and UltraQuant, an FP4 approximation path that uses FP8 queries, FP4 KV tensors, UE8M0 group scales, and native scaled-MFMA support on CDNA4. On a long-context, multi-turn agentic workload, UltraQuant cuts P50 time-to-first-token by 3.47x in the cache-pressured late rounds (2.3x across all rounds) and raises output throughput by 1.63x over the FP8 KV baseline.

AI 总结：针对低延迟、小批量、设备端物理AI服务场景，提出执行状态胶囊机制，通过图绑定检查点与恢复完整可恢复状态，在RTX 5090上实现亚毫秒级恢复，TTFT加速比达3.9倍至27倍。

链接：https://arxiv.org/abs/2606.20537

机构：GitHub

作者：Liang Su

英文摘要：Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

AI 总结：研究联邦学习中客户端数据分布受决策影响的双层优化问题，提出联邦双层执行稳定点概念及两种求解方法，实验验证了稳定性阈值和元泛化提升。

链接：https://arxiv.org/abs/2606.19734

机构：Nanyang Technological University（南洋理工大学）； Zhejiang University（浙江大学）； Washington State University（华盛顿州立大学）

作者：Liangxin Qian, Chang Liu, Xuanyu Cao, Jun Zhao, Kwok-Yan Lam

英文摘要： Federated bilevel optimization is widely used for nested learning problems across distributed clients, such as federated hyperparameter tuning and meta-learning under privacy and communication constraints. Most existing formulations assume fixed client data distributions, which can be violated by performativity, where deployed decisions reshape client behavior and data collection, inducing client-specific, decision-dependent distribution shift. We study federated bilevel performative prediction, where both upper-level (UL) and lower-level (LL) objectives are evaluated under client-dependent, decision-dependent distributions. We formalize the federated bilevel performatively stable (FBPS) point under a decoupled-risk perspective and provide sufficient conditions for its existence and uniqueness. We then develop two federated methods to compute the FBPS solution: FBi-RRM, which converges linearly under a contraction condition, and FBi-SGD, a communication-efficient stochastic method based on federated hypergradient estimation with convergence guarantees under diminishing step sizes when sensitivities are sufficiently small. Experiments on strategic regression and meta strategic classification validate the predicted stability thresholds and demonstrate improved meta-generalization over non-performative baselines, and CNN-based classification further demonstrates the practical effectiveness of the proposed methods in nonconvex neural network settings.

AI 总结：针对联邦部署中标准共形风险控制（CRC）对个体机构覆盖不足的问题，提出基于风险曲线收缩的联邦CRC协议，在真实脑肿瘤数据上实现2.7/20的违规率且预测集仅扩大2.0倍。

链接：https://arxiv.org/abs/2606.20115

机构：institutetext: Dhaka, Bangladesh（达卡，孟加拉国）

作者：Nafis Fuad Shahid

英文摘要：Conformal risk control (CRC) provides distribution-free guarantees on segmentation quality by calibrating a prediction-set threshold on held-out data. In federated deployments, the standard approach pools calibration scores across sites into a single threshold. We provide the first quantification, on real multi-institutional brain tumor data (FeTS-2022, 1,251 subjects, 20 institutions), showing that this naive pooled CRC protects the average hospital but violates coverage at 40% of individual institutions, with the worst site exceeding the target false-negative rate by 7.8 percentage points. The naive alternative, per-site local CRC, largely restores coverage but inflates prediction sets by 83x, rendering them clinically useless. We propose a shrinkage-based federated CRC protocol: each site transmits only its empirical risk curve (G scalars) to a server, which computes a shrinkage-regularized threshold per site. A single hyperparameter n0 smoothly trades worst-case coverage for prediction-set efficiency; leave-one-site-out sensitivity analysis identifies n0=19, achieving 2.7/20 violations at 2.0x stretch. We further show that direct Lagrangian optimization of coverage budgets fails, concentrating risk on vulnerable hospitals, and that the finite-sample correction term is essential: removing it triples violations. The marginal CRC guarantee is preserved by construction under the stated site-mixture assumption; per-site coverage is validated across four targets with three seeds. No patient-level images, masks, or per-volume scores leave any site.

AI 总结：针对联邦图学习中客户端级和节点级模态不平衡问题，提出隐式图感知潜在语义表示合成范式FedMGS，通过可用性感知图编码器、原型引导语义合成器和可靠性校准融合机制恢复缺失模态语义，在四个任务上最高提升17.41%。

链接：https://arxiv.org/abs/2606.20382

作者：Zhengyu Wu, Hongchao Qin, Xunkai Li, Zekai Chen, Rong-Hua Li, Guoren Wang

英文摘要：MultiModal Federated Graph Learning (MM-FGL) offers a natural collaborative training paradigm, but its practical deployment is challenged by two granularities of modality imbalance. Client-level imbalance occurs when certain clients lack entire modalities, while node-level imbalance occurs when individual nodes exhibit missing visual or textual attributes. While several relevant studies exist, our investigation reveals that they predominantly target graph-agnostic or centralized scenarios, rendering them difficult to adapt directly. To address these challenges, we formalize modality-imbalanced MM-FGL as an implicit graph-aware latent semantic representation synthesis problem. This paradigm recovers missing modal semantics directly within the representation space, thereby maximizing alignment with the original data's semantic distribution and mitigating the high variance induced by missing modalities. To this end, we propose FedMGS (Federated Modality-aware Graph Synthesis), which integrates three core components. The availability-aware graph encoder prevents missing modalities from contaminating local structural propagation. The prototype-guided latent semantic synthesizer establishes cross-client semantic anchors for unavailable modalities. The reliability-calibrated semantic fusion mechanism regulates the impact of recovered latent representations prior to predictive readout. Extensive experiments on four tasks show that FedMGS consistently outperforms competitive baselines with gains up to 17.41% with best efficiency-performance tradeoff.

AI 总结：提出可预测性框架，通过攻击者预测敏感信息的能力增益来衡量隐私泄露，与差分隐私互补，并基于广义矩方法分析渐近可预测性，用于ERM输出扰动。

链接：https://arxiv.org/abs/2606.20546

机构：Cornell University（康奈尔大学）

作者：Linda Lu, Karthik Sridharan

英文摘要：Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-accuracy tradeoff. We introduce privacy via predictability, a fine-grained framework that explicitly incorporates the attacker's core knowledge, a compromised portion of the dataset generated by a stochastic process, and a specified family of queries. Predictability measures privacy leakage as the incremental gain in an attacker's ability to predict sensitive information about unknown individuals after observing the algorithm's output, beyond what can already be inferred from the compromised data. We show that predictability and DP are generally incomparable: each can be small while the other is large. However, in the worst-case regime where all but one individual is compromised, and all binary queries are considered sensitive, predictability implies mutual-information DP. More generally, predictability provides a finer-grained privacy metric tailored to specific sensitive information and specific attacker models. We introduce a general framework, using the generalized method of moments (GMM), to analyze asymptotic predictability when the compromised data is generated by a stationary, ergodic, mixing process. Using this analysis, we derive a predictability-calibrated output perturbation scheme for ERM. Our approach is complementary to DP and can be used alongside DP to provide fine-grained privacy control.

AI 总结：提出自由能签名（Fes）作为谱描述符，将注意力拉普拉斯视为哈密顿量并提取热力学势和随机矩阵理论谱形因子，用于检测LLM幻觉，无需训练即可实现高AUROC。

链接：https://arxiv.org/abs/2606.19404

机构：Talan Research & Innovation Center（Talan研究与创新中心）

作者：Salim Khazem

英文摘要：Hallucination detection in large language models (LLMs) is deployment-critical, and recent work shows that the spectrum of attention-derived graph Laplacians carries strong signal about reasoning quality. Prior spectral diagnostics, however, summarize the Laplacian spectrum by a handful of eigenvalues or hand-picked scalars, leaving most of its structure unused. We propose Free-Energy Signatures (Fes), a spectral descriptor that treats each layer's attention Laplacian as a Hamiltonian and extracts its thermodynamic potentials partition function, free energy, spectral entropy, heat capacity together with the random-matrix-theory (RMT) spectral form factor. We prove three results: (i)~Lipschitz stability of Fes under attention perturbation; (ii)~an expressiveness result showing that Fes enriches finite spectral summaries and approximates moment-derived spectral functionals under explicit regularity and grid-resolution assumptions; and (iii)~a finite-sample PAC bound on the AUROC of a training-free detector built from Fes. Empirically, across six open-weight LLMs and six benchmarks, a lightweight probe on Fes descriptors achieves the strongest aggregate AUROC among attention-spectral baselines, improving over LapEig by $+6.5$ AUROC points and over GoR-4 by $+2.4$ points on average, while requiring no update to the underlying LLM. In the fully unsupervised setting, an RMT-deviation score achieves mean AUROC $0.71$, providing a label-free but weaker detector. A complementary RMT analysis shows that correct generations exhibit more Wigner-Dyson like spectral statistics, whereas hallucinations exhibit more Poisson-like statistics. The anonymized code and config are provided in the supplementary material.

AI 总结：针对概率机器学习中回归问题的不确定性量化，提出基于最高密度区域体积的QUEST框架，满足单调性和平移不变性公理，在选择性预测基准上优于方差和微分熵。

链接：https://arxiv.org/abs/2606.19569

机构：Northeastern University London（东北大学伦敦校区）

作者：Sam Goring, Tom Kuipers, Nicola Paoletti, David S. Watson

英文摘要：Uncertainty quantification (UQ) is essential for reliable decision-making in safety-critical applications in probabilistic machine learning. For regression problems, dominant scalar UQ approaches - notably, those based on proper scoring rules - measure uncertainty via pointwise predictive risk. This can lead to counterintuitive results when the target statistic is not the conditional expectation. We propose an alternative framework, in which uncertainty is characterised by the volume of the most probable subset of a distribution's support. QUEST (Quantifying Uncertainty via highest dEnSiTy regions) is a novel approach to UQ based on the concentration of Lebesgue measure at a distribution's peak(s), evaluated at one or more values of a robustness parameter $\alpha$. We establish connections between our measures and classical statistics from information theory and economics. We show that, unlike popular alternatives based on proper scoring rules, QUEST measures of epistemic and aleatoric uncertainty satisfy a set of axioms adapted from the UQ literature, including monotonicity under distributional spread and invariance to location shifts. Selective prediction benchmarks confirm that QUEST performs favourably against standard measures such as variance and differential entropy.

AI 总结：研究证明马氏余弦相似度与OOD AUROC存在线性关系，提供理论解释并验证其作为线性探针比较指标的有效性。

链接：https://arxiv.org/abs/2606.19603

机构：Columbia University（哥伦比亚大学）； Stanford University（斯坦福大学）； Schmidt Sciences（施密特科学）

作者：Zhuofan Josh Ying, Peter Hase, Nikolaus Kriegeskorte

英文摘要：Linear probes are widely used in interpretability research and often compared by cosine similarity. The Mahalanobis cosine similarity (MCS) between two directions, which reweights the inner product by test data covariance, is a natural task-aware refinement. Ying et al. (2026) report that a probe's MCS to a reference probe trained on the out-of-distribution (OOD) data near-perfectly linearly predicts the probe's OOD AUROC (R^2 = 0.98). Here, we extend this empirical finding across models, layers, and concept domains, and prove this general phenomenon in closed form: For balanced classes whose projections are Gaussian, OOD AUROC and MCS to the reference probe are linear because both are sigmoid-shaped functions of the probe's signal-to-noise ratio (SNR) on the test data. The theory also predicts when this linearity fails, which we verify empirically. MCS offers a theoretically grounded and empirically effective alternative to Euclidean cosine similarity for comparing linear probes.

AI 总结：提出不确定性感知奖励建模（UARM），通过分位数保形预测校准不确定性并利用异方差方差分解重加权GRPO优势，以缓解奖励黑客问题，提升对齐质量。

链接：https://arxiv.org/abs/2606.19818

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

作者： Licheng Pan, Haocheng Yang, Haoxuan Li, Yichen Sun, Yunsheng Lu, Shijian Wang, Lei Shen, Yuan Lu, Zhixuan Chu, Hao Wang

英文摘要：Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards. However, this pipeline faces two fundamental challenges: (1) reward models cannot signal when their predictions are unreliable, since they usually act as deterministic point estimators; and (2) modern group-based policy optimization can amplify unreliable reward signals, as exemplified by GRPO's uniform treatment of rewards during advantage computation. As policies explore increasingly diverse responses, these two limitations create a critical vulnerability: unreliable reward estimates may be granted disproportionate influence, triggering severe reward hacking. We propose Uncertainty-Aware Reward Modeling (UARM), which equips reward models with calibrated uncertainty via quantile-based conformal prediction and reweights GRPO advantages through heteroscedastic variance decomposition. Experiments across HelpSteer, UltraFeedback, and PKU-SafeRLHF demonstrate that UARM significantly improves reward model calibration, reduces reward hacking, and enhances downstream alignment quality compared to standard GRPO and uncertainty-agnostic baselines.

AI 总结：提出一种轻量级防御框架，通过基于输入统计分布的伪特征填充增加输入维度，使对抗攻击因扰动不可转移和填充结构不可预测而计算不可行，显著提升深度神经网络在电网状态估计中的鲁棒性。

链接：https://arxiv.org/abs/2606.20415

机构：University of Tennessee（田纳西大学）； The University of Illinois at Springfield（伊利诺伊大学斯普林菲尔德分校）； Clemson University（克莱姆森大学）

作者：Farhin Farhad Riya, Shahinul Hoque, Yingyuan Yang, Jinyuan Sun, Kevin Tomsovic

英文摘要：Deep Neural Networks DNNs have achieved remarkable accuracy in various tasks including their application in CyberPhysical Systems CPS for detecting False Data Injection Attacks FDIA during critical operations However the unique infrastructure of CPS makes DNNs vulnerable to exploitation by attackers aiming to evade detection Additionally the distinct nature of CPS presents challenges for conventional defense mechanisms against FDIA This paper proposes an innovative defense framework that strengthens DNNs against such attacks by introducing an additional input layer that performs padding in the input samples using pseudofeature values derived from the inputs statistical distribution This padding increases the input dimensionality in a randomized and dataaware manner making adversarial attacks computationally infeasible due to the nontransferable nature of crafted perturbations and the unpredictability of the padded structure Our method is lightweight modelagnostic and requires no modifications to the core architecture making it highly deployable in realworld CPS settings We evaluated our framework on critical power grid applications such as state estimation using the IEEE 14bus 30bus 118bus and 300bus systems Experiments under adversarial settings demonstrate that our padding strategy significantly improves model robustness with negligible impact on performance and effectively mitigates attacks that would otherwise bypass conventional defenses

AI 总结：本文提出一种确定性算法，实现多校准的极小化最优样本复杂度，并推广到结果不可区分性，解决确定性预测器是否必要的问题。

链接：https://arxiv.org/abs/2606.20557

机构：University of Pennsylvania（宾夕法尼亚大学）

作者：Georgy Noarov, Aaron Roth

英文摘要：A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweighting contexts by each $g \in G$. It is a useful property for many downstream applications and is a basic desideratum of trustworthy machine learning. Before this work, all predictors known to attain the minimax-optimal $\widetilde O(\varepsilon^{-3})$ sample complexity rate for $\varepsilon$-multicalibration were randomized, while deterministic predictors were known only with substantially worse sample complexity. Whether randomization is necessary for optimal sample complexity in multicalibration was explicitly asked by [CLNR26] and implicitly in several prior works. We resolve this open problem by giving a minimax-optimal multicalibration algorithm that outputs a deterministic predictor. We then generalize the algorithm to produce optimal deterministic predictors that satisfy outcome indistinguishability (OI) with respect to finite or finitely covered collections of tests. As an application, this also gives deterministic omnipredictors and panpredictors with optimal sample complexity, resolving open problems posed by [OKK25] and [BHHLZ25].

AI 总结：提出一种二级结构感知的图神经网络，通过增强残基节点表示并基于能量过滤的氢键构建边，以捕获局部结构上下文和长程耦合，在蛋白质基准上取得一致改进并增强生物学可解释性。

链接：https://arxiv.org/abs/2606.19374

机构：College of Computing, UM6P（穆罕默德六世理工大学计算机学院）

作者：Mohamed Mouhajir, Limei Wang, El Houcine Bergou, Hajar El Hammouti, Lamiae Azizi, Dongqi Fu

英文摘要： Graph-based representations are widely used in protein modeling, yet many existing approaches rely primarily on sequence adjacency or geometric proximity, which only partially reflect the principles governing protein folding. Proteins instead adopt complex three-dimensional conformations organized around secondary structure elements, such as $\alpha$-helices and $\beta$-sheets, which encode recurring local motifs and stabilizing hydrogen-bond interactions. In this work, we introduce a secondary-structure-aware graph neural network for protein representation learning. Residue-level node representations are augmented with secondary structure assignments, and graph edges are constructed from hydrogen-bond interactions filtered by their energetic strength. This design enables the model to capture both local structural context and long-range couplings that are central to protein stability and function. We evaluate the proposed approach on commonly used protein benchmarks and observe consistent improvements over existing graph-based methods. In addition, the resulting graph representations offer enhanced biological interpretability, as the learned connectivity aligns with established structural motifs. These findings suggest that incorporating secondary structure and energy-filtered hydrogen-bond topology provides an effective inductive bias for protein representation learning. The code is released at this https URL

AI 总结：提出使用Delaunay三角剖分等邻近图作为图神经网络输入，通过消息传递捕捉沙尘源排放的时空动态，相比随机图和LSTM模型显著提升预测精度。

链接：https://arxiv.org/abs/2606.19825

机构：Amirkabir University of Technology（阿米尔卡比尔理工大学）； University of Tehran（德黑兰大学）

作者：Maryam Sanisales, Zahed Rahmati, Ali Darvishi Boloorani, Ali Vefghi

英文摘要：Accurate prediction of dust source emissions is critical for mitigating the significant environmental and health hazards posed by dust storms. Traditional forecasting methods often struggle to capture the complex spatiotemporal dynamics of these phenomena. In this paper, we demonstrate that proximity graphs enable Graph Neural Networks (GNNs) to effectively model the intricate spatial and temporal relationships between data points. Specifically, we use proximity graphs--such as Delaunay triangulation, Gabriel graph, k-Nearest Neighbor graph, and Yao graph--as the input for GNNs (including GraphSAGE, Graph Convolutional Networks, and Graph Attention Networks) to perform message passing. Our approach highlights the effectiveness of integrating proximity graphs with GNNs for robust and accurate dust source forecasting. To emphasize the importance of proximity graph representations, we compare our method against GNNs using random graphs for message passing. The results show that GNNs with proximity graphs significantly outperform those with random graphs and are also far superior to Long Short-Term Memory (LSTM) model in dust source emission forecasting.

AI 总结：本研究首次探索将图深度学习应用于建筑足迹简化（节点移动预测）和聚合（链接预测），评估了GCN、GAT和GraphSAGE等架构，发现GraphSAGE在链接预测上表现较好，但节点移动预测仍具挑战，且聚合比简化更复杂。

链接：https://arxiv.org/abs/2606.19956

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Zhejiang University（浙江大学）； Mainz University of Applied Sciences（美因茨应用科学大学）

作者：Yanning Wang, Zhiyong Zhou, Zhouyu Liu, Mengni Yu, Yu Feng

英文摘要：Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-based deep learning to both tasks, reformulating simplification as node movement prediction and aggregation as link prediction within a unified graph learning framework. We evaluate representative graph neural network architectures (GCN, GAT, and GraphSAGE) on multi-scale building datasets, showing that GraphSAGE demonstrates relative strengths in link prediction accuracy, while also revealing persistent challenges in precise node movement prediction. Beyond quantitative performance, the results highlight that aggregation poses greater complexity and challenges than simplification, underscoring the difficulty of capturing higher-level spatial relationships in map generalization with current deep learning approaches. Although limitations such as data imbalance and the need for post-processing remain, the study provides valuable insights and methodological directions for advancing automated map generalization with deep learning approaches.

AI 总结：针对图结构纠缠导致的分类性能下降，提出边界嵌入塑造模块，通过自适应对比学习选择性抑制决策边界处的虚假结构噪声，提升节点分类和链接预测精度。

链接：https://arxiv.org/abs/2606.20283

机构：Yunnan Normal University（云南师范大学）； Adelaide University（阿德莱德大学）； The University of New South Wales（新南威尔士大学）

作者：Jiaqing Chen, Zidu Yin, Yichao Cai, Yuhang Liu, Zhen Zhang, Dong Gong, Javen Qinfeng Shi

英文摘要：Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near class boundaries in the embedding space, where amplified structural noise blurs decision boundaries and destabilizes predictions. Existing robust GNN methods largely treat all nodes uniformly, ignoring boundary vulnerabilities. In this paper, to improve classification performance, we tackle graph structural disentanglement by identifying boundary-region entanglement as the primary bottleneck and propose Boundary Embedding Shaping (BES), an adaptive contrastive learning GNN plug-in module that selectively suppresses spurious structural noise at decision boundaries with minimal model parameter perturbation. Extensive experiments demonstrate that BES consistently improves boundary discrimination and outperforms existing leading methods. Notably, BES boosts GCN performance by an average of 3.3% in node classification (up to 5.0% on WikiCS) and achieves superior accuracy in link prediction.

AI 总结：提出LOKI方法，通过希尔伯特-施密特独立性准则动态选择层，并将梯度更新投影到模型权重的零空间，实现无需访问旧知识的终身知识编辑，平均准确率提升14%。

链接：https://arxiv.org/abs/2606.19679

机构：Department of Electrical and Computer Engineering（电气与计算机工程系）

作者：Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis, Jennifer Dy

英文摘要：Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserving acceptable performance on past knowledge. One unresolved challenge is that existing methods modify a fixed set of layers for all new knowledge samples, reducing flexibility and increasing catastrophic forgetting. Another is requiring access to previous knowledge and extensive pre-processing to obtain data statistics. To address these challenges, we introduce LOKI, a novel approach that uses dynamic layer selection based on the Hilbert-Schmidt Independence Criterion and projects gradient updates onto the null-space of the model weights, bypassing the requirement for previous knowledge access. We show that LOKI achieves superior performance to existing approaches across a wide variety of experiments, achieving up to a 14\% improvement in average accuracy.

AI 总结：通过可控玩具框架研究持续学习中的遗忘机制，发现叠加随时间增加但任务边界处有瞬降，高稀疏性增加叠加但不必然导致遗忘，任务级有效秩随稀疏性增长。

链接：https://arxiv.org/abs/2606.20431

机构：Rochester Institute of Technology（罗切斯特理工学院）； Wrocław University of Science and Technology（弗罗茨瓦夫科技大学）

作者：Jan Wasilewski, Jędrzej Kozal, Michał Woźniak, Bartosz Krawczyk

英文摘要：Continual learning (CL) systems often forget previously acquired knowledge, yet the mechanisms driving forgetting remain hard to isolate in practice because real datasets entangle many factors. We present a controlled, toy-world framework that makes these mechanisms observable and testable. Using a synthetic generator-separator pipeline, we define ground-truth latent features, build tasks with tunable sparsity and overlap, and introduce measurable quantities for representation strength and superposition (directional overlap among features). We then study retention dynamics-the temporal change of representation strength by fitting sparse dynamical relations (via SINDy) between retention, superposition, and exposure history. A complementary task-level analysis based on effective rank characterizes how representational capacity is allocated across tasks. Our controlled experiments yield three takeaways. (1) Superposition tends to increase over time with transient dips at task boundaries, suggesting boundary-specific interference rather than steady drift. (2) Higher feature sparsity induces more superposition yet does not inevitably cause forgetting; when representations remain strong, forgetting can be reduced despite overlap. (3) Task-level effective rank grows with sparsity, indicating broader capacity usage under sparse regimes. Together, these results nuance the common intuition that more superposition leads to more forgetting by showing that overlap interacts with representation strength and capacity allocation. Our toy analysis provides falsifiable hypotheses and diagnostic tools for CL.

AI 总结：提出多任务上下文学习框架，通过将先验信息表示为上下文数据集前缀，训练Transformer实现分层贝叶斯预测推理，在多种分布偏移下匹配最优贝叶斯性能且速度提升数个数量级。

链接：https://arxiv.org/abs/2606.20538

机构：New York University（纽约大学）

作者：Qingyang Zhu, Eric Karl Oermann, Kyunghyun Cho

英文摘要：Bayesian predictive inference provides a principled framework for uncertainty quantification, data efficiency, and robust generalization. However, exact inference is often intractable, and scalable approximations may remain computationally expensive or require restrictive modeling assumptions that degrade predictive performance. Prior-Data Fitted and in-context models have recently emerged as an amortized alternative by learning to map datasets directly to predictive distributions, but existing approaches are tightly coupled to the support of the training prior and lack explicit mechanisms for adapting to new priors at test time, resulting in limited robustness under distribution shift. We introduce a multi-task in-context learning framework for amortized hierarchical Bayesian predictive inference that explicitly represents prior information as a prefix of in-context datasets. A transformer trained on sequences of prior and target tasks learns to adapt its predictions across families of priors. On a suite of evaluations with increasing difficulty, including out-of-meta-distribution priors and priors with high-dimensional latent structures, our method matches oracle Bayesian predictors while being orders of magnitude faster. We further demonstrate its practical relevance on a real-world spatiotemporal temperature prediction benchmark. Code is available at this https URL.

AI 总结：提出将NP难的DPP-MAP选择问题转化为Stiefel流形上的连续优化，通过非线性特征值问题（NEPv）的自洽场迭代实现近线性时间求解，适用于大规模数据选择。

链接：https://arxiv.org/abs/2606.19411

机构：Hong Kong Baptist University（香港浸会大学）； TadReamk Limited（TadReamk有限公司）

作者：Richard Yi Da Xu

英文摘要：Selecting a small, diverse, high-quality subset from a massive pool of candidates is a recurring primitive in modern machine learning -- data curation and coreset selection for training and fine-tuning large models, active-learning batch acquisition, prompt and exemplar selection for in-context learning, retrieval diversification, and experimental design. Determinantal Point Processes (\DPP s) give a principled, well-calibrated notion of diversity for this task, but their \emph{MAP} objective -- pick a size-$k$ subset $S$ maximizing $\logdet(L_S)$ -- is NP-hard, and the standard greedy and sampling algorithms scale superlinearly in the ground-set size $n$. This cost is prohibitive precisely in the data-centric regime where diversity matters most, where $n$ ranges over millions to billions of candidate examples, features, or embeddings. We recast \DPP-MAP as a continuous optimization problem over the Stiefel manifold, and show that its first-order optimality conditions form a \emph{Nonlinear Eigenvalue Problem with eigenvector dependency} (\NEPv) of a previously unstudied form. This \NEPv\ admits a self-consistent field (\SCF) iteration with a spectral-gap-based local contraction guarantee, giving a principled iterative solver where the diversity objective drives an eigenvector-dependent operator. The resulting algorithm, \OurMethod, requires only matrix-vector products with the kernel and runs in time $O\!\big((ndk+nk^2)\,t\big)$ for a small number of iterations $t$, scaling near-linearly in $n$ and integrating directly with low-rank and feature-map kernels common in ML. This paper focuses on the relaxation, solver, and scaling analysis; full real-data benchmarking is left to a planned empirical study.

AI 总结：提出MortarBench基准，通过金融数据合成与变异管道生成覆盖边缘案例的示例，评估大语言模型在贷款发起任务中的表现，发现模型准确率低且存在偏见，并引入CRIT校准框架提升准确率至80.5%。

链接：https://arxiv.org/abs/2606.19416

机构：Columbia University（哥伦比亚大学）； Tidalwave

作者：Matthew Toles, Yunan Lu, Manav Munjal, Bojun Liu, Yuanhao Deng, Stephanie Selig, Derek Rindner, Cheng Li, Zhou Yu

英文摘要：Loan origination is the process by which a lender creates a new loan, from application and underwriting through approval and funding. This process serves a critical role in evaluating the eligibility and level of risk posed by an applicant. Recently, firms have begun using mortgage loan agents to augment human loan officers, despite a lack of any public benchmark. To fill this gap, we present MortarBench, a loan origination agent benchmark. MortarBench uses a financial data synthesis and mutation pipeline to generate examples with broad edge case coverage that match real-world distributions and questions. We find that state-of-the-art large language models (LLMs) perform poorly, with closed-source models achieving at most 77.1\% exact match accuracy. We also discover systematic biases in LLM perception of foreignness related to non-English names. Noting these weaknesses, we introduce CRIT, a confidence calibration framework. Our method increases accuracy to 80.5\% while improving risk management steering and reducing bias.

AI 总结：针对电子健康记录离散化导致模型泛化性差的问题，提出基于真实临床轨迹的离线强化学习数据集Insulin4RL，包含375,000+决策和12,209名患者，用于评估模型在真实采样假设下的性能。

链接：https://arxiv.org/abs/2606.19481

机构：Institute of Health Informatics（健康信息学研究所）； University College London（伦敦大学学院）

作者：Thomas Frost, Steve Harris

英文摘要：Offline reinforcement learning (ORL) offers the potential to improve the quality of clinical decision-making using historical electronic health record (EHR) data. Current training and evaluative practices in this field rely heavily on EHR datasets that have been temporally discretised into fixed, regular time intervals. Discretisation creates fictional representations of complex clinical scenarios and compromises the generalisability of retrospective model evaluations. In this paper, we introduce Insulin4RL, a healthcare ORL dataset featuring naturally irregular inputs and actions from real clinical trajectories. Derived from MIMIC-IV, Insulin4RL comprises over 375,000 labelled decisions across 12,209 patients requiring insulin infusion titration in the Intensive Care Unit. The dataset can thus be used for research into ORL model performance under realistic clinical sampling assumptions. We provide a description of the dataset's structure and characteristics, baseline performance metrics using model-free offline reinforcement learning, and a standardised evaluation protocol using fitted Q-evaluation. We conclude with suggested areas for future research that could be addressed using this resource.

AI 总结：本文研究KL散度等保真度指标在量化语言模型部署中与下游基准分数的相关性，发现整体强相关但在近基线区域失效，归因于KL散度主要衡量分歧量而非方向。

链接：https://arxiv.org/abs/2606.19558

机构：ByteShape； University of Toronto（多伦多大学）； Vector Institute for Artificial Intelligence（向量人工智能研究所）

作者：Miloš Nikolić, Ali Hadi Zadeh, Enrique Torres Sanchez, Andreas Moshovos

英文摘要： Fidelity metrics, such as per-token KL divergence (KLD) against a high-precision reference, are often used in practice as low-cost proxies for benchmark quality. We test this practice on a 28-quant cohort of Qwen3.6-35B-A3B and a 41-quant cohort of Devstral-Small-2-24B, evaluated across a suite of downstream benchmarks. We find that KLD is strongly correlated with benchmark score over the full cohort ($\rho=-0.72$ on Qwen and $\rho=-0.86$ on Devstral, both with $p<0.001$). However, this relationship collapses to non-significance in the near-baseline silent zone ($\rho=+0.00$ on Qwen and $\rho=-0.24$, $p=0.36$, on Devstral). This collapse persists across 14 measurement variants, including different KLD aggregations, perplexity formulations, top-1 agreement, calibration corpora, and context lengths. At the per-prompt level, KLD has only weak failure-prediction power on code, with failed-vs-passed geometric-mean ratios in $[1.08,1.22]$ across five models on LiveCodeBench, and fails as a cross-model router, achieving only $42.3\%-49.4\%$ accuracy on disagreement prompts. We trace the collapse to a structural decomposition: KLD primarily measures the volume of disagreement with the reference, with silent-zone composite $\rho=+0.94$ ($p<0.001$) on Qwen and $+0.55$ ($p=0.03$) on Devstral, while its relationship to the direction of those disagreements is weak and task-conditional.

AI 总结：提出IHBench基准，评估语音代理在结构化工作流中处理中断后的恢复能力，涵盖任务完成和恢复质量两个维度，实验表明闭源模型比开源模型更鲁棒。

链接：https://arxiv.org/abs/2606.19595

机构：Boson AI

作者：Ahmad Salimi, Wentao Ma, Yuzhi Tang, Dongming Shen, Mu Li, Alex Smola

英文摘要：Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timing of interruptions: barge-in detection, endpointing, and turn-taking dynamics. They leave unmeasured what happens after the interruption: does the agent resume the workflow at the correct step? Does it address the user's interjection? Does it avoid re-delivering content the user already heard? We introduce IHBench (Interruption Handling Benchmark), a benchmark that evaluates post-interruption recovery in voice agents executing state-machine-driven workflows across 10 enterprise domains. Six interruption types are injected at controlled points mid-utterance, with per-interruption evaluation rubrics generated alongside the data. Each interruption is scored on two axes: task fulfillment and recovery quality. We evaluate 27 audio-language model configurations from OpenAI, Google, and the open-weight community. Models vary widely, and recovery quality depends strongly on the interruption type. Across our experiments, closed-weight models are consistently more robust to interruptions than open-weight ones: they win far more often on task fulfillment, degrade roughly 3.3x more slowly as conversations grow longer, and show no audio-versus-text modality gap, whereas the open-weight models lose ground on all three. A human study validates the LLM judge against human annotators, and a cross-benchmark analysis against AudioMultiChallenge indicates that recovery quality is a largely distinct capability axis.

AI 总结：本文系统审查了基于串联质谱的分子发现中机器学习模型的评估问题，以MassSpecGym基准为例，发现26篇论文中至少17篇存在数据泄露、捷径学习和实现错误三类问题，并通过实验量化影响，提出改进建议并发布MassSpecGym v1.5。

链接：https://arxiv.org/abs/2606.19624

机构：Massachusetts Institute of Technology（麻省理工学院）； Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague（捷克信息学、机器人学与自动化捷克技术大学）； Enveda Biosciences（Enveda 生物科技）； Tufts University（塔夫茨大学）

作者：Hongxuan Liu, Roman Bushuiev, Ivy Lightheart, Mrunali Manjrekar, Anton Bushuiev, Magdalena Lederbauer, Filip Jozefov, Yinkai Wang, Soha Hassoun, Josef Sivic, James Taylor, Runzhong Wang, David Healey, Tomáš Pluskal, Connor W. Coley

英文摘要：Reliable benchmarking is critical for developing machine learning models for tandem mass spectrometry (MS/MS) based molecule discovery. Subtle issues in experimental design and model evaluation procedures can degrade the trustworthiness of such benchmarks and lead to erroneous conclusions. We conduct a thorough review of model evaluation issues in the recent MS/MS machine learning literature, using the standard MassSpecGym benchmark suite as a case study to illustrate the impact of these issues. We find evaluation issues in at least 17 of 26 papers reporting MassSpecGym benchmark results in the first year of its adoption. We isolate three classes of failures: (i) data leakage, (ii) shortcut learning, and (iii) implementation bugs and metric divergence. Through extensive experimentation and code replication, we quantify the impact of these issues and show how they corrupt the evaluation standards MassSpecGym was designed to enforce. We distill our findings into recommendations generalizable to MS/MS challenges, benchmarks, and custom evaluation setups. We also release MassSpecGym v1.5, an implementation of our recommendations in the MassSpecGym benchmarking suite which addresses the failure modes identified in this audit. MassSpecGym v1.5 is publicly available at this https URL.

AI 总结：发现pass@k在数学推理难度估计中存在盲点，通过激活嫁接的确定性采样可恢复10.3-22.9%的零解样本，揭示结构可识别性。

链接：https://arxiv.org/abs/2606.19636

机构：Sapienza University of Rome（罗马大学）

作者：Luca Zhou, Sajel Shah, Emanuele Rodolà, Roberto Dessì

英文摘要： Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with verifiable rewards, math data curation, synthetic curricula, and verifier training. We show this proxy has a persistent blind spot on its hardest stratum: on the eight free-form math cells we test (GSM8K and MATH across four open-weight models), 10.3-22.9% of the examples that no sampling seed solves in six tries are instead solved at matched compute by a six-chain deterministic regime. These are greedy decoding plus five cheap residual-stream perturbations applied via activation grafting, while greedy alone solves at most 6% on these math cells. Recovery scales with the additional budget, across perturbations whose mechanistic distinctness we verify across all twelve cells (cross-kind fix-set Jaccard <= 0.47 in every setup). Activation grafting is used as an intervention on internal representations, not a decoding method; we use it purely as a diagnostic and diversification tool, and our recovered items show that the pass@k= 0 % stratum is structurally identifiable in the residual stream rather than that the unmodified model reaches them under ordinary inference.

AI 总结：提出自适应尺度处理模块，通过学习自适应尺度因子保留语义区分性并减少逆缩放误差，在基金销售数据集上提升主流预测模型性能。

链接：https://arxiv.org/abs/2606.20010

机构：College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院）； Ant Group（蚂蚁集团）

作者：Xu Zhang, Zhengang Huang, Yunzhi Wu, Xun Lu, Erpeng Qi, Yunkai Chen, Zhongya Xue, Peng Wang, Wei Wang

英文摘要：Current time series forecasting (TSF) research predominantly focuses on scale-homogeneous data, where different time series share similar numerical magnitude ranges. However, in real-world industrial scenarios such as financial product sales, different time series often differ by orders of magnitude (scale heterogeneity). Since these series share similar temporal patterns, joint modeling is desirable for better data utilization, yet existing scaling methods either compress low-scale signals (global normalization) or destroy semantic discriminability and amplify inverse-scaling errors (window-based scaling). This paper proposes a self-Adaptive Scale-handling (AS) module that learns adaptive scale factors tailored to each input, preserving semantic discriminability while reducing inverse-scaling errors. AS consists of Scale Calibrating (SC), which calibrates prior mean scaling factors through neural networks, and Scaling Selection (SS), which decides whether to apply calibration or retain the original factor, avoiding over-calibration. Experiments on real-world fund sales datasets from Ant Fortune and Alipay show that AS seamlessly integrates into popular TSF models and consistently improves their performance. The code and dataset are available at the link this https URL.

AI 总结：本文从理论上分析概念漂移特征，并评估多种漂移检测算法在合成和真实数据集上的性能，旨在增强对漂移检测器行为及其适用性的理解。

链接：https://arxiv.org/abs/2606.20216

机构：Department of Computer Science, University of Regina（里贾纳大学计算机科学系）

作者：Md Moman Ul Haque Khan, Samira Sadaoui

英文摘要：Machine learning algorithms deployed for evolving streaming environments must handle the non-stationary data distributions, commonly referred to as concept drift. The presence of concept drift poses a major challenge for many real-world applications because it can severely degrade their predictive performance, hindering their ability to support robust decision-making. Consequently, the timely and efficient detection of drift events is critical for sustaining high accuracy over time. This study examines theoretically the concept drift characteristics and numerous drift detection algorithms across several categories. Furthermore, we evaluate their performance on both synthetic and real-world datasets exhibiting diverse streaming scenarios and drift characteristics, such as abrupt and gradual changes. This study aims to enhance understanding of the complex notion of concept drift characteristics and behavior of drift detectors, along with their applicability to diverse contexts.

AI 总结：提出基于临界平均场渗流簇的层次函数合成数据集，具有稀疏、分形和幂律分布特性，支持几乎线性时间算法生成任意规模数据，可用于评估可解释性方法。

链接：https://arxiv.org/abs/2606.20347

机构：Aryeh Brill； Tom Ingebretsen Carlson

作者：Aryeh Brill, Tom Ingebretsen Carlson

英文摘要：Neural networks learn features that reflect the hierarchical, multi-scale structure of natural data. Synthetic datasets used to evaluate interpretability methods typically lack this structure, limiting their value as realistic toy models. To close this gap, we introduce a family of synthetic datasets consisting of hierarchical functions defined on critical mean-field percolation clusters embedded in a high-dimensional data space. The percolation data consists of sparse, low-dimensional fractal clusters with a power-law size distribution. Latent variables modeling a taxonomic hierarchy generate each data point's target value. The data model is analytically tractable with known critical exponents that fix its properties without requiring hyperparameter tuning. We leverage a mapping between percolation clusters, random trees, and additive coalescence to propose an almost linear-time algorithm to jointly sample a random tree and its hierarchical latent decomposition, enabling data generation at arbitrary scale. Using probing experiments, we find that the model's ground-truth latent variables can be linearly decoded from neural network activations. Together, sparsity, self-similarity, power-law statistics, and analytical tractability make critical percolation a principled testbed for interpretability research.

AI 总结：提出基于JAX加速的安全RL基准CRAX，利用MJX物理引擎实现高达100倍加速，包含6个环境套件和3个智能体任务，评估6种方法揭示性能与安全权衡。

链接：https://arxiv.org/abs/2606.20376

机构：Eindhoven University of Technology（埃因霍温理工大学）

作者：Tristan Tomilin, Mourad Boustani, Mickey Beurskens, Thiago D. Simão

英文摘要：Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing safety benchmarks with high-fidelity 3D physics remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine with realistic 3D dynamics, CRAX leverages vectorized operations and hardware acceleration, yielding up to ~100x speedups over comparable CPU-based safety benchmarks. The benchmark features six environment suites and three agent-specific tasks, each spanning three difficulty levels. Evaluating six popular safe RL methods shows that no single approach dominates across all tasks, and reveals the trade-offs between performance and safety. We find that curriculum learning across difficulty levels and safety transfer can improve performance over direct training in harder settings.

AI 总结：提出无需人工标注的对话生成框架，利用主题和风格属性增强多样性，并设计两种后处理风格化模型，实验表明风格多样性比主题多样性更关键，性能可达人工标注数据的93.3%。

链接：https://arxiv.org/abs/2606.20400

机构：University of Amsterdam（阿姆斯特丹大学）

作者：Zahra Abbasiantaeb, Zeno Belligoli, Omar Essam, Mohammad Aliannejadi

英文摘要：Generating high-utility synthetic data for intent classification typically requires human-annotated seed data, which is often unavailable in fast-paced industrial settings. In this paper, we propose a framework for synthetic dialogue generation that works entirely without human-annotated data, relying solely on intent definitions. Our proposed dialogue generation framework utilizes two different types of topic and style attributes to improve data diversity. Also, we propose two novel post-hoc stylization models called Univ and Exam to transform synthetic LLM-generated utterances into more varied, human-like linguistic styles. To enhance data quality, we utilize an LLM-as-a-judge filtering process. Experimental results on both industrial and public datasets demonstrate that the proposed approach achieves up to 93.3% of the performance obtained using human-annotated training data. Crucially, the findings reveal that style diversity is more critical than topic diversity for synthetic data utility, as it prevents models from learning spurious stylistic correlations. Furthermore, the study shows that incorporating style attributes during the generation process is more effective than post-hoc style adaptation.

AI 总结：针对多敏感属性交叉群体的偏差问题，提出在覆盖约束下扩展偏差缓解框架，通过整数线性规划优化缓解策略，权衡偏差近似误差与数据效率，并刻画公平的代价。

链接：https://arxiv.org/abs/2606.20461

机构：Khoury College of Computer Sciences, Northeastern University（东北大学库里计算机科学学院）； Cheriton School of Computer Science, University of Waterloo（滑铁卢大学切里顿计算机科学学院）

作者：Bruno Scarone, Alfredo Viola, Renée J. Miller

英文摘要：Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender. This stems in part from two interrelated challenges: the lack of principled measures for quantifying bias (potentially intersectional), and insufficient representation of intersectional subgroups in training data. We extend a recent bias mitigation framework to incorporate coverage constraints that enforce sufficient representation across groups, including intersectional subgroups. Since achieving exactly zero bias for all groups may not be data efficient (meaning it may require large amounts of data), our solution trades small approximation errors in bias for greater data efficiency while satisfying coverage constraints. We also formulate bias mitigation as an integer linear program that optimizes over all mitigation strategies, and characterize the price of fairness, the minimum data modification cost, as a function of fairness tolerance. This is essential both for legal compliance, where regulations may mandate specific fairness thresholds, and for data governance, enabling practitioners to make informed trade-offs between bias reduction and data modification (particularly, data purchasing) costs. We evaluate our techniques on publicly available datasets, demonstrating that bias mitigation via our framework preserves predictive accuracy across multiple classifiers, and that coverage constraints, while motivated by statistical considerations, are essential for preserving downstream ML performance.

AI 总结：提出Guard框架，通过上下文路由器和不确定性门控温度机制，从多个分布偏移的基础模型中蒸馏知识，训练轻量级预测器，在气象、碳通量等四个领域降低RMSE。

链接：https://arxiv.org/abs/2606.19363

机构：Colorado State University（科罗拉多州立大学）

作者：Rupasree Dey, Abdul Matin, Nathan Orwick, Yao Zhang, Shrideep Pallickara, Sangmi Lee Pallickara

英文摘要： The deployment of Time-Series Foundation Models (TSFMs) in physical sciences is hindered by a critical trade-off: while these models encode rich, universal temporal dynamics, they suffer from severe distributional misalignment when applied zero-shot to specific scientific domains, and their computational cost prohibits deployment in edge-computing sensor networks. We address a fundamental challenge: How can we extract latent structural knowledge from misaligned foundation models (FM) to train lightweight, specialized forecasters? We propose Gated Uncertainty-Aware Routing for Distillation (Guard), a novel framework that reframes multiteacher distillation as an instance-wise decision process with two adaptive mechanisms: (1) a Contextual Router that dynamically selects the most relevant teacher based on local input statistics, exploiting complementarity across diverse foundation models; and (2) an Uncertainty-Gated Temperature mechanism that acts as a "circuit-breaker," automatically attenuating distillation strength when teacher confidence diverges from domain reality. We evaluate our proposed lightweight framework on four climate-critical domains: meteorology, ecosystem carbon flux, soil moisture, and energy grids. Our method significantly reduces RMSE relative to a fixed-weight multi-teacher distillation baseline, successfully distilling knowledge from pretrained FMs (teachers) even when they exhibit suboptimal zero-shot accuracy due to distribution shift between the original and target data domains. We demonstrate that these domain-misaligned teachers can still serve as critical correctives, outperforming the globally superior FMs on 28.5% of the hardest instances. Ultimately, this enables high-precision scientific forecasting suitable for resource-constrained edge deployment. Code is available at this https URL.

AI 总结：提出ProMUSE，一种渐进式多模态不确定性引导的分阶段证据网络，通过自适应决定何时需要额外模态，在保持准确性的同时降低数据采集成本。

链接：https://arxiv.org/abs/2606.19371

机构：Kennesaw State University（肯尼索州立大学）； Michigan Technological University（密歇根理工大学）； University of Iowa（爱荷华大学）

作者：Long Doan, Branden Chen, Ethan Litton, Huan Huang, Jiajing Huang, Yixin Xie, Weihua Zhou, Nandakumar Narayanan, Chen Zhao

英文摘要：Alzheimer's disease (AD) is a fatal disorder that destroys memory and cognitive skills in the elderly population. Most treatments for AD are effective in the early stage, leading to an increasing demand for early AD diagnosis. AD diagnosis increasingly relies on multimodal data such as clinical assessments, structural Magnetic Resonance Imaging (MRI), and Positron Emission Tomography (PET) imaging. However, MRI and PET acquisition remain costly and not universally accessible, making full-modality inference impractical in real-world clinical workflows. We propose ProMUSE, a Progressive Multi-modal Uncertainty Guided Staged Evidential Network that adaptively determines when additional modalities are necessary, helping reduce the overall cost of data acquisition while maintaining accuracy. ProMUSE first performs evidential classification using low-cost clinical data and quantifies uncertainty via a Dirichlet-based subjective logic model. When uncertainty exceeds a learned threshold, ProMUSE progressively incorporates MRI or PET features, fusing modality-wise belief and uncertainty through Dempster-Shafer theory to obtain a calibrated multimodal prediction. This staged acquisition strategy enables accurate diagnosis while minimizing reliance on expensive imaging. Experiments on ADNI, AIBL, and OASIS across CN-AD, CN-MCI, and MCI-AD tasks demonstrate that ProMUSE achieves competitive or superior accuracy compared to full-modality baselines while reducing MRI/PET usage by 50-90%, yielding substantial cost savings. These results highlight ProMUSE as a practical, uncertainty-aware, and resource-efficient solution for real-world AD screening.

AI 总结：提出cAPM框架，通过任务无关的代理神经网络、主动学习和持续学习策略，在减少起搏标测数据量的同时，实现跨室性心动过速的知识迁移，将定位精度提升至81%。

链接：https://arxiv.org/abs/2606.19373

机构：Rochester Institute of Technology（罗切斯特理工学院）； University of Utah（犹他大学）； Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）； Medical University of Graz（格拉茨医科大学）； University of Pennsylvania Perelman School of Medicine（宾夕法尼亚大学佩雷尔曼医学院）； The University of Arizona College of Medicine（亚利桑那大学医学院）； Dalhousie University（达尔豪斯大学）

作者：Dylan O'Hara, Pradeep Bajracharya, Casey Meisenzahl, Karli Gillette, Anton J. Prassl, Gernot Plank, Saman Nazarian, Roderick Tung, John L Sapp, Linwei Wang

英文摘要：Ventricular tachycardia is a life-threatening rhythm disorder and a major cause of sudden cardiac death. Pace-mapping is a clinical procedure for identifying the intervention target during catheter ablation of VT. It requires clinicians to pace different sites in the ventricles and rapidly interpret the resulting electrocardiograms to determine where to pace next or whether a target site has been identified. Active learning AI models have been proposed to guide clinicians to the next pacing site, showing promise in reducing the number of pacing sites and improving the efficiency of pace-mapping. Existing methods require retraining each target without the ability to transfer knowledge across multiple VTs within the same patient or across patients. We introduce cAPM for continuous AI-assisted pace-mapping to capture and transfer knowledge accumulated from past pace-mapping data to reduce the number of pace-mapping data needed for future target VTs. This is made possible by a task-agnostic surrogate neural network that learns the mapping from pacing sites to 12-lead ECG morphology, an active-learning strategy that refines this surrogate model by selecting the most informative pacing site for each target, and a continual learning strategy to do so sequentially while retaining knowledge from prior targets. Evaluated on an in-silico testbed consisting of sequentially-presented localization tasks across different physiological conditions and ventricular geometries, cAPM with and without replay of past data samples achieved an 81% probability of localizing within clinical tolerance (5 mm accuracy) using 4.5 pace-mapping sites, compared to the state-of-the-art active-learning method achieving 38% probability using 13.7 pacing sites. These results provide a strong basis for preparing cAPM towards in-vivo preclinical and clinical studies where it can be used to guide pace-mapping.

AI 总结：提出一种物理信息框架，从全场位移和反力数据中自动发现各向异性屈服函数，无需应力观测或预设参数形式，采用凸神经网络表示并嵌入弹塑性应力积分中训练。

链接：https://arxiv.org/abs/2606.19375

机构：KAIST（韩国科学技术院）

作者：Hyeonbin Moon, Donghyuk Cho, Jecheon Yu, Jeong Whan Yoon, Seunghwa Ryu

英文摘要：Identifying anisotropic yield functions remains challenging since yielding is not directly observed in full-field mechanical measurements, directional calibration can require many loading directions, and selecting an appropriate analytical form is nontrivial. This study proposes a physics-informed framework for discovering yield functions from full-field displacement data and reaction force data, without stress observations, plastic strain measurements, direct yield surface data, or a prescribed parametric yield function. The framework identifies the yield function as a mechanically constrained constitutive component inside elastoplastic stress integration, rather than through direct stress-space supervision. The yield function is represented by a convex neural network that enforces convexity and positive homogeneity of degree one while imposing the assumed tension-compression symmetry, and this neural yield function is trained with a differentiable stress update and a physics-informed force equilibrium loss across multiple loading cases. The proposed framework is validated using finite element (FE) benchmark studies with von Mises, Hill 1948, and Yld2000-2d yield functions, assessing yield contour agreement, displacement-noise sensitivity, identifiability through plastically active stress states, epistemic uncertainty, and polynomial-surrogate deployment. This study provides a mechanics-constrained pathway for discovering anisotropic yield functions from displacement and force data while keeping the identified component within the structure of elastoplastic stress integration.

AI 总结：针对LLM推理成本与服务质量之间的矛盾，提出SLARouter在线路由算法，利用稀疏单侧用户反馈学习成本最优策略，理论保证成本最优和SLA合规，实验显示成本降低高达2.2倍。

链接：https://arxiv.org/abs/2606.19376

机构：Technical University of Munich（慕尼黑工业大学）； University of Exeter（埃克塞特大学）； Horace Greeley High School（霍勒斯格里利高中）

作者：Herbert Woisetschläger, Arastun Mammadli, Ryan Zhang, Shiqiang Wang

英文摘要：Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a fundamental tension between cost and quality. Recent progress on cost-aware LLM request routing has shown potential to resolve this tension, but existing approaches rely on complete feedback signals, offline training, extensive per-workload tuning, and most lack SLA guarantees or inference-time adaptivity. We introduce SLARouter, an online routing algorithm that learns a cost-optimal policy from the sparse, one-sided user feedback available in production systems. SLARouter provides theoretical guarantees for both cost optimality and strict SLA compliance. Experiments across a wide range of LLM benchmarks show that SLARouter satisfies SLA constraints without the need for per-benchmark tuning, reducing operating cost by up to 2.2x over existing baselines.

AI 总结：提出混合GNN-FEM框架，用图神经网络替代相场更新步骤，保留FEM位移求解器，通过无量纲特征设计和物理信息损失实现跨几何、载荷、材料和离散化的通用断裂模拟，降低计算成本并保持精度。

链接：https://arxiv.org/abs/2606.19378

机构：KAIST（韩国科学技术院）

作者：Hyeonbin Moon, Yongjin Choi, Seunghwa Ryu

英文摘要：Scientific machine learning (SciML) has emerged as a promising approach for accelerating simulations of complex physical systems, yet achieving physically consistent and generalizable predictions for nonlinear, history-dependent problems remains a central challenge. In this study, we propose a hybrid GNN--FEM framework for efficient and generalizable phase-field fracture modeling. While phase-field approaches provide a robust variational framework for simulating complex crack evolution, their high computational cost limits practical applications because they require solving coupled, nonlinear, and history-dependent systems within an incremental finite element procedure. To address this challenge, a graph neural network surrogate is integrated into the conventional staggered scheme, replacing the phase-field update at each load increment while retaining the FEM-based displacement solver to enforce mechanical equilibrium and boundary conditions. By preserving the incremental solution structure, the framework remains consistent with history-dependent fracture evolution without requiring the surrogate to approximate the full solution trajectory. This selective surrogate strategy emphasizes the identification of a physically meaningful and incrementally structured learning target, rather than relying on brute-force data generation to learn the full fracture process. The proposed framework achieves strong generalization across varying geometries, loading conditions, material properties, and discretizations through dimensionless feature design, a graph-based formulation on mesh-based domains, and a physics-informed loss derived from the governing phase-field equation. Numerical experiments demonstrate that the hybrid approach reduces computational cost while maintaining accuracy compared with conventional FEM, and exhibits robust predictive performance across diverse problem settings.

AI 总结：提出VERITAS框架，通过两阶段协议（Best-of-N采样+批评引导MCTS）利用验证器反馈进行零样本定理证明，在miniF2F上达40.6%准确率，并发布组合学基准VERITAS-CombiBench。

链接：https://arxiv.org/abs/2606.19399

机构：Department of Computer Science, Vanderbilt University（范德堡大学计算机科学系）； Amazon（亚马逊）

作者：Manish Acharya, Zhenyu Liao, Yueke Zhang, Kevin Leach, Yu Huang, Yifan Zhang

英文摘要： LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back into proof search through a two-phase protocol: Best-of-N sampling first, then a critic-guided MCTS pass that ingests Phase 1 failures as explicit negative examples. The protocol preserves every theorem solved by its own Phase 1 sweep, so Phase 2's additional solves are attributable to feedback-driven exploration. VERITAS reaches 40.6% on miniF2F (vs. an independently run Best-of-5 at 36.9%, Portfolio 26.2%) and 7.3% on VERITAS-CombiBench, a 55-theorem combinatorics benchmark we release on which Best-of-5 (1.8%) falls below Portfolio (3.6%), exposing that unguided sampling hurts when correct lemma names must be recovered iteratively from verifier feedback. Artifacts are available on GitHub.

AI 总结：提出SpecReTF方法，通过将时间序列转换为窗口化频率表示并采用结合幅度和相位的相似性度量，以及指数移动平均加权方案，解决了现有检索方法在频谱盲区和时间近因上的局限性，提升了非平稳时间序列预测的准确性。

链接：https://arxiv.org/abs/2606.19412

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

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

英文摘要：Time series forecasting leverages historical patterns to predict future values, but traditional methods face challenges when dealing with complex, non-stationary patterns that are difficult to memorize during training. Retrieval-augmented approaches have emerged as promising solutions by retrieving similar historical patterns to enhance predictions. However, existing retrieval methods suffer from two fundamental limitations: spectral blindness, which overlooks critical frequency-domain characteristics that capture underlying periodic structures, and temporal recency, which treats all historical data equally without emphasizing recent, more relevant patterns. In this paper, we propose SpecReTF, a novel retrieval method that addresses these issues by converting time series into windowed frequency representations, measuring similarity with a combined metric that captures both amplitude and phase information. To balance recency and historical context, we apply an exponential moving average weighting scheme that emphasizes recent windows. Extensive experiments on benchmark datasets demonstrate that SpecReTF outperforms time-domain retrieval methods, achieving superior forecasting accuracy across diverse, non-stationary time series.

AI 总结：针对多模态时间序列预测中文本分支被忽视导致“文本坍缩”的问题，提出REST-TS方法，通过让文本分支专门预测数值主干无法解释的残差，强制其提取真实内容，实现最先进性能。

链接：https://arxiv.org/abs/2606.19413

机构：Applied Artificial Intelligence Initiative（应用人工智能计划）

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

英文摘要：Multimodal time series forecasting, which pairs numerical sequences with domain-relevant textual reports, promises to inject world knowledge into forecasting pipelines. However, we uncover a critical failure mode in existing frameworks that we term text collapse: the text branch converges to a content-independent transformation, contributing negligible discriminative signal regardless of the input description. We argue that text collapse is a consequence of a fundamental asymmetry in time series forecasting: the numerical input is strongly autocorrelated with the output, making the numerical backbone inherently dominant, while the text branch, despite carrying complementary and often critical information, is insufficiently utilized, leading to its systematic underexploitation. To address this, we propose \textbf{REST-TS} (\textbf{R}esidual-\textbf{E}xclusive \textbf{S}upervision for \textbf{T}ext in \textbf{T}ime \textbf{S}eries), which turns the asymmetry into a design principle: the numerical backbone produces its own independent numerical forecast, and the text branch is exclusively supervised to predict the structured components of the residual, the prediction gap that numbers cannot explain. Because no numerical pathway can reduce these losses, the text branch must extract genuine content from the input description. Evaluated across diverse real-world domains and backbone architectures, REST-TS achieves state-of-the-art performance and consistently demonstrates greater text-branch utilization than existing frameworks, providing strong empirical evidence that supervising the text branch on the residual compels it to extract genuine content from the input.

AI 总结：系统评估多种时间序列模型在流感预测中的表现，发现混合专家模型性能最优，预训练在长时域提升显著，而LLM方法效果较差。

链接：https://arxiv.org/abs/2606.19560

机构：Department of Computer Science, School of Engineering and Applied Science, University of Virginia（弗吉尼亚大学工程与应用科学学院计算机科学系）； School of Data Science, University of Virginia（弗吉尼亚大学数据科学学院）； Biocomplexity Institute, University of Virginia（弗吉尼亚大学生物复杂性研究所）； Department of Electrical and Computer Engineering, School of Engineering and Applied Science, University of Virginia（弗吉尼亚大学工程与应用科学学院电气与计算机工程系）

作者：Alireza Jafari, Judy Fox, Geoffrey C. Fox, Madhav Marathe, Aniruddha Adiga

英文摘要： Seasonal influenza infects millions of people and causes substantial morbidity and mortality in the United States each year, making accurate short-term forecasting a core public-health need. Reliable forecasts of epidemic time series can inform vaccination timing, hospital staffing, and resource allocation, yet the comparative behavior of modern forecasting architectures on infectious-disease surveillance data remains insufficiently characterized. We address this gap through a systematic evaluation of regional influenza forecasting using influenza-like illness surveillance and influenza-associated hospitalization time series under both temporal and spatial generalization settings for 1-4-week-ahead prediction. We compare classical neural network architectures, numerical transformer-based models, pretrained time series foundation models, and LLM-based forecasting approaches. Across tasks, we demonstrate that a mixture-of-experts model that fuses multiple pretrained forecasters achieves the strongest overall performance, indicating that heterogeneous pretrained representations provide complementary predictive information. Our results further show that numerical transformer-based models produce reliable forecasts, while pretraining provides the largest gains at longer horizons, particularly when the pretraining domain is mechanistically aligned with influenza dynamics. In contrast, LLM-based time series methods underperform relative to numerical forecasters in this setting. Finally, we examine hospitalization information as both an auxiliary covariate and a pretraining source. Hospitalization signals provide complementary improvements in selected settings and clarify when additional surveillance streams enhance the robustness of multi-horizon forecasting. These findings provide actionable guidance on model selection, pretraining strategy, and auxiliary-signal use for influenza preparedness.

AI 总结：综述科学机器学习在耦合流体流动与输运问题中的进展，包括基于SVD的线性降阶和PINNs、β-VAE等神经网络方法，并展示其在浊流和热对流中的应用。

链接：https://arxiv.org/abs/2606.19562

机构：COPPE - Federal University of Rio de Janeiro - UFRJ（里约热内卢联邦大学COPPE学院）

作者：Gabriel F. Barros, Rômulo M. Silva, Alvaro L. G. A. Coutinho

英文摘要：This chapter reviews recent advances in Scientific Machine Learning (SciML) for modeling coupled fluid flow and transport phenomena governed by the incompressible Navier-Stokes and scalar transport equations. Such systems, found in applications like turbidity currents and thermal convection, feature strong nonlinear coupling and multiscale behavior that make high-fidelity simulations computationally expensive. To address this, the chapter surveys state-of-the-art SciML methods for building efficient surrogate models, including linear reduced-order techniques based on Singular Value Decomposition (such as Dynamic Mode Decomposition) and nonlinear neural network approaches like Physics-Informed Neural Networks (PINNs) and $\beta$-Variational Autoencoders ($\beta$-VAEs). It first covers the authors' work combining these models with High Performance Computing strategies, including Adaptive Mesh Refinement/Coarsening (AMR/C) and scientific floating-point data compression. It then presents two new contributions: surrogate modeling of turbidity currents via PINNs, and the extraction of disentangled nonlinear modes from thermal flows using $\beta$-VAEs. Governing equations and representative benchmarks, including lock-exchange flows and Rayleigh-Bénard convection, illustrate these methodologies. The chapter is intentionally long, covering both the mathematical and physical foundations of coupled fluid flow and the computational aspects of state-of-the-art modeling. Overall, it demonstrates how SciML enables fast, accurate approximations of complex coupled systems within the specific data regimes and modeling assumptions considered, while substantially reducing computational cost relative to full-order simulations. Broader capabilities such as real-time prediction and uncertainty quantification remain active research directions whose feasibility depends strongly on the problem at hand.

AI 总结：提出SEAGAN，将植物A-Ci曲线中的生化限制状态识别建模为图节点分类问题，利用距离kNN和辅助信号引导连接构建图，通过边缘感知图注意力网络提升分类性能，F1分数达0.857。

链接：https://arxiv.org/abs/2606.19623

机构：Center of Studies in Resources Engineering（资源工程研究中心）； Indian Institute of Technology Bombay（孟买印度理工学院）

作者：Antriksh Srivastava, Soumyashree Kar

英文摘要：Graph neural networks (GNNs) provide a flexible framework for learning from scientific data linked through physical, biological, or functional relationships. One promising domain is plant physiology, where measured responses often arise from multiple interacting processes whose exact separation remains difficult even with manual intervention. In plant physiology, a key example is the A-Ci curve, which relates net CO2 assimilation rate (Anet) to leaf intercellular CO2 concentration (Ci) and is used to estimate photosynthetic parameters in leaf and crop-canopy models. However, reliable estimation requires identifying the active biochemical limitation state at each curve point, which remains a major source of uncertainty. Here, we formulate limitation-state identification along A-Ci curves as a graph-based node classification problem, with curve points as nodes. Domain-specific graph representations are created using distance-based k-nearest-neighbor (kNN) and auxiliary-signal-guided (ASG) connectivity, with edge attributes encoding pairwise relations. The framework was evaluated against conventional learning baselines, graph-based architectures, and an automated fitting-based benchmark. Results on a large synthetic dataset with known ground-truth limitation states show that graph-based models improve classification, particularly near biochemical transition regions. The best-performing configuration, SEAGAN (domain-Specific and Edge-Aware Graph Attention Network for Dynamic Plant Processes), integrates process-aware node features, edge attributes, kNN connectivity, and graph attention with weighted cross-entropy loss, achieving an F1-score of 0.857 and an accuracy of 0.882. The results show that representing A-Ci curves as graphs improves biochemical limitation-state analysis, with edge-aware attention over local kNN neighborhoods providing the most effective strategy.

AI 总结：提出自适应主干DeepONet框架，通过KNN构建荷载相关学习域、距离感知特征和刚度-informed Schur补全重建，实现大跨度桥梁局部响应高精度快速预测，相对误差低于5%，速度提升约60倍。

链接：https://arxiv.org/abs/2606.20015

机构：Urban Engineering Department , addressline= New York University Abu Dhabi , country= United Arab Emirates； organization= National Center for Supercomputing Applications , addressline= University of Illinois at Urbana-Champaign , country= United States of America； organization= Department of Structural Engineering , addressline= Mansoura University , country= Mansoura, Egypt

作者：Bilal Ahmed, Diab W. Abueidda, Waleed El-Sekelly, Tarek Abdoun, Mostafa E. Mobasher

英文摘要：Long-span roadway bridges exhibit highly localized structural responses under vehicular loading, making repeated FE analysis computationally expensive for applications such as influence surface generation and structural digital twins. Existing SciML approaches struggle to accurately capture these localized responses. To address this challenge, this study proposes an adaptive-trunk DeepONet for localized structural response prediction in large-scale bridge systems. The framework dynamically constructs a load-dependent learning domain using a KNN strategy, allowing the network to focus on structural influence zones. The trunk network is further enhanced using distance-aware features that encode the geometric relationship between the load and structural nodes. A physics-based full-field reconstruction is incorporated through a stiffness-informed Schur complement formulation, enabling predictions at adaptive nodes to be extended to the entire structural domain. To enable scalable training, response data are generated using a reduced-order equivalent shell model that preserves the dominant global behavior while significantly reducing computational cost. The proposed framework is validated on both a benchmark bridge model and the real-world Mussafah Bridge. Results show that the method achieves FEM-level accuracy with relative errors below 5%, while reducing the total response evaluation time (including full-field reconstruction) by approximately 60x; excluding the post-processing reconstruction step, the AD-DeepONet inference is up to four orders of magnitude faster than FEM. In addition, the framework enables rapid generation of full-field responses, influence lines, and influence surfaces under arbitrary vehicular loading configurations, demonstrating strong potential for large-scale bridge analysis and digital twin applications.

AI 总结：本研究对比TESSERA和AlphaEarth嵌入与传统Sentinel-1/2数据，使用注意力U-Net将粗分辨率LCZ图提升至10米，发现嵌入模型在跨城市迁移和精度上表现更优，但跨年迁移仍是挑战。

链接：https://arxiv.org/abs/2606.20034

机构：International Space Science Institute（国际空间科学研究所）； CYCLOPS MRV

作者：Htet Yamin Ko Ko, Clement Atzberger

英文摘要：Understanding urban spatial morphology is critical for climate modeling, risk assessment, and sustainable urban design, and Local Climate Zone (LCZ) mapping provides the basic framework for this. However, many cities still use coarse ~100-m resolution LCZ records, which are unsuitable for fine-scale urban research. In this study, precomputed embeddings from TESSERA (Feng et al., 2025) and AlphaEarth (Brown et al., 2025) are compared to traditional Sentinel-1/2 (S1S2) composites in five Swiss cities to see if they can upscale coarse LCZ maps to 10-m resolution using an attention-based U-Net. Three experiments assess multi-city transferability, the impact of higher-resolution reference data, and temporal robustness to year-to-year phenology changes. We find that all datasets achieve strong performance with test data Intersection-over-Union (IoU) ranging from 0.59-0.69 and 0.77-0.82 in the first two experiments. TESSERA consistently outperforms both S1S2 and AlphaEarth across both settings As expected, we find that the transfer of embedding-based models from one year to another remains an open challenge. Overall, however, our results demonstrate the promising potential of embeddings derived from EO foundation models to reduce time consuming preprocessing, respectively, manual feature engineering tasks and to guide a universal deep learning-based LCZ mapping workflow. When combined with a simple location-aware attention U-Net architecture, the embeddings enhance regional transferability and scalability, supporting the development of comprehensive and reproducible fine-scale LCZ maps for global urban climate applications Improving reference data quality remains the strongest lever for further accuracy gains.

AI 总结：提出结合3D卷积特征提取器与三种融合策略（拼接、门控多模态单元、门控自注意力）及稀疏门控混合专家分类器的多模态模型，用于阿尔茨海默病诊断，在三个二分类任务上验证了输入自适应建模的有效性。

链接：https://arxiv.org/abs/2606.20037

机构：DSS Lab, School of ECE, NTUA（NTUA ECE学院DSS实验室）

作者：Loukas Ilias, Anthi-Maria Vozinaki, Christos Ntanos, Dimitris Askounis

英文摘要：Alzheimer's disease (AD) is an irreversible neurodegenerative disorder and a leading cause of death worldwide. Early diagnosis plays an important part especially at the Mild Cognitive Impairment stage, where timely intervention can help slow its progression before it advances to AD. Neuroimaging data, like Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) scans, can help detect brain changes early by providing structural and functional brain changes related to the disease. Yet, many multimodal models still fuse MRI and PET with static concatenation and apply identical computation to all subjects, which limits robustness to patient/site heterogeneity and can waste computation. To address these limitations, we present the first study of combining 3D convolutional feature extractors with three fusion strategies - concatenation, Gated Multimodal Unit (GMU), and gated self-attention - and a sparsely gated Mixture-of-Experts (MoE) classifier that performs input-adaptive routing, activating only the most informative experts per case. Finally, we utilize Grad-CAM to visualize disease-related regions, ensuring model interpretability. Experiments are performed across three binary classification tasks (NC vs. MCI, MCI vs. AD, and NC vs. AD). Results show that GMU achieves accuracies of 80.46 % (NC vs. MCI) and 95.47 % (NC vs. AD), while gated self-attention attains 82.08 % on MCI vs. AD. Ablations show that removing the MoE consistently degrades accuracy across all tasks. These findings underscore the value of input-adaptive, multimodal modeling for AD diagnosis by leveraging the complementary nature of MRI and PET.

AI 总结：系统比较四种神经网络架构（MLP、ResNet、U-Net、FNO）作为自回归状态转移算子，预测锂离子电池DFN模型内部状态，发现U-Net因多尺度空间归纳偏置在精度和速度上最优。

链接：https://arxiv.org/abs/2606.20053

机构：IAV GmbH（IAV公司）

作者：Gihyun Lee, Thorben Menne, Simon Olma, Jakob Hilgert, Sangyoung Park

英文摘要：The Doyle-Fuller-Newman (DFN) model resolves internal electrochemical states in lithium-ion batteries with high fidelity. However, the numerical solution of its governing equations is computationally prohibitive for real-time deployment, limiting scalability from individual cells to pack and fleet-scale applications. While machine learning surrogates can substantially reduce inference latency through GPU acceleration, most existing approaches learn solution approximations tied to specific operating conditions rather than learning generalizable state-evolution dynamics. This work presents a systematic comparison of four neural network architectures (MLP, ResNet, U-Net, FNO) formulated as autoregressive state-transition operators that predict full DFN internal states across a wide range of operating conditions. To ensure a controlled architectural comparison, all models are trained under a unified framework using multi-step unrolling and current-conditioning, isolating the impact of spatial inductive bias. Results demonstrate that the U-Net's multi-scale feature hierarchy achieves a mean final-step nRMSE of 3% averaged across all internal state variables after 300-step autoregressive rollouts, while providing a 5.38x speed-up over the numerical solver. These findings highlight spatial inductive bias as a critical determinant of surrogate performance, advancing the development of surrogates for internal state observability for next-generation battery management systems and digital twins.

AI 总结：提出PaAno模型，通过多尺度特征提取、跨变量融合注意力和补丁窗口排序预任务，实现轻量高效的时间序列异常检测，在TSB-AD基准上达到SOTA。

链接：https://arxiv.org/abs/2606.20055

机构：School of Mathematical Sciences, Guizhou Normal University（贵州师范大学数学科学学院）； School of Big Data and Computer Science, Guizhou Normal University（贵州师范大学大数据与计算机科学学院）

作者：Youji Zhu, Hongbing Wang, Wenchao Liu, Xiaodong Liu, Xiangguang Xiong

英文摘要：Time-series anomaly detection has significant practical value for industrial and medical monitoring, as well as other critical domains. Current Transformer- and large-model-based detection approaches incur excessive computational overhead, while existing lightweight alternatives are constrained by insufficient feature extraction and inadequate modeling of dependencies across multivariate variables. To mitigate the above drawbacks, this study develops a lightweight, efficient anomaly detection model, dubbed PaAno, within the patch-oriented representation learning paradigm. In the encoder module, a multiscale feature-extraction backbone is constructed using convolutional kernels with differentiated receptive fields to capture hierarchical temporal characteristics; subsequent cross-scale adaptive attention aggregation, combined with residual connection optimization, further stabilizes feature representation learning. A cross-variable fusion attention module is embedded to explicitly characterize inter-variable correlations, empowering the model to identify anomalous patterns amid intricate operational conditions. Moreover, a novel pretext task based on temporal patch-window sorting is customized to uncover intrinsic structural properties of time series, and triplet loss is leveraged to optimize the patch embedding space for enhanced feature discrimination. Extensive experiments on the TSB-AD benchmark demonstrate that the proposed PaAno achieves state-of-the-art detection accuracy on both univariate and multivariate tasks, yielding significant performance gains across evaluation metrics, including VUS-PR, relative to the original PaAno. Leveraging a compact network design, the presented model achieves favorable computational efficiency, enabling deployment on resource-limited terminals for real-time anomaly inference.

AI 总结：提出结合多模态胎儿MRI和机器学习流程预测出生胎龄，包括数据插补、特征选择和回归模型，在333例对照和93例早产数据上评估，R²=0.13，MAE=2.74周，准确率0.77。

链接：https://arxiv.org/abs/2606.20172

机构：Leibniz University Hannover（莱布尼茨汉诺威大学）

作者：Diego Fajardo-Rojas, Megan Hall, Daniel Cromb, Mary A. Rutherford, Lisa Story, Emma C. Robinson, Jana Hutter

英文摘要：Preterm birth is associated with significant mortality and a risk for lifelong morbidity. The complex multifactorial aetiology hampers accurate prediction and thus optimal care. A pipeline consisting of bespoke machine learning methods for data imputation, feature selection, and regression models to predict gestational age (GA) at birth was developed and evaluated from comprehensive multi-modal morphological and functional fetal MRI data from 333 control cases and 93 preterm birth cases. The GA at birth predictions were classified into term and preterm categories and their accuracy, sensitivity, and specificity were reported. An ablation study was performed to further validate the design of the pipeline. Performance was evaluated using stratified 10-fold cross-validation. The pipeline achieves an R2 score of 0.13 and a mean absolute error of 2.74 weeks. It also achieves a 0.77 accuracy, 0.59 sensitivity, and 0.82 specificity across folds. The predominant features selected by the pipeline include cervical length and statistics derived from placental T2* values. The confluence of fast, motion-robust and multi-modal fetal MRI techniques and machine learning prediction allowed the prediction of the gestation at birth. This information is essential for any pregnancy. To the best of our knowledge, preterm birth had only been addressed as a classification problem in the literature. Therefore, this work provides a proof of concept. Future work will increase the cohort size to allow for finer stratification within the preterm birth cohort. Our code is available at this https URL.

AI 总结：综述2022-2025年cfDNA多癌早期检测的计算方法，重点分析片段组学和表观遗传特征提取技术，指出多模态集成方法最具临床整合潜力，但需标准化评估协议。

链接：https://arxiv.org/abs/2606.20174

机构： AGH University of Krakow（AGH克拉科夫大学）； Norwegian Institute of Public Health（挪威公共卫生研究所）

作者：Nicko Starkey, Marcin W. Wojewodzic, Krzysztof Rzecki

英文摘要：Cell-free DNA (cfDNA) is a promising avenue for non-invasive multicancer early detection (MCED), in that, it can enable multiple cancer detection simultaneously from a single blood draw, with particular sensitivity to cancers that currently lack established screening programs. Here we review the computational methods developed between 2022 and 2025 for cfDNA-based MCED. We focus on how fragmentomics and epigenetic features are extracted and analyzed to detect cancer at early stages. We first briefly outline the biological basis of cfDNA signals, then review classical statistical and machine learning approaches alongside deep learning frameworks including autoencoder-based models. For each method we discuss biological interpretability, validation strategy, and readiness for clinical integration. Furthermore, we categorize the current challenges into technical, computational, and methodological while outlining open problems in the field. This review shows that multimodal ensemble approaches have the strongest promise for clinical integration and the highest readiness. However, for better assessment of future work and side-by-side comparison, standardization of evaluation protocols and reporting results will be crucial.

AI 总结：提出VibrantForests框架，结合卫星影像、激光雷达样本和计算机视觉，以10米分辨率生成美国本土的冠层覆盖、高度、生物量等森林属性图，减少饱和与回归均值问题。

链接：https://arxiv.org/abs/2606.20291

机构：Vibrant Planet Public Benefit Corporation（Vibrant Planet 公益公司）

作者：Luke J. Zachmann, David D. Diaz, Vincent A. Landau, Chelsey Walden-Schreiner, Tony Chang, Nathan E. Rutenbeck, Katharyn A. Duffy, Kiarie Ndegwa, Andreas Gros, Scott Conway, Guy Bayes

英文摘要：Remote sensing is increasingly relied upon to deliver actionable science for forest and wildfire risk management across large landscapes. Wall-to-wall, annually updated maps are a persistent need for effective forest management. Many planning systems and data collections combine disparate data sources with different purposes, vintages, and prediction quality, which leads to confounding behavior in operational planning systems. We introduce the VibrantForests framework, developed and applied to map forest attributes and provide a coherent foundation for effective forest and wildfire planning. VibrantForests includes a satellite-based forest structure model trained on lidar-derived samples and applied across the contiguous United States to concurrently generate estimates of canopy cover, canopy height, aboveground live tree biomass, basal area, and quadratic mean diameter at 10-meter resolution. We demonstrate predictive capability spanning the full spectrum of forest conditions ranging from sparse-canopy/low-biomass to dense-canopy/high-biomass. Results show that our model extends the range at which saturation is commonly encountered in comparable passive-sensor models, and reduces regression-to-mean behavior that commonly produces overestimation of forest attributes in small/sparse conditions and underestimation in large/dense conditions. The VibrantForests framework addresses a key limitation in large-area forest and wildfire planning by delivering coherent wall-to-wall estimates of management-relevant attributes at annual cadence and 10m resolution.

AI 总结：提出QCPIKAN，首个量子-经典物理信息Kolmogorov-Arnold网络，结合Chebyshev多项式KAN层和参数化量子电路，通过嵌入物理约束加速高频误差指数收敛并抑制数值色散，在多孔介质渗流场景中优于现有量子-经典PINN。

链接：https://arxiv.org/abs/2606.20326

机构：School of Petroleum Engineering, Yangtze University（扬州大学石油工程学院）； School of Computer Science, Yangtze University（扬州大学计算机科学学院）； State Key Laboratory of Low Carbon Catalysis and Carbon Dioxide Utilization (Yangtze University)（扬州大学低碳催化与二氧化碳利用国家重点实验室）； Western Research Institute, Yangtze University（扬州大学西部研究院）

作者：Xiang Rao, Yuxuan Shen

英文摘要：We develop QCPIKAN, the first quantum-classical physics-informed Kolmogorov-Arnold network designed to solve partial differential equations (PDEs). Built upon Chebyshev-polynomial KAN layers and parameterized quantum circuits, this hybrid framework embeds physical constraints into the training loss to enforce physical consistency. Our theoretical investigations grounded in approximation theory prove that this design accelerates high-frequency error convergence to an exponential rate and effectively mitigates numerical dispersion. We validate the framework across three typical seepage scenarios in porous media, including single-phase flow, component transport and two-phase flow. Compared with existing quantum-classical physics-informed neural networks, QCPIKAN achieves superior performance in global prediction accuracy, local error control, dynamic evolution tracking and displacement front localization. This work provides a robust and efficient alternative for solving complex PDEs.

AI 总结：提出首个混合建模框架，利用神经网络从宏基因组推断功能性状预测过程模型参数，并整合生态理论约束，有效预测微生物动态和有机质周转。

链接：https://arxiv.org/abs/2606.20329

机构：Agrosphere (IBG-3), Forschungszentrum Jülich GmbH（农业圈（IBG-3），于利希研究中心）； Institute of Crop Science and Resource Conservation, University of Bonn（波恩大学作物科学与资源保护研究所）； Institute of Computer Science, University of Bonn（波恩大学计算机科学研究所）； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习和人工智能研究所）

作者：Paul Collart, Juergen Gall, Andrea Schnepf, Holger Pagel, Lars Doorenbos

英文摘要： Soil microorganisms control organic matter cycling and largely determine how soil systems can cope with and mitigate climate change and environmental threats. Representing microbial dynamics in process-based soil models is therefore critical to predict carbon cycling in soils, albeit highly challenging to inform from data. One promising approach to improve their parametrisation is the integration of genomic data, yet modelling the complex and unknown relationship between genomes and the processes the microbes are driving is an unsolved problem. In this work, we present the first hybrid modeling framework for deriving biokinetic parameter values of a process-based soil organic matter turnover model from metagenome-inferred functional traits based on DNA sequencing data. Our model predicts biokinetic parameters of the process-based model from genomic trait data with a neural network and integrates constraints from ecological theory and literature to ensure realistic behavior, even of non-observed state variables. We evaluate our method on synthetic genomic trait datasets of varying complexity and on real data, showing that our approach improves performance over multiple baselines and learns the dynamics of unmeasurable components of the process-based model effectively, even for small training datasets.

AI 总结：研究自诉租户、房东和帮助台工作人员如何获得正确的法定引用，通过四组实验比较微调、检索及混合方法，发现SFT+RAG混合模型在精确匹配上得分最高且无幻觉引用。

链接：https://arxiv.org/abs/2606.20359

机构：Transformer Lab

作者：Ali Asaria, Tony Salomone, Deep Gandhi

英文摘要：Self-represented tenants, landlords, and help-desk staff need to be pointed at the provision of law that actually governs a question, with a correct statutory citation. We study this task on the Ontario Residential Tenancies Act, 2006 (RTA) and its core regulation, asking the operator's question empirically: is fine-tuning enough, or is hybrid retrieval needed? We run a four-arm head-to-head on Qwen2.5-7B-Instruct (base zero-shot, LoRA SFT-only, RAG-only, and an SFT+RAG hybrid), scored on citation exact-match (section+subsection) over a small, human-verification-pending real eval set. The base model cannot cite the RTA and SFT-only mis-recalls sections; retrieval is essential and drives hallucination to zero by construction; and the SFT+RAG hybrid scores highest at 0.481 exact-match with zero hallucinated citations. Its edge comes from SFT making provision selection more robust to the higher-recall candidate sets that hurt zero-shot RAG. Notably, this cheap bge-small hybrid matches or beats a pipeline built on bigger, specialized retrieval models (a larger embedder and a cross-encoder reranker), and a larger/improved training set does not help either: strong statutory-citation performance here does not require specialized retrieval models or more data. The artifact zeroes hallucination and clears the lift-over-base bar but does not reach the aspirational 0.70 exact-match target. All results are on a small, human-verification-pending real eval set and are reported as preliminary.

AI 总结：本文提出一种去偏的跨模型 VLM-as-3D-Judge 协议，将评判者从排序扩展到优化，通过训练与评估评判者分离、位置偏差校正及修复三种失效模式，实现轻量级适应下与强基线的匹配。

链接：https://arxiv.org/abs/2606.20364

机构：Transformer Lab

作者：Ali Asaria, Tony Salomone, Deep Gandhi

英文摘要：A companion study established a de-biased, cross-model VLM-as-3D-judge that reliably ranks single-image-to-3D mesh quality where cheap geometry and CLIP proxies fall short. This paper asks: can that judge's preferences specialize a strong open generator, TRELLIS, on one asset class (furniture), cheaply and without human labels? Taking the judge from ranking to optimization is where the work lives. Pushing a VLM judge into the training and evaluation loop exposes failure modes ranking never triggered, so our contribution is an optimization-grade hardening of the judge: a training judge (Qwen2.5-VL-7B) held distinct from an evaluation judge (InternVL3-8B) to break circularity; position-bias correction; and fixes for three failure modes (image overload, geometry-hiding splat renders, and reference-free judging that rewards clean-but-wrong outputs), with calibration evidence (clear-gap win-rate 0.83-1.0; base-vs-base ~0.5). Using this protocol as an independent evaluator, and working only from public models and data with lightweight parameter-efficient adaptation, we find our methods match the strong base rather than exceed it. Independent base samples carry essentially no learnable preference (0.94 order-flip rate), so signal must be engineered by quality-contrastive construction. Across six adaptation methods, two input regimes, and a severity sweep, the most targeted - conditioner repair under severe degradation - reaches parity (0.50) with the base, while no method clears the >=65% win-rate target. The result is mechanistic: clean inputs saturate the judge, flow-DIT fine-tuning washes out through the sampler, and conditioning repair is the locus that moves geometry. Win-rates are directional at n=8 objects. Matching a strong public-data base with cheap adaptation is itself informative: exceeding it needs more than lightweight PEFT on public data, and the judge protocol is reusable.

AI 总结：提出DeepGaLA神经网络代理模型，为微分方程求解器提供不确定性感知预测，结合延迟接受MCMC诊断，实现高效可靠的贝叶斯反演。

链接：https://arxiv.org/abs/2606.20417

机构：School of Mathematics and Maxwell Institute for Mathematical Sciences University of Edinburgh（数学学院和麦克斯韦数学科学研究所爱丁堡大学）

作者：Christian Jimenez-Beltran, Aretha L. Teckentrup, Antonio Vergari, Konstantinos C. Zygalakis

英文摘要： Inverse problems for differential equations arise throughout science and engineering, where one seeks to infer unknown model parameters from noisy or incomplete observations. Traditional numerical methods for these problems are often computationally expensive, particularly in Bayesian settings where evaluating the likelihood becomes costly for complex forward models and high-dimensional parameter spaces. To address this challenge, we introduce DeepGaLA, a neural-network surrogate for differential equation solvers that provides uncertainty-aware predictions, reducing overconfident inference when training data are limited. To evaluate the fidelity of the surrogate-induced posterior approximations in practice, we show that a short run of delayed-acceptance Markov chain Monte Carlo can serve as an effective diagnostic. Across a range of numerical experiments, DeepGaLA delivers forward-model approximations with accuracy comparable to established Gaussian-process surrogates, while better maintaining efficiency as parameter dimension grows. Moreover, it can incorporate differential-equation constraints, including in nonlinear settings. Overall, these results indicate that uncertainty-quantified neural surrogates can enable scalable and reliable Bayesian inference for inverse problems in complex systems.

AI 总结：提出ASYS框架，通过智能体将PDE理论转化为可微分符号程序，结合进化搜索和梯度优化自动发现解析形式或近似，在多个问题中生成可解释表示。

链接：https://arxiv.org/abs/2606.20467

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

作者：Zongmin Yu, Liu Yang

英文摘要：Mathematicians understand a PDE solution through mathematical structures rather than tables of computed values. Historically, this has been the product of mathematical analysis, carried out by hand for each problem individually. Neither numerical simulation nor neural networks produce those structures directly. We propose Agentic Symbolic Search (ASYS), a prior-guided framework in which an agent translates PDE theory, public problem constraints, and accumulated search experience into testable differentiable symbolic programs. The mathematical forms are refined under evolutionary search, while their continuous parameters are fit by gradient-based optimization. This makes the search an automated form of inductive-bias injection rather than blind symbolic regression. For problems with known analytical forms, ASYS recovers these forms naturally; for other problems, ASYS constructs analytical approximations which can guide mathematicians toward further analysis. In our experiments, across five problems spanning bounded dynamics, finite-time blow-up, and free-boundary focusing, ASYS produces interpretable representations, including a geometric interface formula for Allen-Cahn 2D dynamics and a nine-parameter contraction law for Keller-Segel chemotactic blow-up, in settings where no closed-form description was previously available. ASYS shows the possibility of a new paradigm for characterizing PDE solutions, beyond handcrafted analytical solutions, mesh-based numerical solutions, and neural network approximations.

AI 总结：利用信息几何和范畴论，提出两种算法（BRIDGE和SKFM），通过干预诱导流的李括号非闭合性检测潜在混杂，大幅缩减因果图搜索空间。

链接：https://arxiv.org/abs/2606.19610

机构：Adobe Research（Adobe研究院）； University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）

作者：Sridhar Mahadevan

英文摘要：Recent work on Kan-Do-Calculus (KDC) has established that the boundary between passive observation and active intervention in causal inference is a category-theoretic bi-adjunction, with interventions modeled by left Kan extensions and conditioning by right Kan extensions. This paper introduces two causal discovery algorithms under latent confounding, building on the information-geometric and categorical consequences of KDC. In smooth statistical settings, Radon-Nikodym derivatives between observational and interventional measures induce local causal vector fields; failures of these fields to close under Lie brackets become computable Frobenius residuals, which we interpret as witnesses of failed visible integrability and possible latent or unmodeled structure. Our first algorithm, BRIDGE (Bracket Residuals for Interventional Discovery and Geometric Estimation), combines an interventional density or Radon-Nikodym-ratio engine with a geometric screen that proposes a high-recall family of admissible arrows, identifies non-closing visible pairs as latent-obstruction candidates, and passes the reduced family to downstream score-based or differentiable discovery routines. The second algorithmic contribution, Spectral Kan-Do Flow Matching (SKFM), learns amortized intervention fields and factors latent curvature spectrally, exposing the direct Lie-space endpoint toward which BRIDGE points. A detailed set of experiments show that both algorithms are capable of discovering causal models with latent confounders while collapsing the super-exponential space of possible DAGs by many orders of magnitude. This paper introduces a new paradigm in causal discovery, where latent structure is inferred directly from the geometry of intervention-induced flows.

AI 总结：提出传染网络框架，量化评估者偏见在多智能体LLM系统中的传播，发现同模型智能体间偏见传播系数为0.157-0.352，且增大评估委员会规模可减少72.4%的传播效应。

链接：https://arxiv.org/abs/2606.20493

机构：Qilu Institute of Technology, School of Software Engineering（齐鲁理工学院软件工程学院）

作者：Zewen Liu

英文摘要： When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a formal framework for measuring how evaluator biases spread across interacting LLM agents. In a controlled 3-agent experiment using DeepSeek-chat with three distinct evaluator bias profiles (structured, balanced, evidence-based), we measure the Cross-Agent Contagion Matrix Gamma_3 and find that evaluator biases consistently propagate between agents (gamma in [0.157, 0.352]), even within the same underlying model. We identify three propagation regimes governed by the spectral radius rho(Gamma_N), and demonstrate that homogeneous-model agents produce contagion coefficients 3-5x weaker than cross-model coefficients observed in prior work (MM-EPC: gamma approx 0.85-1.3), placing them in the suppression regime. We show that increasing evaluator committee size from k=1 to k=3 reduces effective contagion by 72.4%, providing an actionable mitigation strategy. We release the open-source Contagion Network experimental framework.

AI 总结：研究DiffusionGemma在连续潜空间中的推理透明度，通过变量透明度和算法透明度分解，发现可解释的令牌瓶颈将不透明串行深度降至Gemma 4的1.1倍，并揭示扩散特有现象。

链接：https://arxiv.org/abs/2606.20560

机构：Google（谷歌）

作者：Joshua Engels, Callum McDougall, Bilal Chughtai, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue, João Gabriel Lopes de Oliveira, Rohin Shah, Neel Nanda

英文摘要：LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, DiffusionGemma performs a larger fraction of its computation in a continuous latent space; does this make its reasoning less transparent? We study this question by decomposing transparency into two components: variable transparency, whether we understand intermediate snapshots of a model's computational state; and algorithmic transparency, whether we can use these snapshots to reconstruct the process by which the model arrived at its outputs. Naively, DiffusionGemma has poor variable transparency: its opaque serial depth, the amount of serial computation that occurs in between interpretable model states, seems at first 28.6X higher than the corresponding autoregressive Gemma 4 model. However, we show that we can map the information flowing between denoising steps through an interpretable token bottleneck with no decrease in downstream performance. Treating these intermediate states as interpretable reduces the opaque serial depth to just 1.1X that of Gemma 4. Algorithmic transparency is harder for diffusion models than for autoregressive models because all token predictions in the canvas can change at every denoising step, giving the model the power to implement complicated distributed algorithms during the denoising process. To begin bridging this gap, we conduct a suite of interpretability case studies, uncovering initial evidence of novel diffusion-specific phenomena such as non-chronological reasoning, token and sequence smearing, and intermediate-context reasoning. Finally, we test monitorability, a key application of transparency that measures whether model outputs are useful for downstream tasks. We find that DiffusionGemma is similarly monitorable to Gemma 4.