机器学习学术速递[7.8]

AI 总结：研究旨在解决深度自动编码器架构中PCA属性难实现的问题，提出ODIN架构，通过纳入几何约束使潜在维度正交且按方差排序，兼具PCA可解释性与深度网络表达力，还给出理论依据及合成与真实数据集实证结果。

链接：https://arxiv.org/abs/2607.05653

机构：George Mason University（乔治梅森大学）

作者：Jeanie Schreiber, Tyrus Berry, Zeeshan Ahmed

英文摘要：Principal Component Analysis or PCA-like properties (orthogonality, variance ranking) are seldom realized in deep autoencoder architectures. In this work, we present ODIN (Orthogonal Dendritic Intrinsic Network), a novel autoencoder architecture that recovers PCA-like latent structure in a fully non-linear regime. By incorporating a set of geometric constraints directly into the training objective, ODIN encourages latent dimensions to be mutually orthogonal and ordered by explained variance, mirroring the interpretable decomposition of PCA while retaining the expressive power of deep networks. We provide theoretical grounding for these constraints and demonstrate their compatibility with standard encoder-decoder frameworks. We also establish empirical results for both synthetic and real world datasets, establishing a principled path toward interpretable, structured feature learning and dimensionality reduction.

AI 总结：研究针对实际量子设备噪声高、表面码量子比特成本大的问题，提出用双变量双循环码的距离为4的量子纠错技术用于QCNNs，经模拟验证该低开销纠错技术是迈向实用QCNNs的一步。

链接：https://arxiv.org/abs/2607.05724

作者：Alejandro Rosales, Animesh Yadav

英文摘要：Quantum convolutional neural networks (QCNNs) combine the power of quantum computing and classical CNN for computational speedup in classification tasks. However, noise levels on state-of-the-art quantum devices remain too high for practical QCNN execution. In addition, despite the reliable surface code providing a method for error rates below a threshold value, they have a prohibitively large qubit cost. Recently introduced bivariate bicycle (BB) codes are of particular interest for their high error threshold, constant encoding rate, and linear code distance. Through simulation with realistic hardware noise sources, we demonstrate that a 4-qubit unprotected QCNN fails to converge and exhibits a worse learning rate compared to numerical simulations. Addressing both limitations, we propose a distance-4 BB quantum error-correction (QEC) technique for QCNNs. In doing so, we validate that our low-overhead QEC technique for QCNNS represents a step toward practical QCNNs.

AI 总结：研究利用自动微分推导神经场闵可夫斯基泛函的平滑蒙特卡罗估计器，建立设计规则，对比不同方法在二维和三维的表现，发现三维存在梯度下降隐藏拓扑噪声问题，发布相关内容，展示其在高频辅助损失方面的应用及优势。

链接：https://arxiv.org/abs/2607.05815

作者：Gunner Levi Howe

英文摘要： The Minkowski functionals of a field's excursion sets -- area, boundary measure, and Euler characteristic -- describe its level-set morphology; the Euler characteristic is the cheapest handle on topology. We derive smooth Monte-Carlo estimators for all three of a continuous neural field, evaluated at scattered points via the co-area formula and Gauss-Bonnet, using only autodiff: no grid, no complex, no persistence. The estimator is accurate to 1-3% against exact topology in 2D and 3D, and costs about 3 ms per iteration where a persistent-homology (PH) loss on a cubical grid costs 650-1000 ms -- a 250x gap. We establish four design rules without which these losses silently fail: a dense level ladder (invariants are flat in the parameters away from transitions), a $C^2$ backbone (ReLU nets hide curvature in kinks), the full Minkowski vector (Euler characteristic alone is an alternating sum, gamed by debris-hole cancellation; pricing perimeter closes the channel), and sampling-scale coverage. In 2D the vector-valued cap is the only method in a controlled comparison that both repairs topology (3/3 seeds) and preserves fidelity -- uniform smoothing repairs at 11-17x the fidelity cost, and the Euler term alone repairs nothing. In 3D neural-SDF fitting, however, a failure mode we believe general to any sampled soft topology objective appears: gradient descent adversarially hides topological noise below the sampling density, where the estimator is blind -- spurious-feature counts are invariant to 4x more samples, and closing the window needs cubically many points, erasing the cost advantage. A grid-based PH baseline, whose complex is the evaluation resolution, solves the same benchmark ($4/9$ exact; median $b_1$ error 1 vs. ours above $10^4$). The 250x cost of persistence is, at present, the price of having no null space. We release estimators, receipts, and benchmarks.

AI 总结：研究在差分隐私训练中，标准一阶优化器因忽略损失曲率导致效率低的问题。提出DP-NGD框架，通过解耦曲率估计等方法解决集成NGD与DP的挑战。实验证明该框架在精度和收敛速度上有显著提升，突破效用瓶颈。

链接：https://arxiv.org/abs/2607.05866

机构：Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）； Metropolitan College, Boston University（波士顿大学大都会学院）

作者：Pan Li, Kai Chen, Shuai Chang, Shengzhi Zhang, Peizhuo Lv, Jinwen He

英文摘要：Under a fixed privacy budget, the utility of differentially private (DP) training is ultimately determined by its optimization efficiency. Standard first-order DP optimizers such as DP-SGD rely solely on local gradients and ignore the underlying loss curvature. This geometric blindness causes severe zigzagging in ill-conditioned landscapes, squandering precious privacy budgets on inefficient iterations. Practitioners are thus trapped in a bind: either stop training prematurely or inject massive per-step noise, both of which critically compromise final model utility. Natural Gradient Descent (NGD) resolves this by preconditioning gradients with curvature, aligning updates with the loss geometry and extracting more efficient signal from every noisy step, offering a principled pathway to break the privacy-utility bottleneck. Despite its theoretical appeal, directly integrating NGD with DP introduces fundamental challenges: curvature estimation itself consumes prohibitive privacy budgets, isotropic DP operations conflict with the anisotropic scaling of NGD, and the inverse curvature catastrophically amplify parameter updates in flat directions, causing training instability. We propose DP-NGD, a practical framework that systematically addresses these obstacles by decoupling curvature estimation from private data, reconciling isotropic DP constraints with anisotropic second-order optimization via a whitened-space mechanism, and dynamically clamping the curvature to stabilize training. Extensive experiments on standard benchmarks demonstrate that DP-NGD achieves state-of-the-art accuracy, breaking through the utility ceilings of first-order baselines while delivering up to a $10\times$ convergence speedup under the same privacy budget.

AI 总结：研究低秩训练中优化器子空间不可识别性问题，发现不同小批量计算的子空间估计差异大，平均无法恢复其余方向。提出将刷新视为坐标变化，如LDAdam表现良好，还明确了GaLore有效原因及相关检查要点在于可重现秩k*。

链接：https://arxiv.org/abs/2607.05872

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

作者：Noel Thomas

英文摘要：Memory-efficient optimizers such as GaLore train large language models by projecting gradients onto a rank-r subspace recomputed every T steps, assuming this subspace is a slowly drifting object that can be tracked. We show that beyond a small reproducible core, there is no such object. Two estimates of the top-r subspace computed at the same step from disjoint minibatches disagree as much as estimates computed T steps apart (0.73 vs 0.74 of the maximal chordal distance sqrt(2r), at Pythia-160M with r=128): the apparent rotation at each refresh is dominated by estimator noise. This holds across four model families in three architecture classes from 70M to 6.9B parameters, strengthening with scale, and more weakly in a vision transformer. Only ~39 of 128 directions are reproducible across minibatches, and averaging cannot recover the rest: under N-fold averaging the gradient's spectral tail shrinks as N^(-1/4) rather than the N^(-1/2) of pure noise, so no averaging budget makes the subspace well defined. What helps instead follows from treating each refresh as a change of coordinates for Adam's state. Carrying the second moment blindly is provably about (r-k*)/2 worse than the best rotation-blind estimator, while the first moment transports exactly through the rotation, the optimal linear map under isotropic gradients and the rule LDAdam uses. At 1B over 40k steps (3 seeds), full LDAdam reaches 18.7 perplexity at beta2=0.999, beating untransported GaLore after its best beta2 fix (19.3); shortening the second-moment memory to beta2=0.99 helps the refreshing optimizers, though for canonical GaLore the effect is small and a full-rank control reverses it. One measurable fact, subspace non-identifiability, clarifies why GaLore works, which patches work, and what to check before trusting a low-rank assumption: the reproducible rank k*.

AI 总结：本文提出K-ABENA框架，通过排除低损失观测值降低训练成本。其标准形式结合特定设计与重加权得无偏梯度估计器，证明了收敛保证等。还对比了补偿与未补偿估计器在不同情况下表现，在真实数据集上补偿估计器节省计算且与全批量SGD无显著差异。

链接：https://arxiv.org/abs/2607.05903

机构：NeuroSoft IA； YekoElite University（耶科精英大学）

作者：Jean-Francois Bonbhel

英文摘要： We present K-ABENA (K-Adaptive Backpropagation with Error-based N-exclusion Algorithm), a selective gradient computation framework that reduces per-iteration training cost by excluding a fraction of low-loss ("minor") observations from the backward pass. Its canonical form (v3) combines a defensive-mixture sampling design over the minor set with Horvitz-Thompson inverse-probability reweighting, yielding a design-unbiased Horvitz-Thompson gradient estimator (Lemma 2) and whose self-normalized practical variant carries a bias of order O(1/m) with an explicit constant (Lemma 3). We prove an O(1/sqrt(T)) non-convex convergence guarantee for SGD under the estimator, with an additive term that quantifies the residual bias (Theorem 1). We further prove that uncompensated loss-based selection - a family that includes OHEM, SBP, and the two earlier K-ABENA variants - admits no stationary point at any minimizer where its selection bias is bounded away from zero (Proposition 2), and we quantify this failure empirically: at 0.17% class imbalance, uncompensated variants reach test AUC 0.53-0.62 versus 0.9998 for full-batch SGD, while the compensated estimator attains 0.9991 at identical 28.4% compute savings. On real datasets (Breast Cancer, Digits, Wine, Diabetes) the compensated estimator is statistically indistinguishable from full-batch SGD (paired permutation tests, p >= 0.5; Section 7) while saving 28-54% of per-epoch gradient computation. A biased "regularized mode" (the earlier half-domain variant) is retained as an option with a proven exact bias decomposition (Lemma 5) and quantified contraindications: it collapses to 0.386 accuracy under 40% label noise (baseline: 0.832) and to 0.53 AUC under extreme imbalance. Every advantage and every limitation reported in this paper is either proved or measured; all experiments are CPU-scale (NumPy/scikit-learn) and their scope is stated explicitly.

AI 总结：本文提出样条网络这一等几何深度学习方法，用于复杂壳体结构设计分析。基于封闭样条表示构建，能无数据或数据驱动应用。无数据时可结合CAE需求，数据驱动时可作主干网提供可解释性，经数值示例验证了该方法的有效性。

链接：https://arxiv.org/abs/2607.06026

作者：Shizhou Luo, Xiaodong Wei

英文摘要：We present a novel isogeometric deep learning method, termed SplineNet, for the seamless design and analysis of shell structures with complex geometries. The proposed approach is built upon watertight spline representations, e.g., analysis-suitable unstructured T-splines, and features exact geometric descriptions of Computer-Aided Design (CAD) models in neural networks. Bézier extraction is used to build the network architecture, where Bernstein polynomials serve as the nonlinear activation functions. SplineNet can be applied in a data-free or data-driven way. In the data-free case, energy-based formulations can be naturally incorporated as loss terms, which fulfill the need of Computer-Aided Engineering (CAE) and can be accurately calculated. In particular, the Kirchhoff--Love (KL) model is adopted to solve for the mechanical behaviors of shell structures. This way, CAD and CAE can be tightly integrated in a deep neural network without the time-consuming model/data exchange process. In the data-driven case, SplineNet can be used as the trunk net of Deep Operator Networks (DeepONet) to provide interpretability. Given such a trained network and unseen input data, results can be immediately obtained without retraining the network or repeatedly performing the traditional workflow for analysis. In the end, a variety of numerical examples are studied to demonstrate the effectiveness of the proposed method, especially when real-world complex geometries are involved.

AI 总结：针对RVFL模型在处理几何关系和多特征视图的局限，提出IFGRVFL-MV模型，含直觉模糊集、图嵌入和多视图学习三组件，经实验验证其在UCI和KEEL基准数据集上分类准确率超现有模型，是不确定性和多视图领域的进展。

链接：https://arxiv.org/abs/2607.05635

作者：Vrushank Ahire, Yogesh Kumar, M.A. Ganaie

英文摘要：Random Vector Functional Link (RVFL) networks are popular due to their fast training and universal approximation capabilities. However, RVFL models face challenges in preserving geometric relationships and utilizing multiple feature views effectively. To address these limitations we propose the Intuitionistic Fuzzy Graph Embedded Random Vector Functional Link with Multiview Learning (IFGRVFL-MV) model. The proposed approach comprises three key components: intuitionistic fuzzy sets for uncertainty handling, graph embedding to capture intrinsic geometric structures, and multiview learning to use complementary information from multiple feature spaces. The model assigns intuitionistic fuzzy membership and non-membership values to data points making it robust to outliers. Also, the graph embedding framework preserves topological structures, increasing the generalization performance. We performed experiments on benchmark datasets from UCI and KEEL repositories which concludes that IFGRVFL-MV outperforms existing models in classification accuracy. Our results establish that IFGRVFL-MV is a promising advancement in the domain of uncertainty and multiview environments.

AI 总结：研究针对分子性质预测难题，提出三分支模块化融合神经网络，综合三种模态数据，经后期融合架构建立多模态潜在空间，在QM9基准测试中表现出色，降低误差，为高通量虚拟筛选提供高效模型。

链接：https://arxiv.org/abs/2607.05736

机构：Duke University（杜克大学）； Georgia Institute of Technology（佐治亚理工学院）

作者：Qiwei Han, Chi Zhou, Ruobing Wang, Zheng Ma

英文摘要： Molecular property prediction often relies on isolated data modalities, where continuous 3D graph neural networks (GNNs) struggle to efficiently capture long-range topological dependencies and exact macroscopic heuristics. In this work, we introduce a parameter-efficient Tri-Branch Modular Fusion Neural Network that synthesizes three orthogonal modalities: 3D spatial geometry (SchNet), discrete topological grammar (SMILES via ChemBERTa), and explicit macroscopic physicochemical descriptors (Deep & Cross Network). By bypassing standard scalar readouts and employing a shared late-fusion architecture, the framework establishes a mathematically rigorous multimodal latent space that effectively resolves the arithmetic and oversmoothing limitations of local message passing. We evaluate the proposed architecture on the QM9 benchmark, targeting the extensive thermodynamic property of atomization energy at 0 K ($U_0^{\mathrm{atom}}$). Through systematic combinatorial ablation and latent bottleneck optimization ($d_e=64$), the tri-modal framework achieves a validation Mean Absolute Error (MAE) of 0.0207 eV. Operating with fewer than one million parameters, this architecture decisively surpasses the sub-chemical accuracy threshold and yields a substantial 20.6% error reduction over a strictly controlled geometric baseline. Ultimately, our findings demonstrate that integrating orthogonal macroscopic and topological data streams provides a synergistic, $\mathcal{O}(1)$ physical shortcut. This multimodal alignment offers a highly efficient alternative to brute-force parameter scaling, establishing a robust surrogate model for high-throughput virtual screening (HTVS) pipelines.

AI 总结：研究针对治疗性抗体发现中抗体亲和力排序问题，提出AbICL框架，结合预训练结构编码器与上下文排序头，用情节元训练策略，实验表明其在多基准上优于现有方法，凸显ICL在抗体亲和力排序中的潜力。

链接：https://arxiv.org/abs/2607.05846

作者：Zhiyuan Chen, Jing Hu, Junzhe Wang, Yueyang Huang, Xinyi Yang, Zhaoyang Wang, Feng Zhu

英文摘要：Accurate ranking of antibody candidates according to their binding affinity is essential for therapeutic antibody discovery. However, existing methods treat affinity comparisons independently and ignore the contextual information encoded in other labeled comparisons, limiting their ability to capture antigen-specific binding landscapes. For many target antigens, a small number of experimentally characterized affinity comparisons are often available. An important question is whether the model can exploit these existing comparisons to infer antigen-specific ranking patterns that facilitate subsequent affinity ranking. This form of learning from labeled demonstrations closely resembles the paradigm of In-Context Learning, motivating us to revisit antibody affinity ranking from an ICL perspective. To this end, we propose AbICL, an ICL framework for antigen-specific antibody affinity ranking. AbICL combines a pretrained structural encoder with a context ranking head and is trained with an episodic meta-training strategy that enables the model to leverage support demonstrations for test-time adaptation without gradient updates. Experiments on the AbRank benchmark demonstrate that AbICL consistently outperforms existing ranking baselines across almost all data splits and evaluation benchmarks. Further analysis shows that the value of contextual demonstrations depends on how well they match the target inference task, and becomes increasingly pronounced under distribution shift and fine-grained affinity discrimination. These findings highlight the potential of ICL as an effective paradigm for antigen-specific antibody affinity ranking, particularly in challenging settings where a single global ranking function is insufficient.

AI 总结：研究针对高维系统中智能系统自适应要求间的矛盾，聚焦回声状态网络，提出基于扰动学习成本正交分解的在线自监督学习规则，降低有效扰动维度，避免方差增长，为可扩展及硬件兼容学习提供设计原则。

链接：https://arxiv.org/abs/2607.06079

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：Taiki Yamada, Kantaro Fujiwara

英文摘要：Intelligent systems should not only solve tasks but also adapt under real-world constraints. Autonomous adaptation via self-supervised learning, sequential adaptation via online learning, and memory-efficient implementation via perturbation-based learning are important requirements for such systems. However, these requirements are generally in tension for high-dimensional systems, because perturbation-based learning suffers from variance that grows with the dimension of the perturbed variables. In this study, we focus on echo state networks (ESNs), where this tension naturally arises in large reservoirs. We propose a perturbation-based learning rule for online self-supervised learning in ESNs. The proposed rule is derived from an orthogonal decomposition of the self-supervised learning cost, which separates an input-dependent component from a redundant component determined by the fixed ESN parameters. By perturbing only the input-dependent component, the effective perturbation dimension is reduced from the reservoir dimension to the input dimension. Thus, the proposed method preserves self-supervised adaptation, online learning, and scalar-feedback perturbation learning, while avoiding reservoir-size-dependent variance growth. This suggests a design principle for scalable and hardware-compatible learning: online learning should be restricted to the dynamically necessary low-dimensional component of the objective.

AI 总结：针对多池CEST MRI采集时间长、有限数据重建高分辨率Z谱难的问题，提出物理信息洛伦兹编码（LE），将CEST重建作为自监督任务，通过隐式连续坐标学习实现，实验证明其优于现有方法，能确保准确的定量代谢物映射。

链接：https://arxiv.org/abs/2607.06132

作者：Dexuan Li, Yupeng Wu, Chenglong Wang, Hanlin Liu, Hui Zhen, Jianqi Li, Guang Yang

英文摘要： Multi-Pool Chemical Exchange Saturation Transfer (CEST) MRI provides valuable metabolic information but is clinically limited by long acquisition times. Although sparse sampling reduces scanning time, reconstructing high-resolution Z-spectra from limited data remains an ill-posed inverse problem. Conventional interpolation and generic Implicit Neural Rep-resentations (INRs) often lack physical constraints, leading to spectral artifacts and physically invalid signals. To address this, we propose Lorentz Encoding (LE), a physics-informed framework that formulates CEST reconstruction as a self-supervised reconstruction task via implicit continuous coordinate learning. Unlike generic positional encodings, LE regularizes the continuous spectral mapping by projecting sparse coordinates into a physically constrained space governed by a combination of parametric Lorentzian profiles with learnable basis functions. This mechanism effectively reduces noise and enforces consistency with physical models. Experiments on in vivo human brain data demonstrate that LE significantly outperforms state-of-the-art methods. Specifically, under a 39-point sampling strategy, LE achieves a PSNR of 57.58 dB and an SSIM of 0.9994. Furthermore, the learned physics-informed encodings form a continuous, geometrically ordered trajectory in the latent space, ensuring accurate quantitative metabo-lite mapping (APT, NOE, MT).

AI 总结：介绍用于学习偏微分方程解族有限维嵌入的物理信息框架，用多头神经网络，经头正交化惩罚降维，应用于多个方程，结果显示能有效降维且主成分谱稳定，还能得到不变的频率分布，确立了相关可观测量。

链接：https://arxiv.org/abs/2607.06348

机构：ICREA（加泰罗尼亚研究与高等研究院）； Flatiron Institute（熨斗研究所）

作者：Raul Jimenez, Svitlana Mayboroda, Pavlos Protopapas, Leonid Sarieddine, David N. Spergel, Pedro Tarancón-Álvarez

英文摘要：We introduce a physics-informed framework for learning finite-dimensional embeddings of solution families of partial differential equations. The method uses a multihead Physics-Informed Neural Network in which a shared body learns a latent manifold representing the solution space, while linear heads reconstruct individual solutions associated with different initial conditions. A head-orthogonalization penalty removes degeneracies in the latent representation and stabilizes the principal-component spectrum across training realizations. Because the initial condition is built into the network output by construction, these principal components measure the additional variability the network learns on top of the initial profile, not the full solution itself. We apply the method to the one-dimensional viscous Burgers equation, with the heat and wave equations as robustness checks. For a latent dimension $n_b=20$, the learned manifolds exhibit pronounced effective dimensional reduction: for Burgers dynamics, only $2$-$4$ principal components capture about $95\%$ of the latent-space variance, while $4$-$7$ capture about $99\%$, depending on the initial-condition family; the same qualitative compression holds for the heat and wave equations. We also split the wavenumber axis into bands (``Fourier shells'') and measure how much each band contributes to every principal component. The resulting frequency profile is invariant under the change-of-basis freedom that the orthogonalization penalty leaves in the latent space, and is therefore reproducible across independent training runs. More broadly, this establishes the learned spectral profiles and principal components as robust observables of solution-manifold geometry.

AI 总结：研究提出EntroPath流形学习方法，基于最大熵随机游走构建差异，通过Varadhan热核公式使自由能差异在短时间极限下收敛于平方测地线距离，在合成流形和单细胞基准测试中表现良好，尤其在特定流形上优势明显。

链接：https://arxiv.org/abs/2607.06497

机构：Krakow University of Economics（克拉科夫经济大学）

作者：Przemysław Rola

英文摘要：We introduce EntroPath, a manifold learning method that recovers geodesic geometry from data graphs through ensembles of diffusion paths. Many existing graph-based embeddings rely either on locally normalised random walks or on shortest-path distances. The former can concentrate diffusion in densely sampled regions, while the latter are sensitive to spurious shortcut edges in the graph. EntroPath instead builds its dissimilarities from the maximum entropy random walk (MERW), which aggregates the full ensemble of k-step paths between points rather than relying on any single trajectory. We show that the resulting free-energy dissimilarity converges to squared geodesic distance in the short-time limit, via Varadhan's heat-kernel formula. The diffusion depth k interpolates smoothly between local neighbourhood structure and global manifold geometry, and the symmetrised kernel admits an exact Gram factorisation connecting EntroPath to kernel methods. We further provide scalable extensions via landmark projection and diffusion-potential pseudotime. Across synthetic manifolds and single-cell benchmarks, EntroPath consistently matches or outperforms diffusion- and shortest-path-based methods, while remaining competitive with neighbourhood-preserving embeddings (UMAP, t-SNE) on local-structure metrics. Its gains are most pronounced on manifolds with non-uniform sampling density and well-separated branching trajectories, where path-ensemble diffusion more faithfully preserves the underlying geodesic geometry.

AI 总结：研究提出将大语言模型智能体的执行框架视为可学习控制层，通过有限 horizon 的框架马尔可夫决策过程，利用离线强化学习训练轻量级控制器，在多领域实验中改进验证行为、提高任务质量，证明框架控制可学习且离线支持有局限。

链接：https://arxiv.org/abs/2607.05458

机构：University of Toronto（多伦多大学）； Emory University（埃默里大学）

作者：Haiwen Yi, Xinyuan Song

英文摘要： Large language model (LLM) agents are usually improved by changing prompts, models, or hand-written workflows, while the execution harness around the model is treated as fixed infrastructure. We argue that this harness is itself a learnable control layer. We formalize harness operation as a finite-horizon Harness MDP, where a lightweight controller selects structural execution actions while the LLM executor remains frozen. The controller is trained from offline rollouts using advantage-weighted regression with only terminal task-rubric rewards. We also separate final task quality from a post-hoc Harness Maturity Score, which measures whether the harness follows reliable execution patterns rather than only whether the final answer is correct. This separation gives a finite-buffer view of harness learning: final-quality gains require high-return support in the offline buffer, while process behavior can shift whenever it aligns with advantage-weighted actions. Across six controlled domains and two public-benchmark adapters, the learned controller consistently improves verification behavior and selectively improves final task quality, with the largest gains on adapted tau-bench retail, adapted AgentBench DB-Bench, and coding with a calibrated structural verifier. Ablations against behavior cloning and Forced CHECK show that the gains are not explained by imitation or by simply adding checks. These results identify harness control as a learnable layer for frozen LLM agents, while showing that offline support limits when better process control becomes better final answers.

AI 总结：研究针对强化学习中环境反馈稀疏或延迟问题，提出自我审查强化学习框架，通过策略梯度优化自我审查，经选择性蒸馏内化改进到基础策略，用跨情节记忆保留成功审查，在GSM8K基准上评估，该框架优于基线且学习效率更高。

链接：https://arxiv.org/abs/2607.05541

作者：Muhammad Zain Amin, Kibele Sebnem Yildirim

英文摘要：Reinforcement Learning is commonly used to train large language models using environmental feedback. In applied settings, the environment usually provides sparse or delayed feedback. This makes it difficult for the model to pinpoint which actions in its reasoning led to success or failure. So, learning effectively from these signals is hard because the model must determine how each failure should inform meaningful behavioral corrections in subsequent iterations. We introduce a training framework, Self-Review Reinforcement Learning, that embeds an explicit self-review step into each RL episode. When a first-pass response fails, the model generates a self-review to identify what went wrong, which conditions an improved second attempt. Unlike inference-time reflection approaches, such as Reflexion, the framework optimizes self-review with policy gradients and internalizes improvements into the base policy via selective distillation, ensuring they persist across future episodes. A cross-episode memory keeps successful self-reviews for reuse when encountering similar tasks in future episodes during training. We evaluate SRRL against a standard RLVR baseline using the GRPO optimizer across two language models, Qwen 3-4B and OLMo-3- 7B, on GSM8K benchmark. SRRL consistently outperforms the RLVR in final reward performance and achieves greater learning efficiency by successfully transforming feedback into behavioral improvement.

AI 总结：研究智能电网暂态稳定性控制问题，提出FedPPO-PG框架，将其转化为协作多智能体强化学习问题，通过物理基础邻域、引导策略初始化和集中评论家等方法，在模拟中取得良好效果，减少稳定时间、降低控制功率且满足实时要求。

链接：https://arxiv.org/abs/2607.05553

作者：Omar Al-Refai, Ibrahim Shahbaz, Adam Ali Husseinat, Eman Hammad

英文摘要：Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading failures. This paper proposes FedPPO-PG, a Federated Multi-Agent Proximal Policy Optimization framework with Physics-Grounded neighborhoods, which reformulates transient stability control as a cooperative multi-agent reinforcement learning problem optimized directly against closed-loop stability objectives. Each generator hosts an independent local actor augmented with the frequency deviations of its two most strongly coupled electrical neighbors, identified from the post-fault Kron-reduced susceptance matrix. A guided policy initialization phase warm-starts all actors from the classical decentralized controller, while a centralized critic guides advantage estimation under the centralized training--decentralized execution (CTDE) paradigm. Evaluated on a simulation of the IEEE 39-bus benchmark system across five training and three unseen fault contingencies, FedPPO-PG achieves 100% stabilization in all 24 trials, reduces mean stability time by 72.4%, and cuts the control power by 7-14 times compared to the centralized baseline. Each actor executes independently with no central coordinator at deployment, and the per-actor inference latency satisfies the IEEE/IEC 60255-118-1-2018 real-time reporting requirements.

AI 总结：研究随机订单到达下自主订单拣选机器人的动态电池充电问题，提出基于近端策略优化的深度强化学习框架，能动态学习充电站选择和充电时长，实验表明该框架可提高订单完成率、减少充电时间并验证其鲁棒性。

链接：https://arxiv.org/abs/2607.05683

机构：Indian Institute of Management Bangalore（班加罗尔印度管理学院）； University of Antwerp（安特卫普大学）

作者：Taniya Shaji, Abhay Sobhanan, Christof Defryn

英文摘要：Battery charging of Autonomous Mobile Robots (AMRs) in warehouses is a critical operational challenge that heavily impacts both order processing times and throughput. In this study, we address the dynamic AMR charging problem under stochastic order arrivals, where robots must learn optimal charging decisions. Traditional fixed-rule heuristics often prove suboptimal in dynamic environments and fail to account for multi-AMR coordination, leading to severe resource inefficiencies. To overcome these limitations, we propose a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) framework designed for multi-block warehouses with fixed charging stations. Our model dynamically learns two key decisions: charging station selection and optimal charging duration, explicitly accounting for anticipated queuing times at the stations. Extensive numerical experiments benchmark the proposed model against state-of-the-art DRL and traditional heuristic approaches. Results demonstrate that our PPO framework increases order-completion rates by up to 6\% compared to the strongest baseline, while significantly reducing the total time dedicated to recharging operations. Furthermore, we validate the model's robustness across diverse warehouse configurations and stochastic arrival rates. Finally, we interpret the learned DRL policy, offering valuable operational insights into its superiority over standard benchmarks.

AI 总结：针对电网调度中分布鲁棒优化依赖预测场景构建模糊集存在的问题，提出基于决策聚焦的生成框架，依下游运行成本优化场景，适配多种生成模型，开发可微场景选择器，案例研究显示可有效降低运行成本。

链接：https://arxiv.org/abs/2607.05830

作者：Yangze Zhou, Yihong Zhou, Thomas Morstyn, Yi Wang

英文摘要：The increasing uncertainty from flexible demand and renewable generation has made distributionally robust optimization (DRO) an important tool for robust power system dispatch. DRO relies on forecast scenarios to construct ambiguity sets, but conventional scenario generation pipelines are often trained in an accuracy-oriented manner and may neglect spatial correlations among uncertainties. This mismatch can produce ambiguity sets that are statistically plausible but suboptimal for downstream operation. This work proposes a decision-focused generative framework for correlated scenario generation in DRO-based dispatch. Instead of training generative models solely to fit the historical uncertainty distribution, the proposed framework optimizes generated scenarios according to their induced downstream operational cost. The proposed framework is tailored to mainstream generative models, including variational autoencoders, generative adversarial networks, and diffusion models, while capturing the joint distribution of uncertainties across buses. To improve computational tractability, we further develop a differentiable scenario selector that selects decision-relevant scenarios from a generated pool and can be trained within the same decision-focused pipeline. Case studies demonstrate that the proposed framework effectively reduces 0.80%-2.02% operational cost across different generative models compared to accuracy-oriented methods.

AI 总结：研究多买家市场中卖家与买家的谈判，提出基于可验证奖励的强化学习方法，使卖家能平衡市场探索与剩余提取，实现多阶段战略演变，提升谈判技能，提取更高剩余，且策略可推广。

链接：https://arxiv.org/abs/2607.05863

机构：Institute for Data, Systems, and Society, Massachusetts Institute of Technology（数据、系统与社会研究所，麻省理工学院）； Mitch Daniels School of Business, Purdue University（米奇·丹尼尔斯商学院，普渡大学）； The Division of Physics, Mathematics and Astronomy, California Institute of Technology（物理、数学与天文学部，加州理工学院）； Department of Computing and Mathematical Sciences, California Institute of Technology（计算与数学科学系，加州理工学院）； H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（H. 米尔顿·斯图尔特工业与系统工程学院，佐治亚理工学院）； Department of Civil and Environmental Engineering, Operations Research Center, Massachusetts Institute of Technology（土木与环境工程系、运筹学中心，麻省理工学院）

作者：Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Xin Chen, David Simchi-Levi

英文摘要：Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting private information, such as reservation costs and hidden valuations. A prevalent yet complex scenario involves a single seller negotiating concurrently with multiple buyers, each possessing heterogeneous, private budgets. In such settings, constrained by a limited number of communication turns, the seller must balance exploring the broader market to discover the highest valuation with concentrating sufficient turns on a single target buyer to secure the best possible outcome. Our analysis reveals a significant gap in standard Large Language Models (LLMs): while these models are linguistically proficient, they fail to act as effective economic decision-makers. Specifically, they exhibit a failure to explore the buyer pool, often fixating on the current highest bid rather than strategically investigating the market to discover latent high valuations. In this paper, we propose a specialized training recipe using Reinforcement Learning from Verifiable Rewards (RLVR). By anchoring the reward function to objective economic outcomes, the strategic balance between market discovery and surplus extraction emerges natively through the learning process. Our results demonstrate that the trained seller undergoes a multi-stage strategic evolution, learning to leverage price anchoring and strategic probing to identify more profitable counterparties. The agent extracts a substantially higher surplus than frontier models by both improving its persuasive bargaining skills and consistently closing deals with high-value buyers. Finally, we show that our seller strategies generalize robustly to unseen buyer negotiation styles and budget distributions.

AI 总结：研究人机服务系统中任务处理的资源分配问题，提出UCB - DPP策略，结合上置信界与漂移加惩罚控制学习未知参数并做队列感知决策，实现\(\widetilde{\mathcal{O}}(K\sqrt{T})\)遗憾值，保证人工服务队列平均速率稳定性，优于自然基线。

链接：https://arxiv.org/abs/2607.06017

机构：Inria（法国国家信息与自动化研究所）； CREST（法国国立统计与经济管理学院）； ENSAE（法国国立统计与经济管理学院）； Institut Polytechnique de Paris（巴黎综合理工学院）； Luiss University（罗马路易斯大学）； Criteo AI Lab（Criteo人工智能实验室）

作者：Giovanni Montanari, Marco Scarsini, Vianney Perchet

英文摘要：We study a human-AI service system in which tasks arrive sequentially and are processed through a two-stage architecture: an automated chatbot followed, when necessary, by a human agent. We consider $T$ sequentially arriving tasks, each belonging to one of $K$ heterogeneous types. For each task the decision maker chooses how many resources to allocate to the chatbot, whose type-dependent success probabilities are initially unknown. Tasks not resolved by the chatbot enter type-dependent human-service queues, where they are processed by a human agent with unknown service rates. This model captures a central tradeoff in hybrid service systems: relying more on automation reduces human congestion but increases chatbot costs, while insufficient automation may overload the human agent. We propose the UCB-DPP policy, which combines Upper Confidence Bounds with Drift-Plus-Penalty control to learn the unknown parameters of the system while making queue-aware decisions. We prove that UCB-DPP achieves regret $\widetilde{\mathcal{O}}(K\sqrt{T})$ and guarantees mean-rate stability of the human-service queues. Simulations on synthetic instances show that the proposed policy outperforms natural baselines.

AI 总结：研究针对全原子生成蛋白质模型内存受限问题，提出 Design-CP 上下文并行推理策略，用于 RFdiffusion 3，在多 GPU 上扩展设计能力，可用于二十面体和八面体纳米颗粒设计，推动大型组装蛋白质设计发展。

链接：https://arxiv.org/abs/2607.05439

作者：Lorenzo Tarricone, Helen E. Eisenach, Aiko Muraishi, Charlotte M. Deane

英文摘要：Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- and atom-pair representations quickly exceed single-GPU memory as the number of chains and residues modelled grows. We introduce Design-CP, two context-parallel (CP) inference strategies for RFdiffusion 3 (1D row-sharding and 2D grid sharding with ring attention) that distribute the quadratic activations across a multi-GPU mesh while preserving pretrained weights. We characterise their scaling when sampling icosahedral assemblies, showing that the maximum feasible asymmetric subunit (ASU) size grows with the expected square-root trend in GPU count and that 2D sharding achieves better wall-clock scaling. Moreover, we show how strong point-group symmetry constraints make CP usable out of the box for end-to-end, all-atom design of icosahedral nanoparticles, yielding favourable in silico structural and interface metrics. Finally, we demonstrate octahedral nanoparticle design on a small cluster of workstation-grade 16GB GPUs, illustrating how Design-CP can be a practical path towards democratising large-assembly protein design.

AI 总结：研究变分自编码器后验坍缩问题，确定梯度不平衡和信息差距两个原因。提出λ-VAE，通过修改重参数化步骤解决问题，实现方差均衡。经标准基准验证，能减少坍缩维度、提升信息容量和重建质量。

链接：https://arxiv.org/abs/2607.05531

机构：Microsoft African Development Center（微软非洲开发中心）

作者：Girum Demisse

英文摘要：Variational Autoencoders (VAEs) frequently suffer from posterior collapse, a failure mode in which the approximate posterior converges to the prior, rendering the latent code uninformative. Despite extensive research, a unified account of why collapse occurs has remained an open question. We identify and formalize two logically independent but coupled causes. \emph{Gradient imbalance} occurs when the decoder's reconstruction signal vanishes faster than the $\mathbb{KL}$ regularization pressure as the posterior widens. \emph{Information gap} occurs when the stochastic sampling step discards a substantial fraction of the encoder's computed representation, attenuating decoder sensitivity and making collapse inexpensive. Both causes share the same collapse trajectory, and we show that the information gap is algebraically equivalent to mismatch between the aggregate posterior and the prior, unifying two pathologies. Subsequently, we introduce $\lambda$-VAE, which resolves both causes through a single modification to the reparameterization step: the sampling noise is scaled by per-dimension exponent, while the $\mathbb{KL}$ penalty retains the original posterior variance. This asymmetry shifts the stable training attractor away from the degenerate collapsed state, driving all latent dimensions toward the same equilibrium -- a mechanism we term \emph{variance equalization}. A closed-form optimal exponent per dimension follows from a net information gain objective, with a single hyperparameter controlling the reconstruction-generation tradeoff. We validate on standard benchmarks (Binary MNIST, Binary Omniglot, CIFAR-10, CelebA-64), showing consistent reductions in collapsed dimensions, information capacity gains of up to $2.8\times$ nats, and reconstruction quality improvements of up to $+0.33$ BPD.

AI 总结：研究基于x预测，通过端点可解码性提出截断跳跃采样方法，无需重新训练等操作，在多个模型和基准测试中减少神经函数评估次数20 - 70%，且质量相近，实现无轨迹重新设计的推理加速。

链接：https://arxiv.org/abs/2607.06114

作者：Xin Peng, Ang Gao

英文摘要：Diffusion and flow matching models generate high-quality samples, but their ODE samplers often need tens to hundreds of neural function evaluations (NFEs). This remains a practical challenge for released checkpoints, since many accelerators require additional design choices and training cost through retraining, distillation, or trajectory redesign. We investigate a different route based on $x$-prediction. During sampling, standard affine probability paths already expose $x_0$ information: an intermediate state and its path velocity determine a principled estimate of the clean sample. We formalize this property as \textbf{endpoint decodability} and show that the decoder is the minimum-MSE estimator $\mathbb{E}[x_0\mid x_t]$ under the usual $\ell_2$ objective. This yields \textbf{Truncated Jump Sampling} (TJS): stop the ODE at an early-exit time $t^*$ and return the decoded $x_0$. TJS requires no retraining, distillation, or architecture change. Across SDXL, SD3.5M, Z-Image-Turbo, and three class-conditional benchmarks, it reduces NFEs by 20--70\% with near-matched quality. The analysis also shows why endpoint prediction can work without straightening the trajectory, providing inference acceleration without trajectory redesign.

AI 总结： 文本到图像扩散模型的概念遗忘研究中，提出TILDE方法，将概念遗忘视为分布对齐问题，通过能量倾斜的无锚点目标抑制概念图像，用残差∇-GFlowNet训练实例化，实验显示其在多方面实现强大遗忘效果，提升保留率和分布保真度。

链接：https://arxiv.org/abs/2607.06432

机构：Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）； Sony AI（索尼人工智能公司）； Sony Group Corporation（索尼集团公司）

作者：Naveen George, Naoki Murata, Yuhta Takida, Konda Reddy Mopuri, Yuki Mitsufuji

英文摘要：Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and safety regulations, deployed systems must be able to suppress unwanted concepts after training. Existing methods often remove the target concept effectively, but practical unlearning also requires an equally fundamental property: the unlearned model should retain quality, diversity, and semantic coverage on benign generation. The gold standard is a retain-only model trained from scratch without the unwanted data. However, common erasure objectives do not specify which post-unlearning distribution should approximate this reference, leaving retention as an implicit consequence of the update rule. We propose TILDE, TILt-based Distributional Erasure, which formulates concept unlearning as a distributional alignment problem: the desired target is the minimum-deviation conditional distribution from the pretrained model under a forgetting constraint. This energy-tilted, anchor-free target suppresses concept-expressing images while preserving benign relative mass for each prompt. We instantiate this principle with residual $\nabla$-GFlowNet training, which learns the score correction induced by the forget energy relative to the pretrained diffusion model. Across objects, artistic styles, and characters, TILDE achieves strong forgetting while improving retention and distributional fidelity over prior baselines.

AI 总结：研究带协变量的时间序列预测器在协变量受干扰时的鲁棒性问题，提出外生随机失活方法，在多领域实验中显著提升鲁棒性，应用于双相关网络表现出色，优于有界架构对比模型，证明无需明确架构有界性，发布基准并推荐该方法为简单强大基线。

链接：https://arxiv.org/abs/2607.05452

机构：Wuhan University（武汉大学）； Hubei Key Laboratory of Water System Science for Sponge City Construction (Wuhan University)（海绵城市建设水系统科学湖北省重点实验室（武汉大学））

作者：Hao Hu, Xue-shan Ai

英文摘要：Time series forecasters that use exogenous covariates are fragile in deployment: when those covariates are noised, temporally misaligned, or missing, strong exogenous-fusion and exogenous-adapted models can degrade far above the endogenous-only floor. We study whether such robustness requires specialized architectures, or whether it can be obtained through a simple training intervention. We propose exogenous dropout, a model-agnostic method that randomly zeros whole exogenous channels during training. Across electricity-price forecasting, reservoir hydrology, and meteorology, exogenous dropout substantially improves robustness under Gaussian noise, temporal misalignment, and fully missing channels, while preserving clean accuracy. Applied to a dual-correlation network, it yields the most robust model in our experiments, outperforming a deliberately strong bounded architectural foil, BoundEx, which combines a learnable gate, a fallback residual to the endogenous backbone, and per-channel exogenous FiLM modulation. Architecture-by-dropout ablations, gate-behavior diagnostics, and a representation-level bound show that explicit architectural boundedness is not necessary for this robustness: an unbounded model trained with exogenous dropout is more robust than the bounded model in every domain. We release a corruption-robustness benchmark and recommend exogenous dropout as a simple, strong baseline for future work on time series forecasting with covariates.

AI 总结：研究DNN测试中停止问题，提出AdaStop框架，将测试视为成本效益决策过程，通过估计边际故障发现率并与阈值比较决定是否停止标注，实验表明该方法能以较少标注预算发现较多故障。

链接：https://arxiv.org/abs/2607.05461

作者：Bonan Shen, Wei-Jung Huang, Xin Liu, Jiazhou Gao, Tao Ning

英文摘要：Existing methods for testing deep neural networks (DNNs) primarily prioritize test inputs likely to reveal model faults under a fixed labeling budget. In practice, choosing that budget is difficult: too little testing misses failures, while too much incurs unnecessary labeling costs. This work studies the stopping problem in DNN testing. We formulate testing as a cost--benefit decision process in which labeling an input incurs cost $c$ and discovering a fault yields value $v$. Based on this formulation, we introduce \textit{AdaStop}, a framework that estimates the marginal fault discovery rate during testing and stops labeling when the estimated rate falls below the threshold $\tau = c/v$. Experiments across multiple datasets, architectures, and selection strategies show that $65$--$84\%$ of faults can be discovered using only $9$--$31\%$ of the labeling budget.

AI 总结：研究在新干预受安全约束的决策场景下的优化问题，利用共形预测构建反事实基线结果的不确定性区间，集成到安全贝叶斯优化中，确保约束 violation 率可控，还能适应协变量转移，提供了多方面分析。

链接：https://arxiv.org/abs/2607.05620

作者：Katherine Avery, Bruno Castro da Silva, David Jensen

英文摘要： In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold. For example, in clinical medicine, new treatments are often acceptable only if they do not worsen outcomes relative to an established standard of care. Safe Bayesian optimization maximizes an objective subject to safety constraints. In the setting that we consider here, safety is defined relative to a known baseline policy whose outcomes are counterfactual and therefore unobserved. Thus, the counterfactual outcomes of the baseline policy must be estimated and those (uncertain) estimates must be used to safely optimize the objective. We address this estimation problem by using conformal prediction to construct valid uncertainty intervals for counterfactual baseline outcomes, and we show how these intervals can be integrated into safe Bayesian optimization to ensure that constraint violations occur at or below a user-specified rate. We also show how to adapt these conformal estimates to different kinds of covariate shift. We provide a safety proof, experimental evidence, and a sensitivity analysis.

AI 总结：研究可分数据上全批量线性分类的速率控制情况，针对无记忆稳定性退火平滑符号下降，证明归一化迭代收敛特性，通过实验验证相关恒等式、展示预测图及缩放，还报告了多种情况的诊断，明确理论范围。

链接：https://arxiv.org/abs/2607.06013

作者：Xiangwu Wang, Chengwei Cao, Yicheng Song, Ran Bi, Peilin Yu

英文摘要：Adaptive gradient methods can favor max-margin separators that differ from gradient descent, yet a fixed positive numerical stability constant eventually changes the update geometry again. This paper studies the rate-controlled middle case for full-batch linear classification on separable data. For memoryless stability-annealed smoothed-sign descent with weighted exponential loss, we prove that the normalized iterates converge to the minimizer of a convex Burg-type barrier over a margin slice. The proof rewrites the dynamics exactly as entropic mirror ascent on a concave dual objective, controls the dual gap by a KL recursion, and yields an explicit S_t^{-1/2} normalized-iterate envelope. The static barrier geometry is fully characterized, including KKT conditions and both endpoint limits. Experiments validate the exact dual identities to floating-point error, illustrate the predicted path and rate diagram, and show an empirical fixed-epsilon crossover scaling in cumulative time. We further report robustness and boundary diagnostics for logistic tails, fixed-epsilon crossover, and adaptive-method variants, delineating the scope of the proved smoothed-sign theory.

AI 总结：研究针对深度学习泛化难题，基于SAM提出EISAM优化器，通过两步更新过程提升泛化性能，对扰动半径敏感度降低。实验表明其在测试准确率和训练效率上优于多种优化器，理论分析证实其收紧泛化边界，还提供实用调优指导。

链接：https://arxiv.org/abs/2607.06151

作者：Yao Fu, Chunxia Zhang, Junmin Liu, Yihang Jin, Haishan Ye, Yuanao Yang

英文摘要：Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data. Building on Sharpness-Aware Minimization (SAM), for seeking flat minima associated with improved generalization, we propose the Extragradient-Inspired Sharpness-Aware Minimization (EISAM), a novel optimizer that enhances generalization via the extragradient technique. EISAM uses a two-step update process: a prediction step investigating the geometry of the loss landscape and a perturbation step that refines updates with a base optimizer. This approach achieves better generalization performance than SAM. Crucially, EISAM reduces sensitivity to the perturbation radius, enhancing robustness, and simplifying the tuning across diverse settings. Extensive experiments on benchmark datasets demonstrate that EISAM consistently outperforms SGD, Adaptive Moment Estimation (Adam), and SAM in test accuracy and training efficiency across various architectures. Theoretical analysis further confirms that EISAM tightens the generalization bound by steering parameters toward flatter minima with reduced curvature. Accompanied by a thorough hyperparameter analysis, EISAM offers practical tuning guidance, establishing it as a robust, scalable, and broadly applicable optimization solution that advances both the theory and practice in deep learning.

AI 总结：研究随机神经网络无限宽度高斯过程极限，通过张量程序视角给出定量收敛理论，有明确有限宽度误差界，框架与架构无关，涵盖多种模型及权重共享方案。

链接：https://arxiv.org/abs/2607.06290

机构：Institute for Mathematical Statistics and Actuarial Sciences, University of Bern（伯尔尼大学数理统计与精算科学研究所）； Department of Mathematics, University of Pisa（比萨大学数学系）

作者：Andrea Agazzi, Eloy Mosig García, Dario Trevisan

英文摘要：We study the infinite-width Gaussian-process limit of random neural networks through the lens of tensor programs, and we provide a quantitative convergence theory in Wasserstein distance. Our main result gives explicit finite-width error bounds, of order inverse square-root of the widths between finite-network executions and their Gaussian-process limits. The framework is architecture-agnostic and covers feed-forward models together with weight-sharing schemes relevant for recurrent and transformer-type architectures.

AI 总结：研究针对深度神经网络隐藏状态冗余问题，提出基于可控性-可观性的框架，通过构建相关矩阵进行A/B/C测试估计秩，用于诊断冗余及确定压缩层宽度，实验表明该方法能在精度损失小的情况下实现有效压缩。

链接：https://arxiv.org/abs/2607.05457

作者：Anis Hamadouche, Amir Hussain

英文摘要：Deep neural networks often contain substantial hidden-state redundancy, but most compression methods operate directly on weights, neurons, or quantised representations without explicitly characterising the dynamical role of internal states. This paper proposes a controllability-observability framework for empirical state-order reduction of deep neural networks. By viewing a trained network as a depth-indexed nonlinear dynamical system, we construct data-driven reachability, observability, and balanced Gramians from hidden-state snapshots and output Jacobians. The resulting A/B/C tests estimate layer-wise reachable, observable, and jointly reachable--observable ranks. These ranks are then used not only as diagnostic measures of hidden-state redundancy, but also as actual compressed layer widths for realised reduced networks. Experiments on MNIST and CIFAR-10 compare the proposed balanced realisation against projection-based reduction, unstructured pruning, structured pruning, low-rank SVD, dynamic INT8 quantisation, and linear baselines. On MNIST, a four-layer SiLU DNN is reduced from state order 1024 to 277, giving 72.95% state compression and 73.48% parameter compression, while maintaining 95.45% accuracy compared with 96.60% for the full model. On CIFAR-10, a larger SiLU DNN is reduced from state order 4608 to 1339, giving 70.94% state compression and 83.09% parameter compression, while preserving accuracy from 54.45% to 54.44% and reducing CUDA inference latency by approximately 3X. The results show that balanced reachable-observable ranks provide a principled empirical minimal-realisation criterion for designing compact neural architectures with little or no loss in accuracy.

AI 总结：针对大型扩散模型训练后优化的挑战，提出FourTune框架，基于端到端W4A4G4范式，引入三分支混合管道、硬件高效量化等，在多任务中质量与全精度微调相当，在特定数据集上降低内存开销、提高训练吞吐量。

链接：https://arxiv.org/abs/2607.05711

作者：Bowen Xue, Zihan Min, Xingyang Li, Zhekai Zhang, Haocheng Xi, Lvmin Zhang, Maneesh Agrawala, Jun-Yan Zhu, Song Han, Yujun Lin, Muyang Li

英文摘要：Diffusion models have become a dominant paradigm for high-quality generative modeling, while post-training is essential for adapting them to diverse downstream applications. However, post-training of large diffusion models is still challenging due to the prohibitive memory footprints and slow training speed, which existing parameter-efficient fine-tuning methods only partially address. To overcome these limitations, we propose FourTune, an efficient post-training framework for diffusion models based on an end-to-end W4A4G4 paradigm. FourTune introduces a triple-branch hybrid pipeline that augments the standard LoRA architecture with a frozen numerical stabilizer to isolate quantization-sensitive outliers, enabling stable training under native 4-bit computation. In addition, FourTune employs hardware-efficient block-wise quantization and customized fused kernels to support efficient quantized backpropagation and reduce memory bandwidth overhead. Across customization, reinforcement learning, and distillation tasks, FourTune matches the quality of full-precision fine-tuning. On FLUX.1-dev (12B), FourTune reduces memory overhead by 2.25$\times$ and increases end-to-end training throughput by 2.27$\times$ compared to BF16 LoRA.

AI 总结：研究键值缓存增长瓶颈，介绍KVpop通过直接监督保留或丢弃决策学习固定预算键值逐出策略，有新计分器及延迟内存计分器，在数学推理任务中压缩缓存时性能优于基线。

链接：https://arxiv.org/abs/2607.05061

机构：NXAI； Johannes Kepler University Linz（约瑟夫·施密特大学林茨）

作者：Lukas Hauzenberger, Niklas Schmidinger, Anamaria-Roberta Hartl, David Stap, Thomas Schmied, Sebastian Böck, Günter Klambauer, Sepp Hochreiter

英文摘要：Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV eviction methods often rely on static heuristics or proxy scores, which poorly track future token utility and cause brittle eviction as relevance shifts. To address this, we introduce KVpop, which learns a fixed-budget KV eviction policy by directly supervising the keep-or-drop decision. The scorer is trained against a novel future-attention target, computed efficiently without materializing dense attention maps. We further introduce a delayed memory-based scorer that, uniquely among learned eviction methods, defers scoring for a fixed number of steps to exploit near-future context. On AIME and HMMT mathematical reasoning, KVpop retains 98% of full-attention performance on Qwen3-4B at 75% KV cache compression and 97% at 88% compression, consistently outperforming established eviction baselines. Qwen3-8B shows even stronger results, reaching near-full teacher performance. These results show that supervising eviction with future-attention signals cuts memory costs while maintaining quality.

AI 总结：研究针对美国大陆日温度降尺度的时间分布变化问题，提出时间域自适应降尺度框架，结合历史数据监督HR重建与域对齐，实验表明该模型优于其他方法，能提升HR气候预测稳健性，尤其在特定区域和条件下效果显著。

链接：https://arxiv.org/abs/2607.05645

机构： Northeastern University（东北大学）； Microsoft（微软公司）； The Institute for Experiential AI, Northeastern University（东北大学体验式人工智能研究所）

作者：Shuochen Wang, Nishant Yadav, Auroop R. Ganguly

英文摘要：Deep-learning-based climate downscaling aims to learn relationships from historical low-resolution (LR) and high-resolution (HR) climate data to generate HR climate projections. However, this setting faces a temporal out-of-distribution (OOD) challenge: models trained on historical data are commonly applied to future projections whose distributions may differ substantially from the training period. This study investigates temporal OOD shift for daily temperature downscaling over the Continental United States using paired LR-HR model simulations. We propose a temporal domain-adaptive downscaling framework that combines supervised HR reconstruction on historical data with domain alignment between historical and future climate distributions. Experiments across future validation periods show that the proposed domain-adaptive model consistently outperforms statistical and deep-learning-based bias-correction methods, with the largest gains occurring when the temporal distribution shift is strongest. Spatial analyses indicate stronger improvements over high-elevation and topographically complex regions, along with higher spatiotemporal correlation with the HR target. The extreme analysis shows that domain adaptation also reduces upper-tail temperature bias relative to the non-adaptive model. These results demonstrate that temporal domain adaptation can improve the robustness of HR climate projections under non-stationary climate conditions.

AI 总结：研究如何对抗神经后门，提出HARVEY方法，通过学习有毒样本的预言机来去除后门。该方法在识别有毒样本上更准确，能近乎完美地去除后门，在多方面优于相关方法，降低攻击成功率且自然准确率损失小。

链接：https://arxiv.org/abs/2607.05748

作者：Qi Zhao, Christian Wressnegger

英文摘要：The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples. In particular, the latter has proven effective for anti-backdoor learning. Our method, HARVEY, leverages a similar yet crucially different technique: learning an oracle for poisonous rather than benign samples. Learning a backdoored reference model is significantly easier than learning a reference model on benign data. Consequently, we can identify poisonous samples much more accurately than related work identifies benign samples. This crucial difference enables near-perfect backdoor removal as we demonstrate in our evaluation. HARVEY substantially outperforms related approaches across attack types, datasets, and architectures, lowering the attack success rate to the very minimum at a negligible loss in natural accuracy. The figure below shows an overview of our methods working principle.

AI 总结：研究机器学习训练数据选择问题，提出基于赫克曼双方程模型的方法用于深度认知不确定性，通过实验表明该方法能校正不可观测因素选择，在真实数据上表现良好，恢复覆盖率，还能精确输出结果并说明识别机制，同时开源代码。

链接：https://arxiv.org/abs/2607.05806

作者：Gunner Levi Howe

英文摘要：Training data for machine learning is routinely collected by a selection process the model never sees: loans are observed only when granted, outcomes only when a test was ordered. The standard fixes -- importance weighting, covariate-shift correction, MAR imputation -- assume selection is ignorable given observables. Econometrics solved the harder case in 1979: Heckman's two-equation model jointly fits a probit selection equation and an outcome equation linked through correlated errors, and the inverse-Mills-ratio term corrects for selection on unobservables, where importance weighting is structurally helpless. We instantiate this for deep epistemic uncertainty: a deep outcome network, a linear selection head, and a joint bivariate-normal likelihood over all units, ensembled for predictive variance. In a controlled generator where sampling probability depends on an unobservable correlated (rho up to 0.9) with the outcome noise, deep ensembles, MC dropout, and GP baselines are overconfident exactly where data was avoided: coverage of nominal-90% intervals falls to 64.4% at rho=0.9, and importance weighting with oracle propensities does not fix it (43.1%) -- reweighting corrects the covariate distribution, not the conditional bias E[y|x,selected] != E[y|x]. The Heckman correction restores coverage (88.9%) when the selection equation has an instrument -- a variable affecting selection but not the outcome -- and degrades measurably without one (40.3%); we chart this honesty curve rather than hide it. On real tabular data with induced MNAR selection, the corrected intervals are the best-calibrated (lowest region-ECE) non-oracle method in selected-against regions; baselines matching its raw coverage do so only by over-widening everywhere. Our estimators reproduce classic Stata output to seven digits. We state which identification regime a practitioner is in, and release the code.

AI 总结：研究针对社交媒体网络信息操作检测难题，提出无监督方法TENSOR，利用多模态数据，通过训练时间点过程捕捉异常行为模式，并引入新证据函数调整输出，在五个真实数据集上表现优于基线。

链接：https://arxiv.org/abs/2607.05855

机构：RMIT University（皇家墨尔本理工大学）； Macquarie University（麦考瑞大学）

作者：Sishun Liu, Sajal Halder, Ke Deng, Yan Wang, Xiuzhen Zhang

英文摘要： Information Operations on social media networks have been identified as a significant threat to democracy and modern society, but they are challenging and expensive to detect by humans. Existing supervised IO detection methods fail to capture the dynamic nature of evolving IO user behavior, while existing unsupervised approaches rely on oversimplified assumptions of coordination among IO users that may not exist in practice. To overcome the limitations of existing methods, we formulate IO user detection as an anomaly detection problem and propose a novel unsupervised IO user detection approach called Temporal-bEhavior-laNguage Signals for information Operation Recognition (TENSOR), which leverages multimodal data, including temporal online user behavior, such as message posting activities, and the textual content of the messages. The motivation is that IO users are typically a very small fraction of all online users and have unique temporal behavioral and language patterns. Specifically, we train a Temporal Point Process (TPP) to capture abnormal temporal behavioral patterns of IO users because they are known to behave in a coordinated manner for IO campaigns. We further introduce a novel evidence function that converts LLM responses, which are generated from user post timelines, into quantitative scores to adjust the TPP outputs for better IO user detection. Experimental results show that TENSOR outperforms the baselines on five real-world IO datasets. Code is available at this https URL.

AI 总结：研究无学习算法能否消除训练数据影响这一问题，利用成员推理攻击计算无学习参数ε下限的审计器来评估多种算法，发现有严格保证的算法ε边界小，经验方法边界大，审计器为证伪无学习声明提供工具并经实验验证。

链接：https://arxiv.org/abs/2607.05898

机构：Stanford University（斯坦福大学）； University of Zurich（苏黎世大学）

作者：Sahasrajit Sarmasarkar, Anastasia Koloskova, Sanmi Koyejo

英文摘要：Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge. We propose a practical auditor that computes data-dependent lower bounds on the unlearning parameter $\varepsilon$ using membership inference attacks. Evaluating multiple unlearning algorithms, we find a sharp separation: algorithms with rigorous guarantees, such as model clipping and rewind-to-delete, achieve very small $\varepsilon$ bounds that do not falsify their unlearning guarantees, whereas empirical methods such as Hessian-based unlearning, interleaved ascent-descent, ascent on the forget set, and fine-tuning on the retain set exhibit large bounds, indicating poor unlearning. Our auditor provides a practical tool for empirically falsifying unlearning claims through a hypothesis-testing framework, and we validate it on CIFAR-100 and Shakespeare text.

AI 总结：研究训练语言模型依据自身无参考评判时的奖励破解问题，发现评判器评分合理性而非正确性致误报。通过隐藏锚点审计衡量，以GSM8K为例展示问题。提出决定性变量及对应解决办法，还有可证伪界限，且过程可复制。

链接：https://arxiv.org/abs/2607.05904

机构：School of Engineering, Institute of Science Tokyo（东京科学大学工程学院）

作者：Chenyu Zhou

英文摘要：Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness. We show it fails structurally: conditioned on a candidate, a judge scores plausibility, not correctness, leaving false-positive basins a policy learns to exploit. We measure this with a hidden-anchor audit: a held-out, cross-source exact-match check the judge never sees. On GSM8K with Qwen3 policies, self-play drives the judge's pass rate from 0.72 to 0.94 while true accuracy stays at 0.20 (three seeds). This reward hacking is not white-box gaming: the errors transfer across judge families (Qwen, Llama, Gemma) and scales, a strict three-judge ensemble still accepts 55% of them, and no plausibility-scoring defense closes the basin. The decisive variable is whether the judge commits an answer of its own before using the candidate: committing first drops the false-positive rate from 0.719 to 0.012, blind solving lifts discrimination to 0.96, and used as the training reward the de-anchored channel keeps false positives at zero, preventing the basin rather than only detecting it. A falsifiable bound (the gap is at most 1 - accuracy) predicts which regimes are exposed. The full arc replicates without training under best-of-N selection in code and competition math, and with a Gemma policy.

AI 总结：研究现实世界数据分布随时间演变带来的时间分布变化对机器学习系统可靠性的影响，通过统一评估框架比较不同模型家族的时间鲁棒性，发现架构归纳偏差塑造时间鲁棒性，为现实系统选架构提供指导。

链接：https://arxiv.org/abs/2607.05908

机构：Department of Electrical Engineering and Computer Sciences, University of California, Berkeley（加州大学伯克利分校电气工程与计算机科学系）

作者：Robin Holzinger (1), Riccardo Colletti (1) ((1) Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA)

英文摘要： Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems. However, the extent to which architectural choices and their associated inductive biases affect temporal robustness remains insufficiently understood. We present a systematic empirical comparison of temporal robustness across three heterogeneous, time-indexed domains encompassing image classification, multi-label text classification, and text regression tasks. Using a unified evaluation framework based on temporal drift matrices, we train models on cumulative historical data and evaluate their performance on both earlier and later time periods, thereby quantifying cross-temporal generalization. Our study spans model families ranging from simple multilayer perceptrons and convolutional networks to recurrent networks and pretrained Transformer-based encoders. Collectively, the results show that architectural inductive biases systematically shape temporal robustness: models whose inductive biases lead them to exploit localized, highly discriminative features attain the highest in-distribution accuracy, yet those features are often the ones that change most over time, so these models degrade fastest, while pretrained encoders that draw on coarser, more stable representations drift more gradually. These observations offer practical guidance for selecting architectures for real-world systems subject to temporal drift.

AI 总结：研究多模态网络物理系统异常检测，提出联合潜在聚类方法，通过MIIM假设集、公平协议及潜在评分建模正常行为，在三个真实数据集上表现优异，优于其他深度检测器。

链接：https://arxiv.org/abs/2607.06094

作者：Alexander Apartsin, Yehudit Aperstein

英文摘要：Faults on a cyber-physical system (CPS) are too rare and unrepresentative to characterise, or even to select a model on, so detection must instead model normal behaviour; the standard point-adjusted evaluation, however, rewards detectors that never do. CPS normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes rather than a single blob; we state this structure as ten assumptions (A1-A10), abbreviated Massive, Implicit, Imbalanced Multimodality (MIIM). We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering, scored in the latent rather than by a global density or a reconstruction residual, and evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration. On three real CPS datasets (WADI, HAI, SKAB), the detector wins both the combined column and the difficult correlation/dynamics-fault column on all three, reaching difficult-subset AUROC 0.831 on HAI, 0.726 on WADI, and 0.610 on SKAB. The margin is largest on the two multimodal datasets the MIIM assumptions target and slimmest on the near-unimodal one, tracking multimodality as the thesis predicts, and it holds against three deep detectors (USAD, TranAD, GDN) re-computed with the same raw metrics, all of which collapse on the difficult subset. The methodological contributions are the MIIM assumption set, the difficulty-stratified fair protocol, and a latent-only score that drops reconstruction because a flexible decoder rebuilds the hard faults faithfully.

AI 总结：针对无监督图聚类中现有方法的“结构隔离”问题，提出SCISE框架，通过社区感知采样、结构熵社区约束算子及结构对比学习模块协同保持结构完整性，实验证明该框架显著优于现有算法。

链接：https://arxiv.org/abs/2607.05469

机构：Beihang University（北京航空航天大学）； University of Illinois at Chicago（伊利诺伊大学芝加哥分校）

作者：Jingyun Zhang, Hao Peng, Jianxin Li, Angsheng Li, Philip S. Yu

英文摘要：Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrastive Learning has demonstrated promising performance, existing methods often suffer from the "structural isolation" issue during mini-batch training, making it challenging to capture cohesive community structures that characterize the global topological distribution. To address these challenges, we propose SCISE, a Scalable unsupervised graph Clustering framework that preserves structural Integrity by synergizing community-aware sampling with constrained Structural Entropy. Specifically, we first introduce the Structural Entropy Community Constraint operator (SECC), which optimizes structural information within a constrained solution space to mitigate community fragmentation and enhance partition cohesion. Second, to prevent global information loss during batch training, we design a Community-Aware Sampling Expansion (CSampE) mechanism that incorporates the community context of target nodes into sampling batches, effectively breaking structural barriers and preserving topological integrity. Finally, we devise a Structural Contrastive Learning (StructCL) module that refines edge weights based on intra-batch structural similarity, guiding the encoder to learn representations in a higher-order structural space. Extensive experiments on six mainstream benchmark datasets demonstrate that SCISE significantly outperforms state-of-the-art algorithms, with ablation studies and robustness analyses further validating its effectiveness and reliability for real-world large-scale graphs.

AI 总结：代谢工程中设计高产微生物菌株有挑战，Canopy异构图基础模型集成多数据源成知识图谱，用特定模型编码特征，经自监督目标预训练，在发酵滴度预测任务中表现优于基线。

链接：https://arxiv.org/abs/2607.06224

机构：an in-house laboratory information management system (LIMS)（一个内部实验室信息管理系统（LIMS））

作者：Jake Bowden, Laurence Legon, Satnam Surae

英文摘要：Designing microbial strains that produce high-value chemicals at commercially viable titers remains a central challenge in metabolic engineering. Existing computational approaches either rely on stoichiometric constraint-based models that cannot learn from experimental data, or apply tabular machine learning to hand-crafted features that discard the relational structure of biological knowledge. We present Canopy, a heterogeneous graph foundation model that integrates ten public and proprietary data sources into a unified knowledge graph (KG) of 6.9M nodes across 13 types and 34 edge types, covering genes, proteins, metabolites, reactions, pathways, strains, and fermentation experiments. Node features are encoded through domain-specific foundation models (ESM-2 for protein sequences, MoLFormer for chemical SMILES, and PubMedBERT for biomedical text), yielding a multi-modal representation within a single graph. We pretrain a Heterogeneous Graph Transformer (HGT) augmented with SignNet positional encodings, Jumping Knowledge aggregation, and virtual nodes using four self-supervised objectives (link prediction, masked node modelling, distance prediction, and contrastive experiment clustering), balanced via learned homoscedastic uncertainty weighting. On the downstream task of fermentation titer prediction, frozen Canopy embeddings achieve $R^{2} = 0.41$ with a lightweight probe, outperforming tabular baselines (best $R^{2} = 0.24$) and homogeneous GNN variants.

AI 总结：研究在模型来自特定管道时MILP实例难获取的问题，提出图原生生成器GraphBU，其基本单元是局部子问题及其接口，通过促进节点耦合等操作生成实例，能保持图统计、可行性并提升下游训练效果。

链接：https://arxiv.org/abs/2607.06532

作者：Xiaolei Guo, Chenyu Zhou, Jianghao Lin, Dongdong Ge

英文摘要：Mixed-integer linear programming (MILP) instances used for solver development are hard to obtain when models come from private or application-specific pipelines. A generator must keep the structure that solvers and learned policies rely on. Existing general generators usually choose their generation unit from a formulation template, summary statistics, local graph edits, or blocks found after recombination. These units do not explicitly record how a local part of the MILP is coupled to the rest of the instance. We propose GraphBU, a graph-native generator whose basic unit is a local subproblem plus its interface. The method promotes coupling nodes into master constraints or boundary variables and uses the resulting block units for compatibility-checked replacement. The analysis focuses on the properties needed by this construction: promotion separates interfaces, replacement can preserve feasibility under an interface-slack condition, and the graph construction is invariant to row-column permutations. On MILP instances generation, this unit keeps graph statistics close to the source family, preserves feasibility on most datasets, and improves downstream Predict-and-Search training. Genrated by GraphBU, The average graph-statistical similarity was approximately 0.934, the average feasibility was approximately 96.7%, and the average increase in the main index of downstream PS was approximately 8.0%.

AI 总结：研究图去噪问题，提出图卷积注意力（GCA）方法，通过利用输入图谱实现谱去噪，在随机块模型中与理想机制匹配，实验证明其能提升图去噪和扩散性能，在 DiGress 中表现良好且推理更快。

链接：https://arxiv.org/abs/2607.06546

机构：University of Pennsylvania（宾夕法尼亚大学）； King Juan Carlos University（胡安·卡洛斯国王大学）； Stanford University（斯坦福大学）

作者：Shervin Khalafi, Igor Krawczuk, Sergio Rozada, Charilaos Kanatsoulis, Antonio G Marques, Alejandro Ribeiro

英文摘要：Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures like graph transformers have recently shown promise in denoising graphs. However, our principled understanding of attention-based graph denoising remains limited, making it unclear whether standard attention is the right mechanism for this task. Here we show that, under a denoising objective, linear attention is suboptimal and can only learn an average spectral denoising filter over the training distribution. This creates a fundamental limitation as graphs often vary spectrally across the distribution. To overcome this limitation, we introduce Spectral Attention, which directly utilizes the input graph spectrum and provably outperforms linear attention by a margin governed by the spectral diversity of the distribution. We then derive Graph Convolutional Attention (GCA), a practical and permutation-equivariant realization of this idea that implements spectral denoising through graph-filtered queries and keys. For stochastic block models, GCA provably matches the idealized Spectral Attention mechanism. We further show that the softmax operation, that follows the attention, provides additional denoising by approximately projecting noisy eigenvectors onto the clean eigenspace. Empirically, replacing linear attention with GCA consistently improves graph denoising and diffusion on synthetic and real datasets, with gains strongly correlated with spectral diversity. In DiGress, GCA matches standard graph-transformer performance without computing expensive structural features, and when combined with the recently proposed PEARL positional encodings, avoids explicit eigendecomposition computations resulting in faster inference without degrading quality. The code can be found here: this http URL

AI 总结：研究利用同家族强源模型改进弱目标模型，提出源引导候选生成协议，在CIFAR - 10和SVHN AlexNet等数据集上实验，结果表明该协议能显著提高准确性，且大语言模型是适应性改进而非复制，家族级分析有积极信号。

链接：https://arxiv.org/abs/2607.05704

机构：University of Würzburg（维尔茨堡大学）； Computer Vision Lab, CAIDAS（计算机视觉实验室，CAIDAS）

作者：Kabir Dev Paul Baghel, Radu Timofte, Dmitry Ignatov

英文摘要：Large language models (LLMs) can generate neural-network modifications, but unrestricted generation is often invalid or harmful. This paper studies a narrower setting: improving a weak target model using a stronger same-family source model from a neural-network database. We propose a source-guided candidate-generation protocol with non-source controls, source-conditioned candidates, and a no-LLM hp_copy ablation under equal evaluation budgets. The protocol reports validity separately from accuracy and selects the best valid candidate only when it improves the target. On CIFAR-10, the strongest source-guided candidate reaches 0.5049 accuracy versus 0.2398 for the best non-source candidate, a +0.2651 advantage, while improving a weak target originally at 0.1254; a five-epoch check preserves the gain at 0.7686 versus 0.4839. On SVHN AlexNet with DeepSeek-Coder-6.7B, source-guided transfer reaches 0.7880 versus 0.2254, a +0.5626 advantage; a fresh repeat reaches 0.8069 versus 0.2509, a +0.5560 advantage. Direct source-recipe copy produces 0.1959 on SVHN AlexNet, matching the original target, while hp_transfer reaches 0.7880, showing that the LLM adapts rather than copies the source recipe. Family-level analysis shows the clearest positive signals for AlexNet, with 6/8 wins across SVHN, Imagenette, and CelebA-Gender, and alt_nn1, with 8/10 wins on CIFAR-10.

AI 总结：研究时间序列预测中的粒度悖论，通过13年公共采购数据集在六种粒度上对10种模型基准测试，揭示非单调阈值结构，表明标准逐点度量会掩盖累积误差传播，引入新诊断方法识别掩盖系统误差传播的模型。

链接：https://arxiv.org/abs/2607.05450

机构：Iscte - Instituto Universitário de Lisboa（里斯本大学学院）； CIES - Centro de Investigação e Estudos de Sociologia（社会科学研究中心）

作者：Hugo Moreira

英文摘要：This paper explores the "Granularity Paradox" in time-series forecasting, wherein finer temporal disaggregation (e.g., Monthly to Weekly/Daily) improves in-sample diagnostics and dataset size (N), but degrades out-of-sample accuracy due to recursive error compounding over longer horizons (H). Conversely, coarse aggregation (Annual) eliminates recursive error propagation but reduces data available to estimators. We formalize this trade-off and benchmark 10 models - spanning naïve, statistical, machine learning, and deep learning architectures - across six granularities using a 13-year public procurement dataset. The empirical results reveal a non-monotonic threshold structure: recursive autoregressive and seasonal models degrade substantially under high-frequency forecasting (e.g., Holt-Winters reaches a Test R-squared of -151 and TPFE of 425.85% at the Daily grain), while the LSTM traces a U-shaped error curve, worsening from Monthly (19.66%) through Bi-Weekly (35.94%) before overcoming the error propagation penalty at Daily (TPFE of 4.35%, R-squared of 0.66). Linear Regression remains stable across all granularities (16.3-17.0% TPFE), confirming that the paradox is driven by recursive feedback topology, not model complexity. The results demonstrate that standard pointwise metrics (RMSE, MAE) systematically mask cumulative error propagation, and that evaluating forecasts without goal-dependent cumulative metrics produces misleading assessments of model adequacy. We introduce a consensus-dissensus diagnostic comparing the directional behaviour of pointwise metrics against cumulative TPFE across granularities, enabling the identification of models whose standard diagnostics mask systematic error propagation.

AI 总结：研究针对户外超宽带传感测距受多种因素影响的问题，提出GAIA几何感知基础设施锚定学习框架，结合多种技术进行范围去噪，在真实数据集和模拟器上评估，相比PoseMLP降低均方误差、提高多边形交并比，为工作区重建提供有效路径。

链接：https://arxiv.org/abs/2607.05449

机构：Department of Civil and Architectural Engineering and Construction Management, University of Wyoming（怀俄明大学土木、建筑工程与施工管理系）； School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆邮电大学计算机科学与技术学院）

作者：Weizhe Tang, Jiaxi Liu, Junwei you, Steven T.Parker, Pei Li, Sikai Chen, Meng Ran, Bin Ran

英文摘要：Accurate work-zone geometry perception is critical for intelligent transportation systems, and ultra-wideband sensing offers a low-cost approach for infrastructure-aided reconstruction. However, outdoor UWB ranging is often degraded by non-line-of-sight propagation, burst noise, and long-tail errors, which can distort downstream spatial reconstruction. We present GAIA, a geometry-aware, infrastructure-anchored learning framework that couples temporal range modeling with latent anchor-layout estimation and deterministic distance projection. GAIA preserves range denoising as the supervised task while orienting the learned distances toward boundary-consistent reconstruction. We evaluate GAIA on a real-world outdoor UWB dataset with synchronized UWB, GNSS, and IMU measurements, and further test robustness using a real-data-calibrated stress-test simulator. GAIA achieves the lowest overall range MSE and highest polygon IoU among evaluated filtering-based and learning-based baselines, reducing MSE by 18.4% and improving polygon IoU by 15.5% over PoseMLP. These results show that geometry-aware range denoising provides an effective path toward spatially coherent work-zone reconstruction.

AI 总结：研究针对基础机器学习力场不能处理外部诱导电子态变化的问题，提出EquiFiLM方法，通过特征线性调制为等变基础MLFF添加外部条件，以少量训练数据学习势能面变化，在带电液态水实验中大幅提升精度，且与骨干和条件无关。

链接：https://arxiv.org/abs/2607.05559

机构：Stanford University（斯坦福大学）； SLAC National Accelerator Laboratory（SLAC国家加速器实验室）； University of Southern California（南加州大学）

作者：Samuel Sahel-Schackis, Ken-ichi Nomura, Aiichiro Nakano, Matthias F. Kling, Thomas Linker

英文摘要： Foundation machine learning force fields (MLFFs) such as MACE-MP-0 and UMA cover broad chemical space at near density functional theory (DFT) accuracy. However, they assume equilibrium ground-state physics and do not natively handle externally induced changes to the electronic state, such as charging, applied fields, or electronic excitation, which limits their use for driven processes such as photoexcitation and charge injection. We propose EquiFiLM, a lightweight extension that adds continuous external conditioning to any equivariant foundation MLFF via a per-layer Feature-wise Linear Modulation (FiLM) block, learning externally driven changes to the potential energy surface from minimal training data. The block modulates only scalar channels and preserves E(3)-equivariance exactly. We demonstrate the recipe on charged liquid water with the foundation model MACE-MatPES as the backbone, yielding E-MACE. On the four training charges, E-MACE delivers a $3.1\times$ reduction in force RMSE ($21.3$ to $6.96$ meV/$\mathring{A}$) and a $61\times$ reduction in per-atom energy RMSE ($6.1$ to $0.1$ meV/atom) over a baseline without EquiFiLM trained on the same data, at indistinguishable inference cost. Across seven held-out interpolation and extrapolation charges, force RMSE stays within $18-61$ meV/$\mathring{A}$ and energy RMSE within $0.7-5.4$ meV/atom. The model runs stable molecular dynamics across the full range tested and predicts the charge-dependent first-shell response of the reduced pair distribution function probed by ultrafast electron diffraction. Adding this conditioning axis to the foundation requires only a few thousand DFT-labeled frames, against the $\approx 10^8$ structures of a charge-aware foundation trained from scratch. The recipe is backbone- and conditioning-agnostic: it applies without architectural change to any equivariant MLFF with scalar interaction-layer channels.

AI 总结：研究临床数据插补问题，提出SafeImpute框架，通过构建事件图、利用双关系GNN和自适应融合学习插补，并结合共形选择控制不可接受误差，实验证明该方法在插补准确性和可靠误差控制上优于基线。

链接：https://arxiv.org/abs/2607.05613

机构：University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Mayo Clinic（梅奥诊所）

作者：Xinrui He, Mengting Ai, Junting Wang, Curtiss B. Cook, Jingrui He

英文摘要：Clinical care often relies on key laboratory indicators, yet real-world patient visits are sparse and tests are ordered irregularly, leading to pervasive missingness. While many imputation methods improve average accuracy, they provide limited guidance on which imputed values are reliable enough for high-stakes downstream use. In this work, we study reliable clinical imputation, aiming to produce accurate imputations while selectively releasing the reliable results, with statistical control over clinically unacceptable errors. To achieve this goal, we propose SafeImpute, a reliable imputation framework for irregular and sparse clinical longitudinal records. SafeImpute constructs an event graph that captures both intra-patient temporal trajectories and inter-patient clinical similarity, and learns imputations with a two-relation GNN and adaptive fusion, regularized by an auxiliary masked reconstruction objective. For reliability guarantees, SafeImpute converts a proxy risk score into conformal p-values and applies the Benjamini--Hochberg procedure to control the false discovery rate (FDR) of unacceptable errors among released imputations at a user-specified tolerance. Experiments on our Mayo Clinic data, the public MIMIC-III and MIMIC-IV datasets show that SafeImpute achieves strong imputation accuracy while providing reliable error control, outperforming diverse baselines in both standard imputation evaluation and FDR-controlled selective-release evaluation.

AI 总结：针对电子健康记录基础模型是黑箱模型的问题，提出基于Transformer的令牌级可解释性方法，训练替代模型近似其行为，识别有影响力令牌，引入临床对齐度量，结果显示该方法能实现可解释且可信的临床人工智能。

链接：https://arxiv.org/abs/2607.06163

机构：School of Computing and Information Systems, University of Melbourne（墨尔本大学计算与信息系统学院）； Royal Melbourne Hospital（皇家墨尔本医院）

作者：Jie Huang, Pengfei Yin, Zihan Xu, Daniel Capurro, Mike Conway, Ting Dang

英文摘要：Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal patient trajectories into generalizable representations for diverse clinical prediction tasks. Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. We train a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while preserving temporal dynamics. We identify the most influential tokens, providing insights into how FEMRs leverage different aspects of patient history for predictions. To evaluate clinical relevance, we introduce a novel clinical alignment metric that quantifies the correspondence between the surrogate model's key tokens and clinically validated features. Our results demonstrate that the surrogate closely approximates FEMR predictions and that token-level explanations align well with clinical knowledge, offering a practical framework for interpretable and trustworthy clinical AI.

AI 总结：研究超参数化机器学习系统是否展现真正智能的问题，引入统计有意义的几何框架，通过建模为Orlicz纤维束，证明在特定刺激下会出现规范对称性破缺，可区分真正发现与幻觉，为认证智能提供无参数、可证伪方法，推动人工智能用于科学的范式转变。

链接：https://arxiv.org/abs/2607.05436

机构：Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）； AMSS Center for Forecasting Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院预测科学研究中心）； Beijing Institute of Mathematical Sciences and Applications (BIMSA)（北京国际数学研究中心）； Department of Statistics, London School of Economics and Political Science（伦敦政治经济学院统计系）； Department of Statistics and Data Science, Tsinghua University（清华大学统计与数据科学系）； Paula and Gregory Chow Institute for the Studies in Economics, Xiamen University（厦门大学经济研究所）； Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）

作者：Bing Cheng, Yi-Shuai Niu, Howell Tong, Shing-Tung Yau

英文摘要：The rapid scaling of over-parameterized machine learning architectures, particularly LLMs, raises a profound crisis: do these systems exhibit genuine intelligence, or are they merely sophisticated statistical pattern matchers? Classical flat Euclidean statistics cannot differentiate continuous interpolation from the autonomous discovery of novel causal laws. To resolve this, we introduce Statistically Meaningful Geometry (SMG), a framework modeling over-parameterized learning systems as infinite-dimensional non-parametric Orlicz fiber bundles. We prove that under persistent out-of-distribution (OOD) stimuli governed by unmodeled causal mechanisms, continuous optimization fails. Unmodeled variance is rejected by the visible horizontal base manifold, leaking into the unobservable vertical fiber space and generating an accumulation of Active Acausal Tension. Driven by the statistical manifold's non-linear curvature, this tension inevitably strikes a conjugate focal boundary ($T_{\text{crit}} = \pi^2 / K_{\text{max}}$), triggering localized volumetric collapse and a catastrophic matrix singularity ($[G_f]^{-1} \to \infty$). We demonstrate this geometric breakdown acts as the strict non-equilibrium trigger for a Gauge Symmetry Break (GSB). The system purges hidden tension from unobservable gauge redundancies, spontaneously crystallizing a new, mathematically independent horizontal coordinate axis. This non-parametric phase transition registers as a discrete $+1.0$ integer step-jump in observable Structural G-Entropy. By decoupling parameter charts and subjecting emergent axes to a Minimal Energy Path Criterion and a Causal Invariance Filter, we distinguish genuine discovery from malignant hallucinations. Ultimately, SMG provides a parameter-free, falsifiable dashboard to mathematically certify true intelligence, transforming AI for Science into an engine of autonomous paradigm shifts.

AI 总结：研究用于分类数据聚类的距离度量，提出统一测量标称和有序属性内距离的新方法及新聚类算法，将属性内距离权重学习和数据划分整合为单一范式，实验验证了算法有效性。

链接：https://arxiv.org/abs/2607.05464

作者：Yiqun Zhang, Yiu-ming Cheung

英文摘要：The success of categorical data clustering generally much relies on the distance metric that measures the dissimilarity degree between two objects. However, most of the existing clustering methods treat the two categorical subtypes, i.e. nominal and ordinal attributes, in the same way when calculating the dissimilarity without considering the relative order information of the ordinal values. Moreover, there would exist interdependence among the nominal and ordinal attributes, which is worth exploring for indicating the dissimilarity. This paper will therefore study the intrinsic difference and connection of nominal and ordinal attribute values from a perspective akin to the graph. Accordingly, we propose a novel distance metric to measure the intra-attribute distances of nominal and ordinal attributes in a unified way, meanwhile preserving the order relationship among ordinal values. Subsequently, we propose a new clustering algorithm to make the learning of intra-attribute distance weights and partitions of data objects into a single learning paradigm rather than two separate steps, whereby circumventing a suboptimal solution. Experiments show the efficacy of the proposed algorithm in comparison with the existing counterparts.

AI 总结：研究如何利用关系数据库预测目标列缺失值，对比无参数和参数化编码器，分析标签输入时RDB编码器属性，通过实验验证简单无参数编码器在多基准任务中仍有强大性能。

链接：https://arxiv.org/abs/2607.05476

作者：Linjie Xu, David Wipf

英文摘要：Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As the space of potential targets is vast across enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models based on RDB-specific encoders provide a viable solution, but ideal design remains an open question. On the one hand, it has recently been argued that certain parameter-free subgraph encoders combined with single-table foundation models can achieve near SOTA performance, with no RDB-specific pre-training required. Meanwhile, other contemporary studies advocate for parameterized encoders pre-trained to exploit observable labels for learning task-specific representations. To address this ambiguity, we analyze RDB encoder properties specifically when labels are present as inputs, proving limitations on the potential efficacy of trainable encoder parameters. As empirical validation, we demonstrate that considerably simpler parameter-free encoders are still capable of strong performance across many relevant benchmarking tasks.

AI 总结：研究针对交互循环程序的不变式合成难题，提出神经符号框架InvWeaver，通过循环级抽象等方法揭示循环间依赖并传播证明义务，在综合基准套件上评估，其性能显著优于现有方法，能有效解决多循环问题并保持单循环任务优势。

链接：https://arxiv.org/abs/2607.05478

作者：Guangyuan Wu, Weining Cao, Zehui Tan, Yuan Yao, Hengfeng Wei, Taolue Chen, Xiaoxing Ma

英文摘要：Loop invariant inference is a fundamental yet challenging problem in program verification. Recent LLM-aided guess-and-check techniques have shown strong performance on single-loop programs, but they often struggle with programs containing multiple interacting loops. This paper presents InvWeaver, a neuro-symbolic framework for synthesizing invariants for such programs. The key idea is to expose inter-loop dependencies and propagate proof obligations through a combination of loop-level abstraction, obligation-guided inference, and weakest-precondition-based refinement. We evaluate InvWeaver on a comprehensive benchmark suite, including a newly curated dataset derived from classic algorithms. Experimental results show that InvWeaver substantially outperforms existing invariant inference methods, solving 72 out of 82 multi-loop benchmark problems and maintaining strong performance on single-loop tasks.

AI 总结：研究共享状态大语言模型工作流问题，提出受光学启发的PatchOptic接口，通过投影读取和验证结构化补丁实现，经PatchBench评估，该设计能减少泄漏和成本，保持输出质量，阻止违规并拒绝受损补丁。

链接：https://arxiv.org/abs/2607.05483

机构：Weizmann Institute of Science（魏茨曼科学研究所）； Massachusetts Institute of Technology（麻省理工学院）

作者：Zhaoyu Bai, Jiaqi Cai

英文摘要：Agentic workflows often operate over shared, structured state. Because LLM context windows are limited, each model invocation is typically shown only the state fragment needed for the current workflow step, a pattern commonly known as progressive disclosure. Modern systems construct such model-facing views using grep-like keyword search, retrieval-augmented generation (RAG), abstract-syntax-tree (AST) queries, and task-specific agent skills. These methods make the read side manageable, but they do not define when a locally proposed rewrite is valid after it is applied back to the full state. The missing piece is a contract between local updates and global validity. We introduce PatchOptic, an optic-inspired interface for shared-state LLM workflows. Optics are compositional bidirectional accessors that describe how views of structured data are read and updated. PatchOptic borrows this view/update intuition and realizes it through projected reads and verified structured patches. Each workflow step declares a projected read view, an authorized write region, and a patch-source region. Beyond runtime enforcement, the same declaration yields a path-level footprint that supports delegation, sub-workflow composition, and static certificates for reordering independent steps within the same phase. We evaluate this design with PatchBench, a benchmark with 46 cases across domains. The results show that projected reads reduce reported leakage and token cost while preserving accepted-output quality under the strong actor. Runtime verification blocks declared workflow-contract violations before commit, and patch-read enforcement rejects compromised patch artifacts that use hidden sources.

AI 总结：研究大语言模型控制问题，提出随机令牌控制和随机块控制方法，无需奖励模型或门控策略。实验表明，仅控制部分令牌就能恢复大部分密集控制效果且保持流畅性，揭示了SAE介导控制的速率限制特性。

链接：https://arxiv.org/abs/2607.05615

机构：The Vanguard Group, Inc.（先锋集团公司）； University of Toronto（多伦多大学）

作者：Nima Eshraghi, Lovedeep Gondara, Yuqing Huang, Sagarika Suresh, Leizer Teran, Jithin Pradeep, Xiaotong Xu, Fanny Chevalier

英文摘要：Activation steering via sparse autoencoders (SAEs) enables behavioral control of large language models without task-specific fine-tuning, but standard methods apply the steering signal at every generated token, incurring constant per-token perturbation that risks degrading fluency. We ask: is dense intervention necessary? We introduce Stochastic Token Steering (STS), which gates each token independently with probability $p$, and Stochastic Block Steering (SBS), which gates a leading window once per sequence; neither requires a reward model or learned gating policy. Across two model families and two behavioral tasks, steering only 50% of the tokens recovers most of the dense-steering effect while preserving fluency, and steering as few as 30% surpasses prompt-based control. The optimal steering magnitude scales inversely with the intervention ratio, revealing that SAE-mediated control is rate-limited: the behavioral outcome depends on cumulative signal dosage across a sequence.

AI 总结：研究在具有潜在混杂因素的线性非高斯无环模型中恢复最稀疏DAG的问题，提出一种有限样本方法，该方法不受潜在混杂因素数量限制，经模拟研究和实际数据分析验证，其有限样本性能优于现有方法。

链接：https://arxiv.org/abs/2607.05984

作者：Ming Cai, Hisayuki Hara

英文摘要：Recovering the exact directed acyclic graph (DAG) in linear non-Gaussian acyclic models with latent confounders (LvLiNGAM) remains a challenging problem. Although LvLiNGAM is identifiable only up to an observational equivalence class, each equivalence class is characterized by a unique sparsest DAG. Recovering the sparsest DAG from finite samples, however, remains difficult. Although existing methods are asymptotically consistent, they do not provide an explicit finite-sample procedure for recovering the unique sparsest DAG, nor do they handle models with an arbitrary number of latent confounders. In this paper, we propose a finite-sample method for recovering the sparsest DAG without imposing any restriction on the number of latent confounders. Simulation studies and real-data analyses demonstrate that the proposed method achieves superior finite-sample performance compared with existing approaches.