机器学习学术速递[7.16]

AI 总结：研究针对全球台站天气预报中现有方法的局限，提出三轴状态空间模型TSSM，通过时间可变历史范式纳入历史数据，设计扫描捕捉多种特性，在多数据集上性能优异，尤其在长期和迭代预测及应对缺失观测方面优势明显。

链接：https://arxiv.org/abs/2607.13101

机构：Beihang University（北京航空航天大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； The Chinese University of Hong Kong（香港中文大学）； Tsinghua University（清华大学）

作者：Songru Yang, Zili Liu, Tao Han, Ben Fei, Fenghua Ling, Lei Bai, Chang Liu, Xiangyang Ji, Zhenwei Shi, Zhengxia Zou

英文摘要：Global Station Weather Forecasting (GSWF) is pivotal for localized and extreme weather prediction over key regions. Despite efforts to exploit look-back windows, existing methods show limited accuracy gains and struggle with extreme events and error accumulation. These limitations stem from overreliance on short-term patterns, which are insufficient to capture chaotic weather dynamics, especially under partial observations. To address this problem, we propose a novel Triaxial State Space Model (TSSM) with a history-enhanced Temporal-VariableHistorical paradigm, which incorporates period-aligned historical weather data to compensate for long-term, large-scale periodic, and full-window weather patterns beyond the temporal lookback window. Specifically, TSSM stacks historical samples into period-aligned batches, where forecasting is causally supported by historical and current observations. Temporal, variable, and historical scanning are designed to capture axial temporal dependencies, variable correlations, and historical evolution. This structure is hierarchically shared to model seasonal to extreme events while alleviating misalignment across historical patterns. TSSM achieves SOTA performance on Weather-5K, the largest station weather dataset to date, with 10% and 61% gains in accuracy and extreme event metrics, and obtains 95% best or second-best results on human-involved datasets. Its advantages are more pronounced in long-horizon and iterative forecasting, reaching a 37.5% gain at 240h and up to 103.5% under a 48h times 5 iterative setting. Moreover, TSSM retains > 90% performance under up to 80% missing observations, compared with < 43% for baselines, demonstrating robustness and practical potential for reliable GSWF in global in-situ observation networks.

AI 总结：针对现实交通数据时空预测难题，提出STKAN架构，将泰勒多项式柯尔莫哥洛夫-阿诺德网络模块引入时空令牌混合，经实验验证其性能有竞争力，表明非线性函数逼近器设计对时空预测架构设计有补充作用。

链接：https://arxiv.org/abs/2607.13108

机构：The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； Chang’an University（长安大学）； China University of Geosciences（中国地质大学）

作者：Sicong Lai, Yuehong Hu, Siru Zhong, Si Qiao, Yuxuan Liang, Guangyin Jin

英文摘要：Real-world traffic data exhibit heterogeneous spatial correlations and nonlinear temporal dynamics, posing substantial challenges for accurate spatio-temporal forecasting. Existing approaches have developed increasingly sophisticated graph, attention, and decomposition architectures, while the influence of the underlying nonlinear function approximator has received comparatively less attention. In this work, we propose STKAN, a spatio-temporal forecasting architecture that introduces Taylor-polynomial Kolmogorov--Arnold Network modules into spatial and temporal token mixing. STKAN first constructs high-level spatial representations through a learnable soft node-group assignment mechanism, applies group-wise spatial mixing, and subsequently models temporal dependencies over the compressed sequence. Spatial and temporal self-attention layers are further employed to capture long-range interactions. Experiments on five traffic forecasting benchmarks show that STKAN achieves competitive performance and performs better than the evaluated MLP-based variant in the tested settings. These results suggest that the design of nonlinear function approximators can serve as a useful complement to architectural design in spatio-temporal forecasting.

AI 总结：针对交通流量预测中自注意力机制扩展性有限的问题，提出EMAGN，通过学习聚类矩阵将空间注意力机制线性化，降低复杂度，实验表明其在准确性和效率上优于其他模型，扩展了可行模型配置。

链接：https://arxiv.org/abs/2607.13241

机构：Shanghai Jiao Tong University（上海交通大学）； University of Michigan, Ann Arbor（密歇根大学安娜堡分校）； University of California, Berkeley（加利福尼亚大学伯克利分校）； Cornell University（康奈尔大学）； Technische Universität Dresden（德累斯顿工业大学）； Carnegie Mellon University（卡内基梅隆大学）； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of Wisconsin–Madison（威斯康星大学麦迪逊分校）

作者：Mingxing Xu, Rakesh Chowdary Machineni, Ke Liu, Xi Cheng, Chengqi Lu, Xin Hu, Lyuhao Chen, Xiangyu Li, Junwei You, Oliver Gao

英文摘要： Traffic forecasting is highly challenging due to complex and nonlinear spatial and temporal dependencies. Self-attention mechanisms have been widely adopted to model dynamic and long-range dependencies, achieving state-of-the-art performance, but suffer from limited scalability due to quadratic computational and memory complexity. To address this, we propose an Efficient Multi-Attention Graph Network (EMAGN) that linearises the spatial attention mechanism itself, inspired by the theory of fast high-dimensional Gaussian filtering. Two learned clustering matrices C_k and C_v adaptively group key and value vectors into M super-clusters, reducing complexity from O(N^2 d) to O(NMd) without sacrificing the flexibility of attention for dynamic dependency modelling. Experimental results on PEMS-BAY and METR-LA show that EMAGN achieves accuracy within 2.7-3.2% MAE of full-attention GMAN while reducing training time by 32%, inference time by 38%, and GPU memory by 58%. Critically, at K=16 attention heads, full-attention GMAN runs out of memory on a standard 11 GB GPU entirely while EMAGN continues to operate, demonstrating a categorical expansion of feasible model configurations. EMAGN also surpasses Linformer and Performer in both accuracy and efficiency within the same backbone, owing to its traffic-network-aware adaptive clustering.

AI 总结：该研究对KANs和MLPs在结构化表格分类任务上进行实证比较，在标准化设置下训练并评估性能。结果显示KANs在二元和多类领域统计上更优，但效应量表明其有更高复杂度。结论是KANs适用于高精度应用，MLPs对资源受限环境更合适，未来应扩展分析。

链接：https://arxiv.org/abs/2607.13413

机构：Institute of Computer Science, University of the Philippines Los Baños（菲律宾大学洛斯巴尼奥斯分校计算机科学研究所）； Machine Learning and Artificial Intelligence Applications Lab, University of the Philippines Los Baños（菲律宾大学洛斯巴尼奥斯分校机器学习与人工智能应用实验室）

作者：Matthew Steven P. Toledo, Justine Raphael H. Jacinto, Vivekjeet Singh Chambal, Rodolfo C. Camaclang III, Jamlech Iram N. Gojo Cruz, Reginald Neil C. Recario

英文摘要：This study presents an empirical benchmarking comparison between Kolmogorov-Arnold Networks (KANs) and Multi-Layer Perceptrons (MLPs) on structured tabular classification tasks. Motivated by the growing interest in KANs as an alternative function-approximating architecture, we evaluate their out-of-the-box performance on twelve publicly available datasets spanning binary, multiclass, multilabel, and ordinal problems. Both models were trained under standardized preprocessing, architecture, and fixed hyperparameter settings, with performance assessed using test accuracy and F1-Score, paired hypothesis testing, and effect size analysis. Results show that KANs statistically outperform MLPs in binary and multiclass domains and achieve a significant aggregate advantage across all datasets. However, the observed medium effect size (d = -0.46) raises an important cost-benefit consideration: while KANs offer superior generalization through adaptive spline-based mappings, this advantage comes with substantially higher parameter and computational complexity relative to the MLP baseline. These findings suggest KANs are the preferred choice for high-precision applications, while MLPs remain a robust and efficient option for resource-constrained environments. Future work should extend this analysis to additional data modalities to further refine these architectural selection criteria.

AI 总结：研究多模态学习中后融合增强问题，提出并行量子特征增强框架PQFA，将其应用于融合特征，经多种处理后幅度编码到量子电路预测。实验表明PQFA性能优、参数效率高，是混合量子 - 经典多模态学习后融合增强的有效策略。

链接：https://arxiv.org/abs/2607.13466

机构：AMSS（中国科学院数学与系统科学研究院）

作者：Mingzhu Wang, Yun Shang

英文摘要：Most multimodal learning methods improve how heterogeneous representations are aligned and fused, while post-fusion enhancement remains less explored. We propose Parallel Quantum Feature Augmentation (PQFA), a hybrid quantum-classical framework that applies multiple shallow variational quantum circuits to fused multimodal features. Text and image representations extracted by frozen RoBERTa and ViT encoders are processed through bidirectional cross-attention, attentive pooling, and adaptive gated fusion. The fused feature is then amplitude-encoded into parallel quantum circuits, whose measurement readouts are concatenated with the classical representation for prediction. We evaluate PQFA on MM-IMDb and N24News through controlled comparisons using the same encoders, fusion backbone, data splits, projection dimension, and augmentation output width. PQFA consistently outperforms both the fusion backbone without quantum augmentation and a width-matched MLP augmentation baseline, while using approximately 2.2K augmentation parameters compared with 24.0K for the MLP branch. Missing-modality experiments further show improved robustness when textual or visual inputs are incomplete, with particularly clear gains when the more informative textual modality is severely degraded. Controlled ablations and feature-space analyses indicate that the improvement cannot be reproduced by random feature mappings, increased classical width, or untrained quantum transformations. Quantum-state diagnostics additionally show stable predictive performance across the tested simulated noise levels and distinct branch-specific transformations of the encoded states. These results establish PQFA as an effective and parameter-efficient strategy for post-fusion augmentation in hybrid quantum-classical multimodal learning.

AI 总结：研究Transformer前馈块架构设计组件在初始化时如何确定跨深度的秩保留，通过重新解释跳跃连接和归一化等，揭示架构各方面对秩的影响，将深度网络架构设计视为在秩崩溃、集成行为和参数数量间的权衡。

链接：https://arxiv.org/abs/2607.14018

机构：MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

作者：Katie Everett

英文摘要： We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization. We reinterpret skip connections and normalization, long understood as controlling magnitude, as mechanisms for preserving gradient rank across depth, since the very matrix multiplications and nonlinear activations that make the network expressive also reduce the rank. We show that skip connections trade off rank collapse against ensemble-like behavior, controlled by the relative scales of the branch and the skip: skip connections route the gradient around the residual branch, where rank is lost, rather than along the long gradient paths that encourage the layers to compose. The placement of the normalization layer controls this same tradeoff by setting the branch-to-skip ratio across depth, unifying much of the normalization placement and depth scaling literature, in particular why rank collapses for Post-Norm but plateaus for Pre-Norm. Other aspects of the architecture, like the two-matrix structure that expands and contracts the width, use additional parameters to preserve the representation or branch Jacobian rank. The second matrix decorrelates a coherent mean spike that would grow across blocks with a single matrix and uncentered activation, preventing the residual representation from collapsing. The width expansion between the two matrices keeps the branch Jacobian full rank: applying the rank-reducing activation in this expanded space leaves enough directions to span the original, at a width that follows a Marchenko--Pastur law. The initialization rank of the input--output Jacobian predicts which networks train on CIFAR-10. Taken together, we recast architecture design for deep networks as navigating an intrinsic tradeoff among rank collapse, ensemble-like behavior, and parameter count.

AI 总结：研究在低秩矩阵分解问题上重新评估Muon优化器，通过与精心调整的自适应基线对比，发现Muon在此设置下不始终优于AdamW，一些优势对超参数选择敏感，更细致地展现谱感知正交化何时有益，主张在受控问题上评估优化器。

链接：https://arxiv.org/abs/2607.13246

机构：Halicioğlu Data Science Institute, UC San Diego（加州大学圣地亚哥分校哈利西奥卢数据科学研究所）； Department of Mathematics, UC San Diego（加州大学圣地亚哥分校数学系）

作者：Ali Parviz, Gal Mishne, Alex Cloninger

英文摘要：Muon has recently emerged as a strong optimizer for large-scale deep learning, where it reshapes gradient updates through approximate orthogonalization and has been reported to outperform Adam and AdamW in large language model training. Its empirical success has motivated a growing body of theoretical work that interprets Muon as steepest descent under the spectral norm. Yet it remains unclear which of Muon's advantages stem from its update rule itself and which are artifacts of the scale, architecture, and data of modern deep networks. In this work, we isolate the optimizer from these confounding factors by studying Muon on a simple, well-understood, and spectrally structured problem: low-rank matrix factorization. Through a controlled comparison against carefully tuned adaptive baselines, we find that Muon does not consistently outperform AdamW in this setting and that several previously reported advantages are sensitive to hyperparameter choices. Our results provide a more nuanced picture of when spectrum-aware orthogonalization is beneficial and argue for evaluating modern optimizers on controlled problems in addition to end-to-end benchmarks.

AI 总结：研究非负矩阵分解，针对多数KL-NMF算法用可分离主元找迭代已达极限的问题，提出用损失的二阶泰勒展开，通过推广HALS算法最小化不可分离替代函数，得到高效且收敛的KL-NMF算法，在多数据集上表现良好。

链接：https://arxiv.org/abs/2607.13919

机构：ENS de Lyon（里昂高等师范学校）； CNRS and LIP (UMR5668, Université de Lyon - ENS de Lyon - UCBL - CNRS - Inria)（法国国家科学研究中心和里昂信息学实验室（联合研究单位5668，里昂大学 - 里昂高等师范学校 - 里昂中央理工学院 - 法国国家科学研究中心 - 法国国家信息与自动化研究所））

作者：Damien Lesens, Jérémy E. Cohen, Bora Uçar

英文摘要：Nonnegative Matrix Factorization (NMF) is a fundamental tool in unsupervised learning, which approximates a nonnegative matrix by the product of two low-rank nonnegative factors. The Kullback-Leibler (KL) divergence is best suited to measure the data to model discrepancy when the decomposed data sample follows a Poisson distribution, which is the case for count datasets such as term-document matrices or images. Most KL-NMF algorithms in the literature minimize a separable majorant of the loss to find their next iterate. We argue that this method has reached its limits and propose to use instead the second-order Taylor expansion of the loss, leading to a Newton-type method. We minimize this non-separable surrogate by proposing a generalization of the well-known HALS algorithm. This yields an efficient KL-NMF algorithm which provably converges and which competes favorably with state-of-the-art algorithms on a large variety of datasets.

AI 总结：研究利用未标记数据进行可泛化神经群体解码的问题，提出MOJO训练框架，联合自监督学习与监督学习目标，在多数据集上评估，结果显示该框架能提升性能、产生更具可解释性表示且可推广到其他神经模态。

链接：https://arxiv.org/abs/2607.14086

作者：Ximeng Mao, Nanda H. Krishna, Avery Hee-Woon Ryoo, Matthew G. Perich, Guillaume Lajoie

英文摘要：Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding performance. However, current spike-based models are restricted to supervised learning (SL), limiting training to datasets with paired behavioural labels. To address this limitation, we introduce MOJO (Masked autOencoder-based JOint training), a training framework for spike-tokenizing models that jointly leverages self-supervised learning (SSL) via masked autoencoding and SL objectives. We evaluate MOJO on three spiking datasets spanning monkey motor cortex during reaching tasks and multi-regional mouse recordings during vision and decision making tasks, demonstrating superior performance over purely SL-trained models. This improvement is especially pronounced when training with limited labelled data, particularly in few-shot finetuning, where only a small amount of labelled data from a new session is available. Incorporating SSL also yields more interpretable neuronal representations, improving performance on brain region classification and spike-statistics prediction without explicit optimization for these tasks. We further show that MOJO generalizes beyond spiking data to human electrocorticography during speech, where it continues to outperform purely SL-trained models and achieves performance comparable to neuro-foundation models (NFMs) designed specifically for continuous signals. Overall, augmenting spike-tokenizing models with SSL improves performance in label-impoverished settings and enables the use of unlabelled data across various tasks and species, while generalizing to other neural modalities. These results suggest a path towards more flexible and scalable data usage when training NFMs.

AI 总结：研究流系统中何时调用大语言模型的问题，将其转化为基于风险的序贯停止问题，证明了相关理论结果。通过在涡轮风扇退化数据上的实验，验证假设、比较基线，得出次线性遗憾、高诊断质量等结论，表明异常分数驱动的风险函数更优。

链接：https://arxiv.org/abs/2607.13048

机构：Viterbi School of Engineering, University of Southern California（南加州大学维特比工程学院）

作者：Zhaohui Wang

英文摘要：Streaming inference pipelines increasingly pair lightweight fast models with Large Language Models (LLMs) that provide rich semantic understanding at substantial cost. The central question of when to invoke the LLM has received limited formal treatment. We cast this as a risk-based sequential stopping problem, where a trigger policy fires when a risk functional over the observation history exceeds a threshold. Within this framework, we prove six results: a minimum inter-event time bound excluding trigger chattering; optimality of threshold policies via smooth pasting; approximate SPRT guarantees under estimated parameters; O(sqrt(T log T)) regret for stationary streams, extending to O(sqrt((C_T + 1) T log T)) under C_T changepoints; O(1/sqrt(T)) convergence of online gradient descent for adaptive thresholds; and a calibration-to-miss-rate transfer inequality. Several classical trigger families, including event-triggered, optimal stopping, SPRT, CUSUM, and Bayesian triggers, can be expressed as special cases of this framework. On turbofan degradation data (CMAPSS) with real LLM calls, we empirically verify the theoretical assumptions, ablate the risk function design, compare against six baselines including a RouteLLM-style router and contextual bandits, and analyze cost sensitivity and LLM failure modes. The results confirm sublinear regret, with alpha < 1 for all principled triggers; high diagnostic quality, with 92.9 percent of 1600 LLM diagnoses reaching grounding score >= 0.75 under our rubric; and that anomaly-score-driven risk functions dominate alternatives by roughly an order of magnitude on the Pareto AUC.

AI 总结：研究安全强化学习中罕见灾难性尾部事件难检测的问题，提出SteinGate方法，利用核斯坦因差异进行稳健一致性检查并考虑边界原子，动态调整学习机制，实验证明该方法能降低约束违反频率和严重性且保持竞争力。

链接：https://arxiv.org/abs/2607.13175

作者：Yassine Chemingui, Chenhua Fan, Honghao Wei, Janardhan Rao Doppa

英文摘要：Safe reinforcement learning typically enforces safety by bounding expected cumulative costs, a criterion that often fails to detect rare but catastrophic tail events. To overcome these limitations, this paper introduces SteinGate, a boundary-aware distributional safety certificate that replaces fragile tail fitting with a robust consistency check using Kernelized Stein Discrepancy while accounting for boundary atoms induced by clipped costs. SteinGate evaluates whether observed policy rollout costs remain consistent with a safe reference distribution, providing a non-parametric safety certificate. This certificate is used to dynamically adapt the learning regime: favoring reward-improving policy updates when rollouts remain consistent with the safe reference and switching to recovery behavior when the cost tail deviates. Experiments on continuous-control benchmarks demonstrate that SteinGate significantly reduces both the frequency and severity of constraint violations during training while maintaining competitive returns relative to state-of-the-art baselines.

AI 总结：研究针对演员-评论家算法在现实世界控制场景中的应用，通过实际水处理厂控制任务进行超33000次实验，分析算法设计组件对运行变异性和超参数敏感性的影响，为从业者在新场景中进行组件级决策提供实证指导。

链接：https://arxiv.org/abs/2607.13274

作者：Haseeb Shah, Lingwei Zhu, Adam White, Martha White

英文摘要：Reinforcement learning is increasingly being considered for controlling real-world systems, from fusion plasma and autonomous vehicles to drug discovery and drinking water treatment, where reliability is essential and tuning budgets are limited. Actor-critic algorithms share a set of design decisions, such as how the policy is updated, how it represents the distribution over actions, how its gradient is estimated, and how often it is updated relative to the value estimator. Using a control task derived from a real water treatment plant, we analyze over 33,000 experiments to determine how these components affect variability across runs and sensitivity to hyperparameters. Common defaults, such as Gaussian action distributions with pathwise gradient estimators, are among the least reliable configurations, whereas bounded distributions with adaptive update schedules remain robust across a wide range of settings. These findings offer empirical guidance to practitioners across scientific and engineering domains for understanding and making component-level decisions when adapting actor-critic methods to new real-world control settings.

AI 总结：研究强化学习训练后计算资源分配问题，引入浮点运算核算框架，通过LoRA适配的Qwen2.5策略发现条件分配前沿，揭示模型选择与训练分配关联及奖励系统对核算影响，提出RACE协议，建议相关论文报告总浮点运算及计算分配方式。

链接：https://arxiv.org/abs/2607.13389

机构：Technische Universität Berlin（柏林工业大学）

作者：Patrick Wilhelm, Odej Kao

英文摘要： Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget. We study the fixed-budget decision problem behind this practice: under the same post-training budget, should one use a larger policy, train a smaller policy longer, generate more rollout search, or spend compute on stronger reward feedback? We introduce a FLOP-accounting framework for GRPO post-training that decomposes compute into rollout/search, policy-update/learning, and reward- or feedback-model evaluation. Across LoRA-adapted Qwen2.5 policies, we find conditional allocation frontiers: the best observed allocation changes with model size, compute budget, reward system, and evaluation target. Same-FLOP model-size comparisons show that model choice and training allocation are coupled because larger policies consume more per-token compute and therefore buy fewer updates or rollouts under the same budget. Reward systems also change the accounting: rule-based rewards spend nearly all non-update compute on policy rollouts, while PRM-style feedback allocates a visible part of the budget to reward-model inference. We present RACE as a diagnostic pilot-grid protocol, not a guarantee of held-out improvement, for identifying allocation regimes before expensive validation runs; our results suggest that RL post-training papers should report total FLOPs together with how compute is divided among model size, search, learning, and feedback.

AI 总结：该研究聚焦强化学习，提出FaStR方法，通过对转移核的三模张量CP分解，用噪声对比目标拟合，产生单独编码器形成谱表示。其因式分解形式缩小假设类，在高维运动任务中效果好，状态编码器可跨执行器移位转移。

链接：https://arxiv.org/abs/2607.13498

机构：University of Washington（华盛顿大学）

作者：Junyi Wu, Dan Li

英文摘要：Learning a compact model of the world from interaction data is central to sample-efficient deep reinforcement learning. Spectral representation methods have become the leading paradigm for representation learning in continuous control by taking a matrix view of the transition kernel, with state-action pairs on one side and next states on the other, and learning a low-rank factorization through self-supervised contrastive objectives. We take this view one step further. The transition kernel is naturally a three-mode tensor over states, actions, and next states, and a CP decomposition gives one feature map per mode. We propose FaStR, which fits this decomposition with a noise contrastive objective, producing separate state, action, and next-state encoders that together form a single spectral representation. The factored form yields a smaller hypothesis class, and the sample size needed for representation learning shrinks by a factor that scales with the smaller of the state and action dimensions. Empirically, FaStR delivers its largest gains on high-dimensional locomotion tasks whose dynamics align with the factored structure, and the learned state encoder transfers intact across actuator shift while only the action encoder is retrained.

AI 总结：研究众包感知中预算受限的在线工人招募问题，工人绩效随经验变化，成本未知。提出成本感知在线学习框架，建模为结构化策略模型，能联合学习奖励轨迹与成本，检测性能饱和，分配预算最大化感知效用，实验验证优于基线方法。

链接：https://arxiv.org/abs/2607.13546

机构：University of Florida（佛罗里达大学）； University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

作者：Yin Huang, Qingsong Liu, Jie Xu

英文摘要：Mobile crowdsensing (MC) recruits mobile users to perform sensing tasks using their smartphones, enabling large-scale applications such as traffic monitoring and environmental sensing. A fundamental challenge is online worker recruitment under uncertainty, where the platform must learn workers' sensing performance while operating with a limited budget. Existing learning-based MC recruitment methods typically assume that each worker's sensing quality is stationary with a fixed mean over time. In practice, however, worker performance often improves with experience and eventually stabilizes, while the incurred sensing cost can be unknown in advance due to time-varying device and context states. In this paper, we study a budget-constrained online recruitment problem in which the platform selects one worker in each round, observes the sensing quality and incurred cost, where the expected sensing quality of each worker increases with experience and eventually converges to a plateau, and repeats until the budget is exhausted. We formulate this problem as a structured bandit model where each worker's expected reward evolves according to an unknown increasing-then-converging function of its participation count, and each worker has an unknown expected cost. We develop a cost-aware online learning framework that jointly learns evolving reward trajectories and heterogeneous costs, detects performance saturation, and allocates the limited budget to maximize long-term sensing utility. We provide theoretical performance guarantees and validate the proposed approach through extensive experiments, demonstrating consistent improvements over baselines that ignore experience-driven dynamics or assume known costs.

AI 总结：研究智能交互驾驶中主导者引导智能体决策的问题，提出在线结构化强化学习框架，贡献包括为单调智能体提出算法、确定相关条件、提出SQP，数值分析显示该方法在优化行驶奖励上比现有方法成本效率高30%。

链接：https://arxiv.org/abs/2607.13576

作者：Merlin Paul, Anup Aprem

英文摘要：Interactive driving, wherein an intelligent lead vehicle equipped with real-time traffic data coordinates route choices of connected vehicles, offers a promising approach to dynamic traffic management. To address the challenge of harmonising decisions, this paper considers the strategic information revealing framework of Bayesian persuasion. Here, the principal (lead vehicle) aims to guide the agent's (connected vehicle) partially observable sequential decision making towards its own objectives by selectively revealing information, such as real-time traffic ahead, using signals. However, the agent's farsighted response to maximize its long-term reward, renders the principal's signaling strategy design computationally challenging. We propose an online structured reinforcement learning framework to synthesize computationally efficient signaling strategy which is persuasive for a far-sighted agent. The main contributions of the paper are as follows: (i) For a monotonic agent with approximate best response, we propose MAPL, a structured policy learning algorithm for faster online learning, (ii) Identification of sufficient conditions for the supermodular structure of the Q function of the principal for a monotonic agent, (iii) Identification of sufficient conditions to ensure the persuasiveness of the principal's signaling strategy, (iv) Supermodular Q learning for Principal (SQP), which leverages the supermodular structure of principal's action value to synthesize computationally efficient signaling strategy that is persuasive for a monotonic learning agent, (v) Numerical analysis considering a real-time application of Bayesian persuasive driving for lane selection demonstrates that the proposed method is 30% cost efficient for optimising travelling rewards of both the lead and connected vehicle compared to the existing methodologies for signaling strategy design.

AI 总结：研究旨在提高无标签大语言模型推理准确性，提出CANON方法将共识转化为token级监督，通过采样多个解决方案并以达到多数答案的方案为条件设置模型快照来监督。实验表明该方法大幅提升性能，还能迁移，改进非单纯分布锐化。

链接：https://arxiv.org/abs/2607.13643

机构：ILLC, University of Amsterdam（逻辑、语言与计算研究所，阿姆斯特丹大学）； ILCC, University of Edinburgh（信息实验室，爱丁堡大学）

作者：John Gkountouras, Josip Jukić, Ivan Titov

英文摘要：Sampling multiple solutions and returning the majority answer is among the most reliable ways to improve the reasoning accuracy of large language models without labels, and a growing family of methods converts this consensus signal into training supervision. However, existing approaches use consensus only in restricted forms: as a filter that selects solutions for fine-tuning, as a preference between answers, or as a scalar reward for reinforcement learning, discarding most of the information that the agreeing solutions contain. We present CANON (Consensus-ANchored self-distillatiON), a label-free training method that turns consensus into dense, token-level supervision. For each unlabeled prompt, CANON samples multiple solutions, extracts the majority answer, and conditions a frozen snapshot of the model on a solution that reaches it; this consensus-anchored teacher then supervises the model on its own rollouts at every token. Experiments on mathematical and scientific reasoning benchmarks show that CANON improves pass@1 by up to 12 points, outperforming label-free reinforcement learning by 6 points at a seventh of its compute and approaching a teacher conditioned on gold solutions; trained on pooled unlabeled data, it transfers to held-out benchmarks, matching training methods that use gold labels. Analysis suggests that the improvements are not pure distribution sharpening: after training, the model solves problems it previously never solved in 32 attempts, and its majority vote itself becomes more accurate.

AI 总结：研究目标条件强化学习中目标编码问题，提出DAGR方法，通过多尺度门控交叉注意力将静态嵌入细化为状态条件嵌入，在OGBench上改善导航，在操纵和拼图任务中有不同表现，是一种结构化细化。

链接：https://arxiv.org/abs/2607.13731

机构：Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）； Department of Electrical Engineering and Automation, Aalto University（阿尔托大学电气工程与自动化系）； School of Engineering, Westlake University（西湖大学工学院）

作者：Xing Lei, Wenyan Yang, Xuetao Zhang, Donglin Wang

英文摘要：Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They still share one trait. None of them sees the current state. Such a state-independent embedding cannot mark which part of the goal still needs action. The policy must then recover that cue by inverting both encoders. We propose DAGR. It refines the static embedding of any late-fusion encoder into a state-conditioned one through multi-scale gated cross-attention. A near-identity gated residual preserves the base representation. Difference-aware Goal Cross-Attention then biases the attention scores using a per-token state-goal discrepancy map. On OGBench, DAGR improves navigation. Our ablations trace the gain to the gated residual, not to the difference bias that names the method. On manipulation and puzzle tasks it matches or falls below the base. DAGR is a structured refinement, not a universal improvement.

AI 总结：针对水下隐蔽协作任务中AUV信息获取与通信问题，提出SVR-MARL框架，利用实际信息刻画信息效用，在通信和隐蔽约束下学习协作策略，通过案例研究证明其能提高协作效率、降低通信与暴露风险。

链接：https://arxiv.org/abs/2607.13880

机构：School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机科学学院）； School of Cyber Engineering, Xidian University（西安电子科技大学网络空间安全学院）； Harbin Engineering University（哈尔滨工程大学）； Department of Informatics and Telecommunications, National and Kapodistrian University of Athens（雅典国立卡波迪斯特里亚大学信息与电信系）； KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University（哈利法大学KU 6G研究中心计算机与信息工程系）； CentraleSupelec, University Paris-Saclay（巴黎萨克雷大学中央理工学院）； School of Electrical and Electronics Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）

作者：Xueyao Zhang, Chenyang Yan, Bo Yang, Xuelin Cao, Zhiwen Yu, Bin Guo, George C. Alexandropoulos, Merouane Debbah, Chau Yuen

英文摘要：In underwater covert cooperative missions, autonomous underwater vehicles (AUVs) often cannot rely on active sonar to continuously obtain complete information, since active sensing and frequent communications increase the risk of exposure. As a result, AUVs primarily rely on passive observation, an approach that yields incomplete local perception and limited task efficiency. Although underwater acoustic communications can mitigate this limitation through information sharing, they are simultaneously constrained by long delays, severe interference, low reliability, and the risk of covert exposure. Existing communications-oriented multi-agent reinforcement learning (MARL) studies often model communication as an ideal information flow, whereas traditional communication optimization primarily focuses on link-level performance. However, both are insufficient to characterize the actual contribution of perceptual information to cooperative tasks under realistic conditions of covert physical communications. This paper proposes a Sensed Information Value Realization Multi-Agent Reinforcement Learning (SVR-MARL) framework that leverages practical information to characterize the utility of information for cooperative tasks and learns distributed cooperative policies under realistic communication and covert constraints. Through a case study of covert multi-AUV cooperative localization and tracking, the potential of the proposed framework to improve collaborative task efficiency while reducing unnecessary communication and exposure risks is demonstrated.

AI 总结：研究针对多轮智能体训练后的信用分配难题，提出TRACE方法，通过特定状态转换、对数概率获取及转换等步骤进行奖励分配。该方法无需额外训练，在长期复杂搜索任务中显著提升基础模型工具使用能力，在基准测试中表现良好且学习曲线更佳。

链接：https://arxiv.org/abs/2607.13988

机构：University of Wisconsin–Madison（威斯康星大学麦迪逊分校）； Microsoft Research（微软研究院）

作者：Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li

英文摘要： Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training. Outcome rewards provide reliable supervision for short-horizon reasoning, but become sparse and high-variance as trajectories grow to tens or hundreds of tool calls. They can also be misleading: a failed rollout may contain many useful actions that move the agent closer to the goal, yet outcome-only training assigns them the same negative advantage as the eventual mistake. We propose TRACE (Turn-level Reward Assignment via Credit Estimation), a dense credit-assignment method for agentic reinforcement learning. TRACE represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values. This requires no additional critic or process-label training, and its one-step log-ratio TD component telescopes across redundant tool calls. On long-horizon complex search, TRACE substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data. On the closed-web BrowseComp-Plus benchmark, it raises Qwen3-4B from $7.2$ to $35.6$ and Qwen3-30B-A3B from $8.4$ to $42.6$. The learned search behavior also transfers to open-web benchmarks, and the learning curves show earlier improvement and faster convergence during RL training.

AI 总结：该研究针对强化学习中稳定垂直运动倒立摆的问题，提出将李雅普诺夫特征指数作为密集奖励信号，智能体借此成功找到卡皮察摆振荡运动并抑制摆动，让摆处于直立位置。

链接：https://arxiv.org/abs/2607.14001

作者：Slava Andrejev

英文摘要：We suggest using the Lyapunov characteristic exponent (LCE) as a dense reward signal for the reinforcement learning problem of stabilizing the inverted pendulum with vertical motion. With LCE, the agent not only successfully found the oscillatory motion known as the Kapitza pendulum but also damped the pendulum's pivoting, leaving it in a strictly upright position.

AI 总结：研究针对模拟电路规模确定问题，提出灯塔强化学习方法，通过策略性重置策略，从高性能配置初始化情节引导探索，相比其他方法在样本效率、优化性能、通用性等方面显著提升，可增强基于强化学习的优化方法。

链接：https://arxiv.org/abs/2607.14008

机构：Sony Group Corporation（索尼集团公司）； EPFL（洛桑联邦理工学院）； Sony Semiconductor Solutions（索尼半导体解决方案公司）； TU Munich（慕尼黑工业大学）

作者：Mustafa Emre Gürsoy, Stefan Uhlich, Ryoga Matsuo, Yağız Gençer, Arun Venkitaraman, Chia-Yu Hsieh, Andrea Bonetti, Eisaku Ohbuchi, Lorenzo Servadei

英文摘要：In this paper, we introduce Lighthouse RL, a sample-efficient reinforcement learning (RL) approach for analog circuit sizing. Traditional methods lack generalization across different performance targets, while standard RL approaches waste resources exploring unpromising regions. Our method addresses these inefficiencies through a strategic reset strategy that initializes episodes from high-performing configurations discovered during training, called "lighthouses". These states, which are closer to the target objectives, guide exploration toward promising regions. When compared to RL and Bayesian optimization methods from the literature, we demonstrate the effectiveness of our approach on a 2D benchmark problem and on two analog circuits, showing significant improvements in sample efficiency (up to 1.72x faster), optimization performance (100% vs. 0-87% success rate), generalization (75% vs. 0-50% extrapolation success), and objective maximization. This efficiency is particularly valuable for computationally expensive black-box optimization problems, and our reset strategy can be used as a plug-and-play enhancement for any RL-based optimization approach.

AI 总结：研究离散扩散模型，引入统一框架从离散状态空间构建审视该模型，让现有公式成为共同设计空间实例，揭示训练、推理等方面权衡，为未来研究提供方向。

链接：https://arxiv.org/abs/2607.13431

机构：McGill University（麦吉尔大学）； Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）； University of Cambridge（剑桥大学）； University of Toronto（多伦多大学）； MBZUAI - Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； Tsinghua University（清华大学）； Rochester Institute of Technology（罗彻斯特理工学院）； Salesforce（Salesforce公司）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

作者：Ye Yuan, Weien Li, Rui Song, Zeyu Li, Haochen Liu, Xiangyu Kong, Zixuan Dong, Linfeng Du, Zipeng Sun, Weixu Zhang, Jiaxin Huang, Changjiang Han, Yonghan Yang, Zichen Zhao, Xiuyuan Hu, Haolun Wu, Yankai Chen, Fengran Mo, Jikun Kang, Bowei He, Philip S. Yu, Xue Liu

英文摘要：Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and iterative global refinement capabilities. Unlike continuous diffusion, where the state space is fixed, DDMs are fundamentally shaped by how the discrete state space is constructed: the tokenization scheme, the vocabulary topology, and domain-specific structural alphabets. This work introduces a unified conceptual framework that views discrete diffusion models through the construction of the underlying discrete state space. Within this framework, existing formulations, including transition-matrix, masking/absorbing-state, and score/ratio-based approaches, emerge as different instantiations of a common design space. The framework further exposes common design trade-offs across training objectives, inference algorithms, scaling behavior, systems optimization, and evaluation protocols, suggesting several promising directions for future research.

AI 总结：针对智能交通系统中联网自动驾驶车辆的通信需求，提出基于VAE的多任务卫星辅助语义通信框架，利用概率潜在表示编码，经噪声信道传输特征进行交通标志重建与分类，能显著降低带宽并保持性能稳定。

链接：https://arxiv.org/abs/2607.13494

作者：S. M. Abtahiul Alam, Niloy Das, Apurba Adhikary, Yu Qiao, Zhu Han, Choong Seon Hong

英文摘要：The development of smart transportation systems and the introduction of 6G wireless communication technologies have significantly changed vehicle network topologies. Future connected autonomous vehicle (CAV) networks require bandwidth-efficient, reliable, and low-latency communication for safety-critical applications such as traffic sign recognition and decision-making. Conventional communication systems transmit raw data regardless of task relevance, which is inefficient in resource-constrained satellite channels where uplink bandwidth is scarce and propagation losses are large. Semantic communication addresses this limitation by transmitting task-relevant information instead of full signal representations. It extracts and conveys essential semantic features and leverages deep learning to optimize task performance at the receiver. Therefore, we present a Variational Autoencoder (VAE)-based multi-task semantic communication framework for satellite-assisted autonomous driving. Unlike deterministic autoencoder-based methods, the proposed model uses probabilistic latent representations for more robust and efficient encoding. The learned features are transmitted over noisy wireless channels to perform traffic sign reconstruction and classification. The framework is trained end-to-end to jointly optimize both tasks. Results show that the proposed approach achieves significant bandwidth reduction of up to 87.23\% to 98.17\% while maintaining stable performance across varying signal-to-noise ratio conditions.

AI 总结：研究重尾数据匹配问题，提出HTFM框架，将重尾源视为时钟条件高斯源混合，用截断对数签名特征编码时钟。实验显示其在多领域优于高斯流匹配等基线，保留低NFE采样优势，还提供尾部控制接口。

链接：https://arxiv.org/abs/2607.13841

机构：Johns Hopkins University（约翰斯·霍普金斯大学）； National University of Singapore（新加坡国立大学）

作者：Zhouhao Yang, Yezhen Wang, Kenji Kawaguchi, Vladimir Braverman, Haoyang Cao

英文摘要：Heavy-tailed data arise in many domains where rare events carry disproportionate importance, such as imbalanced image datasets, financial returns, and weather extremes. Standard diffusion and flow-matching models typically begin from Gaussian noise or Gaussian source distributions, which yield tractable training targets but provide a poor inductive match for heavy-tailed data. We propose Heavy-Tailed Flow Matching via Random Clocks (HTFM), a framework that portrays heavy-tailed sources as mixtures of clock-conditioned Gaussian sources. Conditioning on a given clock path, the source distribution and flow are Gaussian; marginalizing over the clock gives a Gaussian scale mixture covering Gaussian, $\alpha$-stable, and Student-t families. To make the clock-conditioned vector field practical, we encode the path-valued clock using truncated logsignature features, allowing the velocity field to adapt to the realized conditional space with negligible overhead. Empirically, on 2D imbalanced $\alpha$-stable mixtures, CIFAR10-LT, and HRRR weather fields, HTFM improves mode coverage, sample quality, and tail-statistic recovery over Gaussian flow matching and competitive heavy-tailed baselines, while retaining the low-NFE sampling advantage of flow matching. Moreover, the random-clock formulation further provides a practical tail-control interface: by varying only the clock law or tail parameter, the same architecture can calibrate the ``heaviness'' of generated tails across different distribution families.

AI 总结：研究风电场SCADA数据过滤问题，通过比较多种聚类算法与手动过滤的精度，引入适用评估指标，应用于某海上风电场数据，结果显示多数聚类方法精度更高，但不同模型有差异，专家参与仍必要。

链接：https://arxiv.org/abs/2607.13544

作者：Nicolò Italiano, Vasilis Pettas, Tuhfe Göçmen, Nicolaos A. Cutululis

英文摘要：During wind farm operation, Supervisory Control and Data Acquisition (SCADA) systems record numerous anomalies, transients, and specific operational modes, leading to large datasets. However, for a wide range of applications, only measurements corresponding to normal operation are required and, therefore, the SCADA data must be filtered. For this purpose, several methods have been proposed to automate and replace manual filtering conducted by experts via visual inspection of the data. In this paper, we compare the filtering accuracy of multiple clustering algorithms against manual filtering, introducing evaluation metrics that are suitable for unlabeled data and robust across potential applications. Based on the results, we provide recommendations for generalizing model calibration to different datasets and discuss potential use cases for each model. The models are applied to the SCADA data of three turbines of an existing offshore wind farm, using 10-minute statistics across multiple data channels. In addition to the anomalies and operational modes typically recorded, the dataset presents a large number of non-evident outliers due to several field tests. Overall, the results highlight the importance of extending the analysis beyond the power curve, both in feature selection and in the design of evaluation metrics. In most cases, cluster-based methods are able to detect both evident and subtle outliers, achieving higher accuracy than manual filtering. However, the accuracy and the amount of data retained vary considerably depending on the model, and expert involvement remains necessary, though to a reduced extent compared to manual filtering.

AI 总结：研究设计任务中黑箱函数优化问题，提出一种贝叶斯优化方法，该方法能有效找到对最大扰动具有鲁棒性的满意解，且假设优化时输入可控，部署后会受扰。

链接：https://arxiv.org/abs/2607.13652

机构：University of Helsinki（赫尔辛基大学）； ASM International N.V.（阿斯麦尔公司）

作者：Samuli Kinnunen, Petrus Mikkola, Antti Niskanen, Arto Klami

英文摘要： Many design tasks can be cast as black-box function optimization, enabling use of Bayesian optimization to find an ideal design with minimal number of trials. However, often we do not actually need the optimum but instead a sufficiently good solution is enough, for instance a material that is durable enough for its intended use. In most cases there are multiple satisfactory solutions, forming a superlevel set of the function, raising a key question of which one to prefer. We answer this by explaining why robustness to input perturbations that may occur when the solution is deployed is a good criterion and by introduce a Bayesian optimization method that efficiently finds satisficing solutions that are robust to maximally large perturbations. In contrast to previous works, we assume the inputs can be accurately controlled during optimization, but will be perturbed after the deployment.

AI 总结：研究具有通用奖励函数逼近的上下文组合半贪心问题，提出计算高效算法，通过解决凸优化问题采样组合动作平衡探索与利用，证明其实现\(O(\sqrt{m A T \log |\mathcal{F}|})\)极小极大最优遗憾界，推广到多种设置。

链接：https://arxiv.org/abs/2607.13686

机构：The University of Arizona（亚利桑那大学）

作者：Hao Qin, Chicheng Zhang

英文摘要：We study the contextual combinatorial semi-bandit (CCSB) problem with general reward function approximation. At each round, the learner observes a context, selects a combinatorial action consisting of a subset of basic arms, and receives the reward of each selected arm; the goal is to maximize the cumulative reward over time. We propose this http URL, a computationally efficient algorithm that, at each round, solves a convex optimization problem to sample a combinatorial action that balances exploration and exploitation. this http URL scales to large arm sets and imposes no structural assumptions on the action set beyond a cardinality bound of $m$ on each combinatorial action. We prove that this http URL achieves a minimax optimal regret bound of $O(\sqrt{m A T \log |\mathcal{F}|})$, where $A$ is the number of arms, $m$ is the maximum number of arms in a combinatorial action, $T$ is the time horizon, and $\mathcal{F}$ is the reward function class. In the realizable setting, this bound matches the state-of-the-art regret guarantees achieved by policy search-based algorithms in the more restricted slate recommendation settings, while simultaneously generalizing to arbitrary combinatorial action structures and general reward function approximation.

AI 总结：研究在模运算训练的神经网络，当可表达函数类坍缩到有限维代数簇时的情况。通过全纯单项式激活的两层网络及代数表征研究，给出训练损失下界，实验表明代数预测准确率高，呈现二元行为，是容量 - Grokking关系极限，瓶颈消融连接极端与标准网络。

链接：https://arxiv.org/abs/2607.13749

机构：University Paris City & University of Reunion（巴黎城市大学和留尼汪大学）； Dipartimento di Fisica e Chimica Emilio Segrè, Università degli Studi di Palermo（巴勒莫大学埃米利奥·塞格雷物理与化学系）； Thayer School of Engineering, Dartmouth College（达特茅斯学院塞耶工程学院）； EnergyLab, University of Reunion（留尼汪大学能源实验室）； PEACCEL, AI for Biologics（PEACCEL，生物制品人工智能）

作者：Chon-Fai Kam, Xavier Cadet, Miloud Bessafi, Frederic Cadet

英文摘要：Neural networks trained on modular arithmetic exhibit grokking, a delayed transition from memorisation to generalisation known to depend on model capacity: too little and the network memorises slowly or not at all, too much and it generalises almost immediately. What happens at the extreme of this spectrum, when the architecture's expressible function class collapses to a finite-dimensional algebraic variety? We study two-layer networks with a holomorphic monomial activation sigma(z)=z^k, trained on modular tasks encoded via roots of unity. Here the network output, regardless of hidden width, is confined to a (k+1)-dimensional subspace of characters of (Z_p)^2, an O(k/p^2) slice of the full function space. We give a complete algebraic characterisation of this subspace: a task is representable if and only if its discrete Fourier support lies on the diagonal u+v = k (mod p), which for linear-phase targets reduces to the arithmetic criterion m+n=k. This is not merely a constraint on eventual generalisation but on memorisation itself: because the outputs are algebraically confined, a non-representable target cannot be fit even on the training set, and we prove a positive lower bound on the training loss, independent of width. Across 585 runs the algebraic prediction matches the observed outcome with 99.8% accuracy, with no memorisation regime and no grokking; outcomes split cleanly into instant success and outright failure. This binary behaviour is the limiting case of the capacity-grokking relationship: when the expressible class shrinks to a fixed algebraic object, the question of when a network will grok dissolves into whether it can represent the target at all. A bottleneck ablation connects this extreme to standard networks, tracing a continuous path from representational failure, through memorisation without generalisation, to grokking with a shrinking gap as capacity grows.

AI 总结：研究可再生能源预测问题，提出基于聚类的顺序特征选择（CSFS）方法，通过结构化文献综述分析特征选择现状，经实证评估，该方法能在可再生能源预测中实现高效可靠的特征选择，性能与SFS相当且降低计算成本。

链接：https://arxiv.org/abs/2607.14024

机构：University of Würzburg（维尔茨堡大学）； Baden-Wuerttemberg Cooperative State University Mosbach（巴登-符腾堡双元制应用技术大学莫斯巴赫分校）

作者：Daniel Grillmeyer, Marius Hadry, Michael Stenger, Vanessa Borst, Veronika Lesch, Samuel Kounev

英文摘要：With rising global energy demand and growing awareness of climate change and its impacts, the share of renewable energies in the global energy mix continues to grow. Unlike conventional power generation, the output of renewable energy sources cannot be controlled as consistently due to their dependence on environmental conditions. Therefore, reliable prediction of current and future energy production is essential. In this paper, we report findings from two structured literature reviews on real-world renewable energy prediction tasks: wind turbine power curve modeling and photovoltaic power prediction. For the former, we conducted a comprehensive literature review ourselves, while for the latter, we synthesize the key findings regarding frequently selected input features based on an existing survey. Across both domains, our analysis reveals that despite the large number of available monitoring and environmental variables, only limited or unsystematic methods for feature selection exist. To address this gap, we propose Cluster-based Sequential Feature Selection (CSFS), a novel, model-agnostic, clustering-based wrapper method for automatic, efficient, and reliable feature selection in renewable energy prediction pipelines. To support reproducibility and reuse, we provide an open-source implementation of CSFS on GitHub. We empirically evaluate the proposed approach on both use cases and compare it with established feature selection techniques such as wrapper-based sequential feature selection (SFS), filter-based methods, and Random Forest's embedded feature importance. The results show that the wrapper-based methods overall provide better-performing selections of features. CSFS achieves a predictive performance comparable to SFS while reducing computational cost by an average of 21%.

AI 总结：研究如何从线性混合信号中恢复独立源信号，提出用平方瓦瑟斯坦距离衡量非高斯性，基于此构建OT - ICA算法，实验表明该算法在不同分布上优于传统方法，且可用于无分布假设的应用ICA任务。

链接：https://arxiv.org/abs/2607.14081

机构：University of Tübingen（图宾根大学）； Max Planck Institute for Intelligent Systems, Tübingen（图宾根马克斯·普朗克智能系统研究所）； Institute of Artificial Intelligence TU Braunschweig（布伦瑞克工业大学人工智能研究所）

作者：Ashutosh Jha, Michel Besserve, Simon Buchholz

英文摘要：Linear Independent Component Analysis (ICA) recovers jointly independent source signals from their linear mixtures. To achieve this, classical ICA algorithms attempt to maximize non-Gaussianity, measured by negentropy, which is linked to independence by information theory. Because exact negentropy optimization is intractable, they rely on proxy contrast functions, such as fourth-order cumulants, and parametric log-likelihoods. We propose instead to measure non-Gaussianity using the squared Wasserstein distance $W_2^2$ to a standard Gaussian. We prove that the Wasserstein distance between a standard normal distribution and linear projections of the data is maximized when the projection recovers an independent component. Based on this observation, we propose the OT-ICA algorithm which finds this projection by gradient-based optimization. Empirical evaluation on simulated data shows that OT-ICA outperforms proxy-based methods for different distributions of the latent variables. Application to EEG artifact removal and econometric price discovery confirm OT-ICA can be used for applied ICA tasks without distributional assumptions.

AI 总结：本文综述联邦可解释人工智能（FedXAI）范式，介绍其分类法，回顾多种方法及评估实践，讨论不足，识别如非IID数据下可解释性等关键挑战，为设计可信、透明且隐私保护的联邦人工智能系统提供参考。

链接：https://arxiv.org/abs/2607.13045

机构：Department of Information Engineering, University of Pisa（比萨大学信息工程系）

作者：Masoume Gholizade, Fabrizio Ruffini, Pietro Ducange, Francesco Marcelloni

英文摘要：Federated Learning (FL) has emerged as a key paradigm for privacy-preserving collaborative model training across distributed and heterogeneous data sources. By keeping raw data local, FL addresses data confidentiality concerns, yet it does not resolve the opacity of modern machine learning models. In parallel, Explainable Artificial Intelligence (XAI) has gained attention for improving transparency, trust, and accountability, particularly in high-stakes domains. Their intersection has given rise to Federated Explainable Artificial Intelligence (FedXAI) paradigm, which aims to jointly satisfy privacy and explainability requirements. This survey provides a systematic review of FedXAI, highlighting the transition of explainability from a post-hoc tool to an integral component of the FL lifecycle. We show how explainability supports aggregation, personalization, robustness, coordination, and system-level decision making. To organize the literature, we introduce a taxonomy that classifies FedXAI methods by the role of explainability, model and explainer types, explanation scope, integration level, FL settings, and data heterogeneity. We review approaches ranging from model-agnostic explanations to interpretable federated models and explainability-aware aggregation mechanisms. We also examine evaluation practices and discuss the lack of standardized benchmarks and metrics for measuring explanation quality, stability, privacy leakage, and computational overhead. Finally, we identify key challenges, including explainability under non-IID data, explanation-centric security threats, communication-efficient XAI, continual FedXAI, and the integration of domain knowledge and regulatory constraints. By consolidating existing work and identifying key gaps, this survey serves as a reference framework for designing trustworthy, transparent, and privacy-preserving federated AI systems.

AI 总结：研究针对人类认知中理解与生成的耦合循环，引入自校正耦合马尔可夫跳跃过程框架及$\texttt{CO}_\texttt{2}\texttt{Jump}$采样器，解决掩码扩散模型跨模态矛盾问题，创建多模态语料库，该方法在图像相关任务中性能优异，且性能随去噪步骤数提升。

链接：https://arxiv.org/abs/2607.13188

机构：Stony Brook University（纽约州立大学石溪分校）； Google DeepMind（谷歌深度思维）

作者：Minh-Quan Le, Armand Comas, Alexandros Lattas, Stylianos Moschoglou, Pedro Vélez, Amit Raj, Aaron Germuth, Thabo Beeler, Dimitris Samaras, Di Qiu

英文摘要：Human cognition does not separate understanding and generation. A teacher at a whiteboard speaks and draws $\textit{together}$, each modality reshapes the other. In this paper, we bring this coupled loop to artificial systems. Masked Diffusion Models (MDMs) are ideally suited to this task, yet existing samplers either decode text and image interleavedly or independently update them in parallel branches that share only previous-step history, but not the other modality's latest decisions $\textit{within}$ the same step; combined with MDMs' inability to remask, cross-modal contradictions are neither detected nor repaired. We introduce $\textbf{Self-Correcting Coupled Markov Jump Processes (SC-CMJP)}$, a framework in which one modality's transition rates are functionals of the other modality's confidence score, as weighted by cross-modal attention. Furthermore, a remasking jump retracts commitments the moment cross-modal evidence turns against them. In conjunction with SC-CMJP, we introduce $\texttt{CO}_\texttt{2}\texttt{Jump}$ (Self-$\underline{\text{CO}}$rrecting $\underline{\text{CO}}$upled $\underline{\text{Jump}}$), a novel training-free single-pass sampler for joint multimodal geneneration. For training and evaluation purposes, we have created and will release three large-scale joint multimodal generation corpora: $\text{JEdit-1M}$, $\text{JMaze-200K}$, $\text{JNono-200K}$, with matching in- and out-of-distribution benchmarks. $\texttt{CO}_\texttt{2}\texttt{Jump}$ achieves best joint performance for image understanding and editing as well as visual reasoning (maze and nonogram solving). The performance of the sampler scales monotonically with the number of denoising steps, evidence that the benefits of cross-modal coupling $\textit{compound}$ across the trajectory. Project page: this https URL

AI 总结：研究针对模仿学习对分布变化敏感及安全风险问题，提出分布鲁棒且安全的模仿学习框架，利用泰勒级数模仿学习和分布鲁棒自适应控制应对不同诱导变化，在无人机案例中验证了方法有效性。

链接：https://arxiv.org/abs/2607.13436

机构：University of California Berkeley（加利福尼亚大学伯克利分校）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Ahmed Aboudonia, Naira Hovakimyan

英文摘要：Imitation learning (IL) has achieved remarkable success in complex decision-making tasks. However, its performance is highly sensitive to distribution shifts, which can pose significant safety risks. We propose a distributionally robust and safe IL framework that explicitly addresses both policy-induced and uncertainty-induced distribution shifts. Our approach develops a unified framework leveraging Taylor Series Imitation Learning (TaSIL) to mitigate policy-induced shifts and distributionally robust adaptive control to handle uncertainty-induced shifts. This architecture enables the formulation of an IL problem that optimizes performance under distributional uncertainty while systematically accounting for safety constraints. We demonstrate the effectiveness of the proposed approach on an unmanned aerial vehicle (UAV) case study where the UAV performs a task in an uncertain environment while avoiding unsafe regions.

AI 总结：研究 CLIP 潜在空间，提出基于冯·米塞斯-费舍尔分布混合的密度模型，用期望最大化算法学习，实现准确可解释的密度估计，改善长尾和分布外检测，建立几何一致的概率框架。

链接：https://arxiv.org/abs/2607.13660

机构：Tsinghua University（清华大学）； Cisco Research（思科研究院）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

作者：Zijie Yu, Gaowen Liu, Ramana Rao Kompella, Philip S. Yu, Yue Song

英文摘要：Contrastive Language-Image Pretraining (CLIP) representations form a semantic embedding space governed by cosine similarity, reflecting an intrinsic hyperspherical geometry. However, existing probabilistic interpretations typically rely on Gaussian assumptions, which fail to capture this directional and multimodal structure. We propose a principled density model for the CLIP latent space based on Mixtures of von Mises-Fisher (MovMF) distributions defined on the unit hypersphere. Using the Expectation-Maximization (EM) algorithm, we efficiently learn a probabilistic model in which each mixture component corresponds to a coherent semantic concept. This formulation yields a closed-form likelihood naturally aligned with hyperspherical geometry, enabling accurate and interpretable density estimation. Empirically, our model significantly improves long-tailed and out-of-distribution detection and provides a natural semantic decomposition, representing each embedding as a sparse probabilistic combination of interpretable concepts. These results suggest that CLIP latent space is more faithfully characterized as a hyperspherical semantic mixture rather than an isotropic Gaussian, establishing a simple and geometrically consistent probabilistic framework for modeling and understanding multimodal representations. Project page is available at this https URL.

AI 总结：研究从有向图流中恢复潜在势的问题，提出规范不变的图狄利克雷能量方法，该方法具有参数不敏感性，能保留动态范围，定位吸收边界，并通过实验验证其在点击流语料库上的优势，还将其与图神经网络联系起来。

链接：https://arxiv.org/abs/2607.13609

机构：Amirkabir University of Technology（伊朗阿米尔卡比尔理工大学）

作者：Mohammad Forouhesh

英文摘要：Recovering a latent potential from observed flow on a directed graph (a discrete Poisson problem with Dirichlet boundaries) is ill-posed, and the standard fix backfires: ridge regularization shrinks toward a gauge-meaningless origin, collapsing and reversing the recovered ordering ($+0.81\to-0.42$ rank correlation against a planted ground truth). The gauge-invariant graph Dirichlet energy removes the hazard and delivers parameter-insensitivity: the estimate is stable across four orders of magnitude in $\lambda$, whereas ridge inverts the ordering for every $\lambda>0$. We prove the reduced solve is SPD and preserves dynamic range exactly where ridge collapses it, and localize absorbing boundaries from flow alone via a Poisson residual. The $H^1$ seminorm is classical; what is new is the gauge diagnosis, the parameter-insensitivity it buys, and an ablation showing the result is robust to the extraction method. On three public clickstream corpora the gauge-invariant estimate retains $28$--$41\%$ of the interior dynamic range while ridge collapses to as little as $0.2\%$. The same gauge invariance carries into graph neural networks -- neutralizing the constant mode per layer prevents the oversmoothing that collapses a deep directed GCN -- linking this classical inverse problem to a central question in graph learning.

AI 总结：研究电网问题中图神经网络单任务微调的拓扑过拟合故障，提出MxGPS多路图变换器，通过自监督预训练和多任务微调联合训练SSE与PF，实验表明其能有效防止拓扑过拟合，以少得多参数实现拓扑无关泛化。

链接：https://arxiv.org/abs/2607.13763

作者：Charilaos Papaioannou, Ioannis Tsantilas, Dimitris Giannakakos, Vasilis Michalakopoulos, Sotiris Pelekis, Vangelis Marinakis, Arsam Aryandoust, Antonello Monti, Ricardo J. Bessa, Perdo P. Vergara, Jochen Cremer, Elissaios Sarmas

英文摘要： Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode relational structure particular to the training topologies rather than the underlying physics, causing models to fail on unseen grids despite strong in-distribution performance. To expose and address this failure mode, we introduce MxGPS (Multiplex GPS), a multiplex graph transformer that runs K task-specialised GPS branches over a shared node encoder, jointly trained on Static State Estimation (SSE) and AC Power Flow (PF) via a self-supervised pre-training and multi-task fine-tuning protocol, with a cross-branch attention module evaluated in ablation. The joint SSE+PF objective forces the shared encoder to simultaneously satisfy complementary gradient signals, preventing it from overfitting to topology-specific relational structure. Under a 3-fold sliding-window cross-validation spanning four unseen topologies (14-, 24-, 162-, and 300-bus), MxGPS attains 0% boundary violation rate (BVR) on all four zero-shot Power Flow topologies. Critically, models with substantially lower in-distribution PF error degrade by 190% to 1400% under topology shift, whereas MxGPS degrades by only 39%, an inversion that directly implicates topology overfitting as the failure mechanism rather than insufficient model capacity. With only 1.6M parameters (12x fewer than the GridFM reference baseline), MxGPS demonstrates that multi-task joint training is a principled and parameter-efficient mechanism for topology-agnostic generalisation in power grid foundation models.

AI 总结：针对图节点分类的类别不平衡问题，提出利用平衡元集评估节点重要性的方法，推导公式并开发新框架，能过滤有价值节点，构建高质量元集，实验证明该框架在缓解不平衡上具优越性。

链接：https://arxiv.org/abs/2607.13837

机构：Johns Hopkins University（约翰斯·霍普金斯大学）； Zhejiang University（浙江大学）； National University of Singapore（新加坡国立大学）； Grabtaxi Holdings Pte Ltd（Grab出租车控股私人有限公司）

作者：Nan Chen, Zemin Liu, Bryan Hooi, Bingsheng He, Jun Hu, Jia Chen

英文摘要：In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional GNNs often struggle in such scenarios, as they tend to overfit to majority classes while underrepresenting minority classes. Existing solutions, which either prioritize nodes based on class size or synthesize new nodes for minority classes, often fall short of effectively addressing this imbalance issue. This paper introduces an approach to class-imbalanced node classification by utilizing a balanced meta-set for importance measurement, where a training node is considered significant if it enhances model performance under an unbiased setting. Our method identifies important nodes that can counteract class imbalance and utilizes them for model training, allowing for fine-grained and dynamic node selection throughout the training process. We theoretically derive a formula to directly assess node importance, reducing computational overhead and providing an intuitive threshold for node selection. Guided by this metric, we develop a novel framework that filters valuable labeled, unlabeled, and synthetic nodes that enhance model performance in an unbiased context. A key advantage of this framework is its separation of the synthetic node generation process from the filtering process, ensuring compatibility with various node generation methods. Furthermore, we introduce a strategy to construct a high-quality meta-set that closely approximates the overall feature distribution, ensuring robust representation of each class. We evaluate our framework, NodeImport, across multiple datasets using popular GNN architectures, demonstrating its superiority over existing baselines. Our results highlight the flexibility and effectiveness of the framework in mitigating class imbalance, leading to improved outcomes.

AI 总结：针对深度学习模型部署难题，提出轻量级训练策略，解耦特征提取与分类器优化，预计算特征减少开销，重新设计分类器头。在多种架构和数据集上评估，显著减少训练时间，兼顾精度，还能大幅减少二氧化碳排放，提供可持续方案。

链接：https://arxiv.org/abs/2607.13043

机构：Universidade da Coruña（科鲁尼亚大学）； CITIC（中信）

作者：Daniel Vila-Cruz, Laura Morán-Fernández, Verónica Bolón-Canedo

英文摘要：Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands. We propose a lightweight training strategy that adapts normalization layers of the model to the new domain and decouples feature extraction from classifier optimization, reducing overhead by precomputing features only once. A redesigned classifier head with margin-based weighted loss further minimizes ambiguity without end-to-end backpropagation. Evaluated across four CNN architectures (ResNet18, ResNet50, MobileNet, DenseNet121), three Transformer models (ViT, Swin and DeiT) and three medical datasets (Brain Cancer MRI, BreakHis and PatchCamelyon), our approach significantly reduces the required training time with only a marginal accuracy trade-off, often matching or surpassing baseline performance. This efficiency translates to reducing CO2 by orders of magnitude, offering a practical and environmentally sustainable solution for resource-constrained clinical or prototyping environments.

AI 总结：针对大语言模型在有限数据学习中的难题，提出注意力头重新加权（AHR）方法，通过为每个注意力头学习单个标量来适应新任务，大幅减少需学习的参数，实验表明该方法在有限样本学习时优于标准基线，且权重易解释。

链接：https://arxiv.org/abs/2607.13425

作者：Tuomas Oikarinen, Zixiao Chen, Charlotte Siska, Tsui-Wei Weng, Chandan Singh, Jianfeng Gao

英文摘要：Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to struggle when faced with few samples for difficult tasks. To meet this challenge, we propose Attention Head Reweighting (AHR), a data-efficient method that adapts LLMs to new text-classification tasks by learning only a single scalar per attention head. This drastically reduces the number of parameters that need to be learned by making use of the functional specialization of individual attention heads. Experiments on diverse open-source text classification datasets show that AHR can outperform standard baselines like LoRA when learning from limited samples, despite having 200-1000x fewer trainable parameters, as our AHR only modifies ~0.0001% of the model's parameters. In addition, our learned weights are easy to interpret and can be analyzed to better understand the mechanisms and attention heads responsible for in-context learning abilities in LLMs.

AI 总结：研究神经网络可塑性度量，引入基于通用压缩理论的局部冗余，将其定义为局部模型族最坏情况冗余，证明期望平方梯度范数可作下界，实验表明该度量比现有方法更能预测下游性能并助于预训练检查点选择。

链接：https://arxiv.org/abs/2607.13432

作者：Jiaxuan Cheng

英文摘要：Plasticity -- a neural network's ability to adapt to new tasks -- is critical for continual and transfer learning. Existing measures, such as effective rank, dead neuron fraction, and weight norm, lack theoretical grounding and correlate poorly with performance on new tasks. We introduce local redundancy, an information-theoretic measure derived from universal compression theory. We define local redundancy as the worst-case redundancy of a local model family -- parameters in an infinitesimal neighborhood along gradient directions -- and show this is a principled measure of plasticity. Although local redundancy is intractable to compute exactly, we prove that the expected squared gradient norm on a synthetic memorization task provides an efficiently computable lower bound. Experiments on continual image classification and time series transfer learning demonstrate that local redundancy predicts downstream performance better than existing measures and enables pretraining checkpoint selection where validation loss plateaus.

AI 总结：针对机器学习系统模型优化，提出约束驱动的多目标工程决策框架，沿五个约束维度描述生产部署，综合文献经验收益并映射到操作约束，给出规范性决策框架及四个场景优化管道，将模型优化形式化为约束感知过程。

链接：https://arxiv.org/abs/2607.13735

机构：Indian Institute of Science（印度科学研究所）； EXL（EXL公司）

作者：Dhruv Shivkant, Saket Mohanty, Utkarsh Wadhwa

英文摘要：The rapid deployment of machine learning systems across cloud, edge, and enterprise environments has brought model optimization to the forefront of systems-engineering. Despite a rich literature spanning quantization, pruning, knowledge distillation, parameter-efficient fine-tuning (PEFT), and inference-time optimization, practitioners are often left navigating these techniques through heuristics rather than principled methodology. We argue that optimization should be formulated as a constraint-driven, multi-objective engineering decision and introduce a unified framework that characterizes any production deployment along five interacting constraint dimensions: data availability, latency budget, memory budget, accuracy tolerance, and retraining budget. Building on this taxonomy, we synthesize empirical gains reported across the research literature and map them to operational constraints rather than algorithmic categories. To ensure practical relevance, we selected these techniques by reviewing recent literature for methods that report measurable improvements against critical deployment bottlenecks. We propose a prescriptive decision framework and provide optimization pipelines for four representative industrial scenarios to illustrate it in practice. To the best of our knowledge, this work provides one of the first structured attempts to formalize model optimization as a constraint-aware, multi-objective engineering process, synthesizing quantitative evidence from the research literature.

AI 总结：该研究针对单细胞转录组数据推断基因调控网络问题，提出CoDiffGRN方法，将GRN推理转化为归纳图完成问题，引入新基准和协同进化离散扩散框架，实验表明其在新调控发现上性能优越，优于现有方法。

链接：https://arxiv.org/abs/2607.13120

机构：Peking University（北京大学）； National University of Defense Technology（国防科技大学）

作者：Jiaze Song, Runhao Zhao, Minghao Xu, Bin Cui, Wentao Zhang

英文摘要：Inferring gene regulatory networks (GRNs) from single-cell transcriptomic data is crucial for biological discovery, yet existing approaches suffer from a fundamental misalignment with real-world needs. Researchers typically seek a small set of high-confidence regulatory interactions for experimental validation, often involving previously unseen genes. However, current benchmarks rely on transductive splits with global classification metrics, while prevailing models struggle to generalize under inductive settings. To bridge this gap, we reformulate GRN inference as an inductive, ranking-centric graph completion problem and introduce \textbf{\benchmark}, a new benchmark that incorporates an inductive gene-holdout split together with knowledge graph completion metrics to better evaluate top-ranked predictions. Building on this, we propose \textbf{\method}, the first co-evolutionary discrete diffusion framework that jointly models biologically coherent discretized gene expression states and regulatory interactions for robust inductive generalization and improved top-ranked regulatory discovery. We further introduce TF-ALL Subgraph Sampling (TASS) for scalable training. Extensive experiments on {\benchmark} show that {\method} establishes new state-of-the-art performance, significantly outperforming existing methods in novel regulatory discovery, and ablation studies further verify the effectiveness of our design.

AI 总结：研究PyTorch在物理信息神经网络中计算梯度的方式，借助1-3-3-1多层感知器和特定初值问题，追踪前向传播计算图、反向遍历及图中图机制，验证伴随值并联系相关框架与积，明确其计算梯度的完整流程。

链接：https://arxiv.org/abs/2607.13042

机构：CECA, Universidade Federal de Alagoas (UFAL)（塞阿拉，阿拉戈斯联邦大学）

作者：Abdeladhim Tahimi

英文摘要： This paper traces, with explicit numerical values, how PyTorch's automatic differentiation (AD) engine computes gradients for Physics-Informed Neural Network (PINN) training -- a setting that requires two levels of differentiation: computing the physics derivative $\hat{y}'(t)=d\hat{y}/dt$ through the network, and computing parameter gradients $\nabla_\theta L$ of a loss that itself depends on $\hat{y}'(t)$. Using a 1-3-3-1 multilayer perceptron and the initial value problem $y'(t)+y(t)=0$, $y(0)=1$, we trace the complete pipeline at every node: the computational graph built during the forward pass, the reverse-mode backward traversal that computes all 22 parameter gradients in a single pass, and the graph-on-graph mechanism by which \texttt{create\_graph=True} enables correct differentiation through the physics-informed residual. Every adjoint value is verified against the hand derivations of Tahimi (2026), connecting the $P/Q$ sensitivity framework to the vector--Jacobian products used by PyTorch's autograd engine.

AI 总结：研究针对生成性分子模型评估指标不足的问题，引入受工业工作流程启发的六阶段筛选基准刺猬（HEDGEHOG），在标准化协议下评估三个模型类别的23个分子生成器，揭示了当前分子生成器难以同时满足多方面筛选的局限性。

链接：https://arxiv.org/abs/2607.13155

作者：Daria A. Ryabchenko (1,2), Pavel Gurevich (1,2), Shamil Kadyrov (1), Daria Frolova (1,2), Kseniia Fedisheva (1), Sergei A. Nikolenko (1), Alexander Shapeev (1,2), Marina A. Pak (1) ((1) Ligand Pro, Moscow, Russia, (2) Skolkovo Institute of Science and Technology, Artificial Intelligence Center, Moscow, Russia)

英文摘要：Generative molecular models can support early drug discovery by proposing new candidate compounds de novo. In practice, useful candidates must balance target-relevant activity, synthetic accessibility, physicochemical properties, and other multiparameter design constraints. However, metrics commonly used to evaluate molecular generators only weakly reflect whether the generated compounds are medicinally plausible and suitable for downstream computation. This can produce false positives in model evaluation, incorrect assumptions, and inefficient use of computational resources. We introduce HEDGEHOG, a unified six-stage filtration benchmark that is inspired by industrial hit identification workflows: (i) preprocessing; (ii) physicochemical descriptor screening; (iii) structural alerts and graph-sanity checks; (iv) synthesis feasibility; (v) docking and binding affinity estimation; and (vi) three-dimensional pose and interaction checks. We evaluate 23 molecular generators across three model classes under a standardized protocol. Across 230,000 generated molecules, only 0.65% of initial molecules survive all stages. Our results expose a central limitation of current molecular generators: molecules that appear acceptable under isolated criteria rarely satisfy medicinal chemistry, synthesis, docking, and 3D pose filters simultaneously.

AI 总结：研究大规模零售需求预测，提出在训练时对连续序列内变化施加惩罚的方法，结合多种特征评估稳定性。实验表明稳定性感知混合模型能提高预测稳定性得分，且RMSE变化小，拓展了零售预测从点误差最小化到准确性-稳定性权衡的评估视角。

链接：https://arxiv.org/abs/2607.13331

作者：Jize Li, Jiani He, Dishu Yang, Dingyan Shang, Jingjing Liu, Shiqi Huang

英文摘要：Retail demand forecasts are reused across replenishment, capacity, labor, and transportation planning cycles. Point-error objectives do not constrain abrupt movement between adjacent forecasts, while post-hoc smoothing acts only after model fitting. We ask whether a training-time penalty on consecutive within-series movement can improve horizontal forecast-path stability without materially changing point accuracy. The penalty is evaluated in a temporal-structured pipeline combining recent-demand embeddings with calendar, price, hierarchy, item, and store features. On selected M5 demand series at 1000, 3000, and 4000-series scales, the stability-aware hybrid model improves Forecast Stability Score over XGBoost by 6.91%, 6.66%, and 7.68%, respectively, while RMSE changes remain within 0.72% across three random seeds. Post-hoc exponential smoothing attains lower raw movement but incurs a larger RMSE cost; training-time regularization preserves more point accuracy and performs favorably under normalized stability. These findings extend forecast evaluation from point-error minimization toward an accuracy-stability trade-off perspective for operational retail forecasting.

AI 总结：针对银行交易异常检测传统方法的局限，本文提出可解释人工智能框架，用隔离森林模型评分，SHAP层提供解释，通过Streamlit仪表板呈现结果，经实验评估性能良好，能提升审计人员信心与决策质量，推动AI在金融环境的实际部署。

链接：https://arxiv.org/abs/2607.13469

作者：Anupa Lodhi

英文摘要：The banking sector increasingly relies on automated systems to monitor electronic transactions for signs of fraud, yet conventional rule-based approaches struggle with high false-positive rates and offer no justification for their outputs, limiting their utility for compliance teams. This paper introduces an Explainable Artificial Intelligence (XAI) framework tailored for banking transaction anomaly detection within internal audit workflows. An Isolation Forest (iForest) model performs unsupervised anomaly scoring, while a SHAP (SHapley Additive exPlanations) layer provides transaction-level, feature-attributed explanations grounded in cooperative game theory [8]. A lightweight Streamlit dashboard renders these outputs in a form accessible to audit professionals without machine learning expertise. Evaluation on a synthetic banking dataset yields 0.91 precision and 0.88 recall, outperforming three unsupervised baselines. Expert feedback confirms that feature-level explanations measurably improve auditor confidence and decision quality. The framework advances the practical deployment of accountable, transparent AI in regulated financial environments.

AI 总结：研究针对无线射频网络异常检测问题，扩展QKS模板并引入消融协议，通过多深度数据重新上传和环纠缠进行评估。结果表明DCT表示优，适度深度纠缠QKS配置强，QKS优于经典基线，提供了实用可重复的无线网络异常检测框架。

链接：https://arxiv.org/abs/2607.13897

机构：ibm_quebec（IBM魁北克）

作者：Abdallah Aaraba, Alexis Vieloszynski, Remon Polus, Ola Ahmad, Soumaya Cherkaoui

英文摘要： The broadcast nature of wireless channels exposes radio-frequency (RF) networks to anomalous and malicious transmissions, making anomaly detection a fundamental requirement for secure spectrum management. Quantum Kitchen Sinks (QKS) offer a lightweight hybrid quantum feature map suitable for near-term quantum devices, yet their behavior on structured signal data remains poorly understood. In this paper, we extend the standard QKS template with multi-depth data re-uploading and ring entanglement, and evaluate the resulting pipeline on controlled RF spectrogram anomaly detection. We introduce a validation-locked five-stage ablation protocol that systematically separates the effects of shallow architecture, re-uploading depth, episode budget, input representation, and classical readout. Across the completed benchmark, Discrete Cosine Transform (DCT) representations consistently dominate raw and Principal Component Analysis (PCA) inputs, moderate-depth entangled QKS configurations form the strongest operating regime, and QKS improves over matched classical direct-readout baselines across all evaluated representation-readout pairs on the held-out test set, with the best configuration reaching a test Area Under the Receiver Operating Characteristic curve (AUROC) of 0.8778 and a test F1 of 0.7995. The study bridges two levels of realism: real measured sub-6\,GHz cellular signals on the data side and real-device validation on the ibm_quebec Quantum Processing Unit (QPU) on the computing side, with AUROC deviations below 0.013 relative to simulation. These results provide a practical, reproducible framework for deploying QKS-based anomaly detection in wireless networks.

AI 总结：研究输入带李群作用的机器学习模型丢弃信息，定义衡量对称性的对象，通过牛顿迭代计算零纤维元素，成本低，开发相关应用并在分子性质预测等任务中测试，框架适用于经典神经网络和变分量子电路。

链接：https://arxiv.org/abs/2607.13046

机构：QodeX Quantum, Inc.（QodeX量子公司）

作者：Zachary P. Bradshaw

英文摘要：We develop a framework for the information discarded by machine learning models whose inputs carry a Lie group action. Given a representation $\pi$ of a Lie group $G$ on a space $V$ and a learned function $f\colon V \to \mathbb{R}$, we define two objects measuring the symmetry invisible to $f$. The null fiber at a point $x \in V$ is the set $N_G(f,x) = \{g \in G: f(\pi(g^{-1}) \cdot x) = f(x)\}$ of group elements whose inverse action on $x$ is undetectable by $f$. When $N_G(f,x)$ is independent of $x$, it coincides with the stabilizer $\mathrm{Stab}_G(f)$, the largest subgroup of $G$ under which $f$ is invariant. For smooth maps to $\mathbb{R}$, the preimage theorem guarantees that null fibers have dimension at least $\dim G - 1$ at generic inputs, regardless of architecture. For compact groups acting on themselves, the Peter--Weyl theorem yields a spectral characterization of both objects in terms of the Fourier coefficient matrices of $f$. We show that null fiber elements can be computed efficiently via Newton iteration on the orbit map, at a cost comparable to a few gradient evaluations. Applications to data masking, model fingerprinting, and privacy-preserving computation are developed and tested experimentally on molecular property prediction under $\mathrm{SO}(3)$ and spherical image classification under the Möbius group $\mathrm{PSL}(2, \mathbb{C})$. The framework applies uniformly to classical neural networks and variational quantum circuits.

AI 总结：研究提出定向参数分解（tPD）方法，通过引入高秩通用组件，从神经网络中仅识别处理特定感兴趣输入的组件，在玩具模型和Transformer语言模型上验证有效，能以低计算量提取子模型并对记忆序列进行手术式操作。

链接：https://arxiv.org/abs/2607.13047

作者：Antoine Vigouroux, Lee Sharkey

英文摘要：Parameter decomposition (PD) decomposes neural networks into interpretable computational components that faithfully reflect the original network's operations. However, scaling PD to large models requires vast compute, making it a costly and risky endeavor. Here we propose targeted PD (tPD), which identifies only the components that process specific inputs of interest -- from isolated prompts to large subtasks -- by introducing a high-rank catch-all component that handles all non-target data. We validate tPD on toy models and on transformer language models trained on The Pile, where it recovers reproducible, mechanistically faithful circuits. We extract a CSS-only submodel of a 4-block transformer using 7% of the FLOPs of its published decomposition, and in a 12-block transformer we surgically ablate and rewire memorized sequences, with negligible side effects on other inputs.

AI 总结：研究旨在通过能力和熟练程度建模进行知识追踪，提出PAKT框架，基于定制机制分解学生交互，设计多分支Transformer捕获知识状态，通过因果分析揭示偏差，实验证明该方法优于基线。

链接：https://arxiv.org/abs/2607.13103

机构：School of the Information Management, Wuhan University（武汉大学信息管理学院）； School of Computer Science and Artificial Intelligence, Hubei University of Technology（湖北工业大学计算机科学与人工智能学院）； Faculty of Artificial Intelligence in Education, Central China Normal University（华中师范大学人工智能教育学部）

作者：Duantengchuan Li, Yingqian Bi, Jinsong Chen, Rui Zhang, Mingwen Tong

英文摘要：Knowledge tracing (KT) aims to predict students' future performance by modeling their evolving knowledge states from historical interactions. Existing KT methods usually treat the raw interaction sequence as a unified behavioral process, overlooking the phase-specific nature of learning behaviors. Our preliminary observations show that students are more likely to correctly answer previously failed knowledge concepts after sufficient practice, suggesting a transition from ability-building to proficiency-oriented learning. Motivated by this, we propose Phase-Aware Knowledge Tracing (PAKT), a KT framework that decomposes student interactions into ability and proficiency phases based on the tailored decomposition mechanism. To effectively exploit the decomposed sequences, we design a multi-branch Transformer with a type-aware readout module to jointly capture phase-specific and holistic knowledge states. We further provide a causal analysis to reveal the confounding bias caused by entangling complex learning behaviors in phase-agnostic KT models. Extensive experiments on six public benchmarks demonstrate that our method consistently outperforms representative baselines, with a maximum AUC gain of 1.33% and an average gain of 0.82%.

AI 总结：研究针对视听导航骨干网络多年未变的问题，提出Samba，用曼巴状态编码器取代传统GRU，构建音频曼巴编码器，实验表明其泛化性能出色，能提升导航成功率，以低成本解锁更强能力，为范式演进提供途径。

链接：https://arxiv.org/abs/2607.13110

机构：School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）； Joint Research Laboratory for Embodied Intelligence, Xinjiang University（新疆大学具身智能联合研究实验室）； Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语言认知计算国际联合研究实验室）

作者：Yi Wang, Yinfeng Yu

英文摘要：Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks for audio-visual navigation have undergone no essential changes for more than five years, making them inadequate to support efficient representation of dynamic multimodal sequences. This paper proposes Samba(A Hybrid Mamba for Audio-Visual Navigation). It uses the adaptive selection-enabled Mamba State Encoder (M-SE) to replace conventional GRUs for temporal aggregation, and constructs an Audio Mamba Encoder (AME) to remedy the limitations of convolutional operators in capturing global time-frequency dependencies in spectrograms. Experiments demonstrate that Samba exhibits exceptional generalization performance when facing unheard sound sources and unseen scenes. On the Matterport3D dataset, it improves the navigation success rate (SR) by 11.3\% compared with existing state-of-the-art models, and the performance gain is even more pronounced on the Replica dataset, which features finer scene structures. Such modernized architectural reconstruction unlocks stronger embodied representation capabilities at a lower computational cost, thereby providing a highly robust technical pathway for paradigm evolution in the field of audio-visual navigation.

AI 总结：研究结构化剪枝在语言模型自由形式生成任务中存在的问题，提出ShortOPD方法，通过短到长的策略蒸馏，检测重复后缀，合理分配展开预算，有效提升压缩模型分数，减少训练时间和展开令牌，推动结构化剪枝接近可部署的生成质量。

链接：https://arxiv.org/abs/2607.13124

机构：ByteDance（字节跳动）； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）； University of Chinese Academy of Sciences（中国科学院大学）

作者：Qingyu Zhang, Qianhao Yuan, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Xiang Li, Ming Xu, Jiarui Li, Xiuyin Zhao

英文摘要：Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires. Two observations trace this gap. First, greedy \textsc{pass}@$1$ nearly vanishes after compression, yet \textsc{pass}@$k$ recovers substantially under repeated sampling: useful generations are demoted, not erased. Second, the recoverable regime fails mainly through suffix repetition. Recovery should therefore train on the compressed model's own on-policy states with dense token-level supervision, which On-Policy Distillation (OPD) provides by reusing the pre-compression model as a frozen teacher. However, long on-policy rollouts spend early recovery budget on low-information repetitive suffixes, delaying loss descent. To mitigate this waste, we propose \textbf{\shortopd}, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use. Across math, code, and open-ended generation, \shortopd\ raises the compressed model's score to about $9\times$ its unrecovered value and $1.6$--$4.4\times$ standard recovery recipes (SFT w/o KD, KD, and SeqKD), and it matches a fixed $8192$-token rollout horizon within two points using a quarter of the training time ($8.5$ vs.\ $35.9$ hours) and $71\%$ fewer rollout tokens. We hope this recipe helps move structured pruning beyond marginal gains on perplexity and multiple-choice benchmarks, a step closer to deployment-ready generation quality.

AI 总结：研究离散选择估计中表格基础模型的应用，提出编码选择集依赖性和个体异质性的重新表述方法，在酸奶扫描仪面板数据上评估，该方法在预测准确性和速度上优于分层贝叶斯估计，为基础模型应用于消费者选择问题提供原则性方法。

链接：https://arxiv.org/abs/2607.13314

机构：Leeds School of Business, University of Colorado Boulder（科罗拉多大学博尔德分校利兹商学院）

作者：Liu Liu, Dan Zhang

英文摘要：Tabular foundation models (TFMs) generate predictions on structured data via in-context learning, without task-specific estimation. We ask whether TFMs can be effectively applied to discrete choice, a central demand estimation framework in marketing and operations, and find that directly applying TFMs yields limited performance. The gap is structural: TFMs assume row-independent observations, whereas discrete choice is inherently set-valued and subject to persistent consumer preference heterogeneity. We propose a reformulation that encodes both choice-set dependence and individual heterogeneity within a row-based learning framework. Evaluated on a yogurt scanner panel, individual-level heterogeneity encoding is the dominant driver of predictive accuracy. The best reformulation outperforms hierarchical Bayesian estimation by 8\% in holdout log-likelihood and 3.6\% in hit rate, running 16 times faster, a practical advantage for large-scale demand estimation. The advantage is largest in the medium-data regime (10--40 purchase occasions per consumer), where parametric Bayesian shrinkage most distorts estimates for atypical consumers. Fine-tuning on population choice data provides additional gains for consumers with shallow purchase histories, where in-context learning has limited individual-specific signal to condition on. These results establish a principled approach for applying foundation models to consumer choice problems more broadly.

AI 总结：研究旨在解决大语言模型训练资源受限问题，提出Agora系统，通过互联网级链路的带宽高效流水线并行模型分片与多方容错集体操作相结合，实现集体训练、集体所有模型，首次展示Pluralis - 8B预训练，效率达集中式基线63%。

链接：https://arxiv.org/abs/2607.13332

作者：Gil Avraham, Violetta Shevchenko, Hadi Mohaghegh Dolatabadi, Karol Pajak, James Snewin, Harry Xi, Rodney O'Donnell, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin Hewa Koneputugodage, Shamane Siriwardhana, Alexander Long

英文摘要：Training large language models at the multi-billion to trillion parameter scale is confined to datacenters, where data-parallel (DP) and model-parallel (MP) techniques presume homogeneous accelerators, high-speed interconnects, and a single orchestrating entity. Frontier model development is thereby concentrated among the few groups able to assemble such clusters. Meanwhile, an enormous pool of compute remains unusable for training: consumer and professional GPUs that are heterogeneous, preemptible, individually owned, and connected only by the internet. We present Agora, a system that makes efficient use of this compute. Agora combines bandwidth-efficient pipeline-parallel model sharding over internet-grade links with multi-party, fault-tolerant collective operations. Each participant holds only one stage of the model, and no single party ever possesses the full weights. We term this setup Protocol Learning: it enables collectively trained, collectively owned models, opening a path to open-source frontier training with economic sustainability. This report presents the outcome of a research effort spanning communication-efficient parallelism, asynchronous optimization, and fault-tolerant systems design. It culminates in the first demonstration of its kind: Pluralis-8B, an open, permissionless pretraining run of an 8.6B-parameter model on 500B tokens of FineWeb-Edu. The model was trained over 40 days by 330 contributor nodes, predominantly consumer GPUs on internet connections, joining and leaving throughout. The run sustained ~170k tokens/s and 4.2 tokens per TFLOP of pooled compute, 63% of the efficiency of a centralized H100 baseline, and converged to within a small margin of a centralized reference run.

AI 总结：研究针对预测编码中层间路由误差依赖雅可比转置乘积的问题，提出将精确的$J^\top$分解为局部可用项的方法，恢复权重反馈修正，得到 WF-Act-PC，消除自动求导反向传播，在多个数据集上取得较好效果。

链接：https://arxiv.org/abs/2607.13380

机构：University of Alberta（阿尔伯塔大学）； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）

作者：Junlong Shen, Xingyu Li

英文摘要：Predictive Coding (PC) offers a biologically motivated alternative to backpropagation via local weight updates, yet routing error between layers still relies on an autograd Jacobian-transpose ($J^\top$) product - the last non-local operation in PC. We show that this dependency is largely avoidable. For any layer $f(x)=\mathrm{Act}(\mathrm{Norm}(L(x)))$ with frozen normalization statistics, the exact $J^\top$ factors into three locally available terms, $J^\top v = L^\top(s \odot \sigma'(z) \odot v)$, where $\sigma'$ is the activation derivative, $z$ is the pre-activation, and $s=\gamma/\sigma_{\mathrm{run}}$ is the normalization gain. Prior weight-feedback methods omitted both corrections; restoring them closes the transport gap for this layer class. Locality here holds up to three assumptions, which we state upfront: weight symmetry ($L^\top$ mirrors the forward operator, as assumed by all PC), a soft spectral-norm control that is not synapse-local, and a nearest-neighbour approximation for MaxPool. Substituting the identity into PC yields WF-Act-PC, which removes the autograd backward pass from error transport. On CIFAR-10/100 (50 epochs, 5 seeds), WF-Act-PC is the only PC method whose accuracy improves with depth, surpassing iPC - the strongest classical PC baseline - by 2.7-22.3 pp on CIFAR-10. With both methods tuned per architecture, it matches or exceeds a comparably-tuned backpropagation baseline on the deeper CIFAR-10 architectures (VGG-9: 93.57% vs. 92.43%; ResNet-18: 92.76% vs. 91.54%) and on the harder Tiny-ImageNet benchmark, while trailing tuned BP on the deeper CIFAR-100 VGG cells. Our WF-Act-PC implementation is publicly available at this https URL

AI 总结：研究大规模模型自主提升，提出顿悟式无训练后微调范式，通过修改关键模块捷径且不更新权重，针对大语言和视觉语言模型有不同实例化，实验证明有效解锁预训练网络潜力，提升性能。

链接：https://arxiv.org/abs/2607.13395

机构：School of Computer Science and Artificial Intelligence, Guangdong University of Education（广东第二师范学院计算机科学与人工智能学院）； School of Instrumentation Science and Engineering, Harbin Institute of Technology（哈尔滨工业大学仪器科学与工程学院）

作者：Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang, Feifei Zhang, Hang-Cheng Dong, Feng-Lei Fan

英文摘要：The pursuit of autonomously self-improving models has attracted growing interest in the era of large-scale foundation models. Drawing inspiration from the concept of "enlightenment" or "aha moment" in human brain, we hypothesize that large models exhibit an analogous enlightenment phenomenon-a latent capacity for sudden capability boost. Then, we propose Enlightenment, a novel training-free post-tuning paradigm for large-scale models. Our approach modifies shortcuts for key modules/layers without weight updates, while existing training-free ones predominantly manipulate attention weights. We introduce two architecture-specific instantiations: i) For large language models, we propose attention head-mixing shortcuts that recalibrate attention weights by linking the initial attention head's output to all other target heads, modulated by an adaptive scaling factor initialization strategy. ii) For vision-language models, we apply a lightweight scalar-modulated factor to residual connections in the decoder layers, regulating information flow. Extensive experiments show that Enlightenment efficiently unlocks the latent potential of pre-trained networks, yielding remarkable performance improvements across diverse benchmarks and models.

AI 总结：本文针对自动化模拟电路拓扑设计难题，提出EXPLORE框架，集成模拟器引导蒙特卡罗树搜索与基于变压器的解码，利用语言模型先验优化搜索，在6组件基准测试中显著提升成功率、降低均方误差，推动LLM驱动设计自动化。

链接：https://arxiv.org/abs/2607.13416

机构：Duke University（杜克大学）； MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）； IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）

作者：Guanglei Zhou, Chen-Chia Chang, Yikang Shen, Jonathan Ku, Isaac Jacobson, Jingyu Pan, Yiran Chen, Xin Zhang

英文摘要： Automating analog circuit topology design is essential to reduce the extensive manual effort required to meet increasingly diverse and customized application demands. Recent advances have applied sequence-to-sequence fine-tuning on pretrained language models to directly generate circuit topologies from user specifications in a single pass. However, these one-shot generation methods failed to generate complex circuits due to their exponentially growing search spaces and limited training datasets. In this paper, we present EXPLORE, a search-enhanced framework that integrates simulator-guided Monte Carlo Tree Search (MCTS) with transformer-based decoding to enable test-time scaling for analog topology generation. By leveraging language-model priors and bypassing high-confidence structural tokens, EXPLORE allocates expensive simulator budget primarily toward topology-altering decisions during search. On a 6-component benchmark at a tight tolerance of 0.01, EXPLORE raises the success rate from 12% for one-shot generation and 33% for a sampling-and-filter baseline to 65%, and lowers MSE by over 20% relative to sampling-and-filter under the same search budget. These results establish EXPLORE as the first framework to integrate structured test-time search with LM decoding for analog topology generation, and a practical step toward scaling LLM-driven design automation.

AI 总结：研究首页营销板块推荐中访问习惯干扰问题，提出OrDA框架，用双塔结构、门控分配层、正交正则化及因果干预净化兴趣信号，有效消除访问习惯偏差，提升预测准确性和用户点击率。

链接：https://arxiv.org/abs/2607.13420

机构：Ant Group（蚂蚁集团）

作者：Lingxiao Zhang, Xiaobo Li, Tao Xu

英文摘要：Clicks on homepage marketing blocks are driven by a dual-mechanism of content interest and access habits. However, habitual clicks often create Pseudo-Positives in marketing slots, where position advantage masks mediocre content quality, leading to biased recommendation ecosystems. We propose a framework called Orthogonal Disentanglement of Access habits (OrDA) to purify interest signals. OrDA utilizes a dual-tower structure with a gated allocation layer to adaptively route features and minimize interference. To ensure rigorous separation, we employ orthogonal regularization to constrain the latent interest and habit manifolds to be geometrically perpendicular. OrDA performs causal intervention (do-calculus) during inference to rank items solely by purified interest scores. Empirical online evaluations on large-scale datasets demonstrate that OrDA effectively eliminates access-habit bias, outperforming state-of-the-art methods in predictive accuracy. Online AB test 5.64% shows user click-through rates (UCTR) improvement on the Zhima homepage marketing block, Zhima rent-floor recommendation.

AI 总结：研究在违反真实标签假设时温度缩放的校准特性及与模型规模的关系，用CIFAR-10H和ChaosNLI数据集评估，发现温度缩放校准硬标签不如直接校准软标签，差距随模型规模在部分领域增长，多类保序回归也有类似结论，揭示相关校准协议问题。

链接：https://arxiv.org/abs/2607.13423

机构：Faculty of Computing and Mathematical Sciences, University of Mines and Technology (UMaT)（矿业与技术大学（UMaT）计算与数学科学学院）； BlackMatrix AI Research（黑矩阵人工智能研究）

作者：Wisdom Dogah

英文摘要：Temperature scaling is the dominant post-hoc calibration method in modern deep learning. Its theoretical justification rests on an assumption that is rarely stated explicitly: that ground-truth labels are one-hot and deterministic. In practice, labels are frequently soft, crowd-sourced, or genuinely distributional, reflecting real disagreement among human annotators rather than annotation noise. We study whether temperature scaling retains its calibration properties when this assumption is violated, and whether any resulting degradation depends on model scale. Using CIFAR-10H and ChaosNLI, two publicly available datasets with human-annotated soft label distributions, we evaluate three model scales per modality under both hard one-hot and soft distributional label targets. Across all nine configurations we find a positive soft-label calibration gap: temperature scaling calibrated on hard labels consistently underperforms an oracle calibrated directly on soft labels, with Brier Score gaps ranging from 0.002 to 0.134. The gap grows monotonically with model scale in the vision domain and on the SNLI-derived split of ChaosNLI, and is substantially larger in the language domain (mean gap 0.079) than in vision (mean gap 0.003). A scale-ordering reversal on the MNLI-derived split remains after matched-domain training; we treat it as inconclusive for the scale hypothesis and attribute it primarily to near-chance accuracy on that split. As a second post-hoc baseline, multiclass isotonic regression yields the same qualitative conclusion: positive soft-label gaps in all nine configurations, and larger gaps in language than in vision. These findings suggest that calibration protocols built on majority-vote labels systematically misstate model reliability wherever label ambiguity is structural, with direct consequences for deployment in safety-critical settings.

AI 总结：研究正无标记学习问题，基于SAR-PU倾向加权框架提出PUe框架，运用归一化倾向得分和NIPW，有归一化逆概率加权风险公式等贡献，在多个数据集实验中，在非均匀标签分布下优于多个PU基线。

链接：https://arxiv.org/abs/2607.13428

机构：Huawei Noah’s Ark Lab（华为诺亚方舟实验室）

作者：Xutao Wang, Hanting Chen, Tianyu Guo, Yunhe Wang

英文摘要：Positive-Unlabeled (PU) learning aims to achieve high-accuracy binary classification with limited labeled positive examples and numerous unlabeled ones. Existing cost-sensitive-based methods often rely on strong assumptions that examples with an observed positive label were selected entirely at random. In fact, the uneven distribution of labels is prevalent in real-world PU problems, indicating that most actual positive and unlabeled data are subject to selection bias. Building on the SAR-PU propensity-weighted framework of Bekker et al., we study a PU learning enhancement (PUe) framework using normalized propensity scores and normalized inverse probability weighting (NIPW). PUe's main contributions are a normalized inverse-probability-weighted PU risk formulation; additional theoretical analyses of normalized sample-weight error and common PU estimators under biased labeling; regularized deep propensity-score estimation; integration with modern cost-sensitive PU methods; and support for selectively labeled negative classes. Experiments on MNIST, CIFAR-10, and ADNI demonstrate improvements over several PU baselines under non-uniform label distributions.

AI 总结：研究循环变换器中深度缩放问题，提出DeepLoop方法，通过控制访问对齐系数形式化绑定深度效应，保持特定架构并设置参数，在不同规模GPT风格模型上实验，结果显示稳定循环深度需考虑参数访问的残差缩放规则。

链接：https://arxiv.org/abs/2607.13491

机构： Princeton University（普林斯顿大学）； University of California Los Angeles（加利福尼亚大学洛杉矶分校）

作者：Shuzhen Li, Yifan Zhang, Jiacheng Guo, Quanquan Gu, Mengdi Wang

英文摘要：Looped Transformers scale sequential computation by applying a compact stack of physical blocks for multiple rounds, increasing unrolled depth without increasing stored parameters. This reuse changes the residual-scaling problem: in an untied Transformer, each residual branch receives and applies its own parameter update, whereas in a looped Transformer one shared update aggregates gradients from repeated visits and is read back by those same visits in the next linearized forward pass. We formalize this tied-depth effect through a first-order perturbation bound controlled by a visit-alignment coefficient $\kappa_R$. The bound recovers the DeepNorm exponent when visits decorrelate, but in the conservative aligned regime it requires the exponent to increase from $1/4$ to $1/2$ as loop count grows at fixed physical depth. The resulting method, \textbf{DeepLoop}, keeps the Post-LN DeepNorm architecture and sets $\alpha=(2N)^{1/2}$ and $\beta=(8N)^{-1/2}$ for unrolled depth $N$. On GPT-style looped language models at GPT-2 small and GPT-2 medium scale, DeepLoop is neutral when no physical block is revisited and improves validation loss and downstream accuracy once recurrent depth is activated. These results show that stable recurrent depth requires residual scaling rules that account for parameter visits, not only nominal layer count.

AI 总结：研究旨在量化图模型中节点群体间方向性影响，提出基于图模型的结构化反事实干预框架，训练邻居影响模型并定义CDS，通过实验验证该方法能有效恢复方向性影响，对混杂信号有鲁棒性，在生物数据上有合理一致的相互作用。

链接：https://arxiv.org/abs/2607.13508

机构：University of Houston（休斯顿大学）

作者：Humaira Anzum, Md Ishtyaq Mahmud, Jagan Mohan Reddy Dwarampudi, Tania Banerjee

英文摘要：Quantifying directional influence between node populations is a fundamental problem in graph-based modeling, particularly in spatial biological systems where cell-cell interactions shape functional outcomes. Existing approaches based on attention, attribution, or correlation capture associations but do not provide a principled framework for evaluating directional effects under controlled perturbations. We introduce a framework for structured counterfactual interventions in graph-based models to estimate directional influence between node types. Our approach trains a Neighbor Influence Model (NIM) to predict node states from local neighborhoods and applies constrained interventions that modify neighborhood composition while preserving key spatial and structural properties. We define the Counterfactual Directionality Score (CDS), which measures the change in predicted node state induced by targeted perturbations, and provide a theoretical interpretation of CDS as a finite-difference measure of local intervention sensitivity. To obtain valid uncertainty estimates, we introduce a core-level bootstrap procedure that accounts for dependencies within spatial samples. Experiments on synthetic spatial graphs with known directional structure show that CDS recovers directional influence, remains well calibrated under null conditions, and is robust to confounding signals, while preliminary results on spatial transcriptomics data reveal biologically plausible and consistent interactions across tissue cores.

AI 总结：研究提出ExTernD方法，将大语言模型权重矩阵因式分解，扩展内部秩纠正量化误差，残差随秩单调递减可逼近bf16精度。该方法内存、计算和因子稀疏性可连续调整，在多个模型上匹配或接近Q4_K/Q5_K精度。

链接：https://arxiv.org/abs/2607.13511

作者：Chethan Reddy G.P

英文摘要：We introduce ExTernD (Expanded-rank Ternary Decomposition), a post-training factorization of each LLM weight matrix $A \in \mathbb{R}^{m \times n}$ into $A \approx B \mathrm{diag}(D) C$ with ternary factors $B \in \{-1,0,+1\}^{m \times k}$, $C \in \{-1,0,+1\}^{k \times n}$ and a real scale vector $D \in \mathbb{R}^k$. The inner rank $k = \mu \min(m,n)$ is deliberately expanded beyond full rank ($\mu > 1$), so that components past full rank correct the quantization error of earlier ones. We prove the residual decreases monotonically in $k$ and can be driven below any $\varepsilon > 0$: ExTernD approaches bf16 accuracy arbitrarily closely, which no ternary scheme with a fixed plane count can do. Memory and compute scale continuously with $\mu$, and factor sparsity continuously with a threshold $\tau$, so an accuracy target is hit exactly rather than rounded to the next bit-width. ExTernD matches Q4_K's per-matrix accuracy at 5.2-5.5 effective bpw (5.1-5.5 with importance weighting) on Gemma-4-E2B and Qwen3.5-4B, and a full Qwen3.5-4B conversion at $\mu = 3$ reaches 10.10 wikitext-2 perplexity against 9.78 for bf16 (+3.2%), placing it near the Q4_K/Q5_K accuracy band at ~5.7 effective bpw.

AI 总结：研究JEPA世界模型，通过将四个正则化器组织成层次结构，证明选择抗坍缩正则化器决定训练目标是否为有效AIF变分自由能，在特定条件下SIGReg有优势，还扩展对应关系并确定未计算的AIF项。

链接：https://arxiv.org/abs/2607.13612

机构：Université Paris-Saclay, CEA, List（巴黎萨克雷大学，法国国家科学研究中心，List研究所）； Computer Vision Center Barcelona（巴塞罗那计算机视觉中心）

作者：Fabio Arnez, Alexandra Gomez-Villa

英文摘要： Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models, yet they are usually justified by empirical performance rather than a normative principle. We show that the choice of anti-collapse regulariser determines whether a JEPA's training objective, a prediction loss plus a weighted embedding regulariser, is a valid Active Inference (AIF) variational free energy. We organise four non-contrastive regularisers (VICReg, LogDet, PairDist, and SIGReg) into an entropy-estimator hierarchy indexed by a prior-miscalibration gap, and show that the gap's sign, whether the estimator bounds the latent entropy from above or below, decides whether the AIF surprise bound survives: VICReg and LogDet are unsafe upper bounds, PairDist a safe lower bound, and SIGReg eliminates the gap. We then prove a correspondence theorem: under the standard constant-noise encoder model and successful SIGReg enforcement (isotropic-Gaussian embeddings), the gap vanishes, the objective becomes an exact information bottleneck, the surprise bound is preserved, and the latent goal cost becomes an exact proxy for AIF pragmatic value, whereas VICReg leaves an irreducible second-order anisotropy term. We extend the correspondence to multi-step expected free energy, ensemble epistemic value, and a learned-policy regime, and we identify the one AIF term no current JEPA world model computes: the state-epistemic value, a future-state coverage signal. The predictions differ in kind, not degree, and are stated here as theoretical consequences left for empirical test in separate work; full proofs are in Appendix A, and the algebraic core of every result is machine-verified in Lean 4 (Appendix D).

AI 总结：研究针对质心神经网络训练效率低的问题，提出FastCentNN加速变体。核心方法是引入基于epoch总质心移动的早期分裂策略作训练熵代理，支持不同移动阈值。主要贡献是在保持聚类质量时减少运行时间，为CentNN提供实用高效替代方案。

链接：https://arxiv.org/abs/2607.13613

作者：Le-Anh Tran

英文摘要：Centroid neural network (CentNN) is an unsupervised competitive learning algorithm in which centroid splitting is triggered only after strict local stabilization, often leading to prolonged low-movement training phases before model expansion. This report proposes FastCentNN, an accelerated variant that addresses this inefficiency by introducing an early splitting strategy based on the total centroid movement per epoch, which serves as a training entropy proxy. As a result, FastCentNN reduces unnecessary reassignment epochs while preserving the original winner-loser learning dynamics. FastCentNN supports both absolute and stage-relative movement thresholds, allowing the splitting criterion to remain either fixed or adaptive throughout training. Experiments on some benchmark datasets show that FastCentNN consistently achieves clustering quality comparable to CentNN while reducing runtime by up to 16% on synthetic 2D datasets and about 5% on high-dimensional datasets. FastCentNN therefore provides a practical and efficient drop-in replacement for CentNN, retaining its online adaptive learning behavior while offering a simple and interpretable speed-stability trade-off through configurable splitting thresholds.

AI 总结：研究神经网络海森谱与数据的关系，推导线性网络海森矩阵特征值，发现分类任务中解的锐度与样本类别比例有关，经实验验证预测并分析相关影响，结论适用于更实际学习设置。

链接：https://arxiv.org/abs/2607.13631

作者：Jasraj Singh, Enea Monzio Compagnoni, Antonio Orvieto

英文摘要：The Hessian matrix is an important quantity of interest when it comes to studying the loss landscape and optimization dynamics in deep learning, as well as designing measures of generalization, second-order learning algorithms, etc. Prior works have focused on empirical results or pursued a theoretical treatment under overly simplified settings. In this work, we derive the eigenvalues of the Hessian of linear networks with arbitrary widths and depths, and datasets with an arbitrary number of samples, features, and labels. Importantly, for classification tasks with MSE loss, we identify that the sharpness of the solution is directly related to the maximum proportion of samples belonging to any class. We empirically validate our predictions and systematically analyze the effects of shedding the impractical assumptions one at a time, as well as incorporating nonlinearities. We observe that our predictions are considerably robust in most cases, allowing us to extend our conclusions to more practical learning setups.

AI 总结：研究针对优化含可控微观结构的可持续材料需多尺度模拟及数据量大的问题，提出用超网络对混合物理-数据替代模型依微观结构变量条件设定的方法，实现多尺度模拟，优化圆盘降低应力，还能依制造变量设定网络，加速可持续材料和结构开发。

链接：https://arxiv.org/abs/2607.13688

作者：J. Storm, I.B.C.M. Rocha, S. Schyck, K. Masania, F.P. van der Meer

英文摘要：Emerging sustainable materials increasingly rely on engineered hierarchy and microstructure to achieve control of their properties and mechanical behavior. Optimizing these materials with controllable microstructures requires efficient multiscale simulations. Data-driven surrogate models for the microscale can accelerate multiscale simulations, but require large amounts of data even for a fixed microstructure. When a range of microstructures is considered, as is the case in multiscale optimization, even more data is needed to train a surrogate. To overcome this challenge, we condition a hybrid physics-data surrogate on microstructural variables using a hypernetwork. This approach enables accurate predictions of multiscale mechanical behavior for a mycelium-woodchip composite material, even when trained on small datasets. The conditioned surrogate makes multiscale simulations of functionally graded structures tractable, and we validate it against a full FE^2 simulation. We optimize a graded multiscale disk, and reduce the peak stress by 42% compared to one with a random microstructure. Then, we go one step further, conditioning the network directly on manufacturing variables that can have a complex influence on the microstructure. This is a practical route to engineer the microscale for desired macroscale behavior. This contribution highlights the benefits of microarchitectured structures and demonstrates how conditioned surrogate models enable their multiscale optimization, which will accelerate the development and design of future sustainable materials and structures.

AI 总结：研究将条件可逆神经网络用于多旋翼控制，通过有理二次样条耦合等方法学习概率逆动力学模型，开环再现效果良好，闭环场景中位置RMSE与INDI匹配，分析出主要故障机制。

链接：https://arxiv.org/abs/2607.13703

机构：Helmut Schmidt University（赫尔穆特·施密特大学）； University of the Bundeswehr Munich（慕尼黑联邦国防军大学）

作者：Christian Wittke, Stephan Myschik, Oliver Niggemann

英文摘要：We investigate conditional invertible neural networks (cINNs) as probabilistic inverse-dynamics models for multirotor control. For a planar X8 coaxial multicopter, we learn $p(u \mid s_t, c_t)$ from an incremental nonlinear dynamic inversion (INDI) teacher using rational-quadratic spline coupling and invertible linear mixing. Open-loop reproduction reaches $R^2 = 0.944$, mean CRPS 0.0915, and log-probability-error correlation $\rho = -0.60$. Over 15 closed-loop scenarios, position RMSE matches INDI (9.7 vs. 9.5 m), with 47 percent tracking acceptably; failures separate into attitude divergence under aggressive steps and phase lag under high-frequency references, isolating command bandwidth and data coverage as dominant failure mechanisms.

AI 总结：针对量子化学低数据和资源受限情况，提出拓扑对齐归纳偏差，用于分子性质预测。体现在变分量子电路Iso-QGNN和经典消息传递模型Iso-CGNN中，经QM9基准测试，参数高效，性能良好，表明该偏差是QM9规模驱动参数效率的关键，对量子机器学习基准测试有影响。

链接：https://arxiv.org/abs/2607.13737

作者：James T. Pegg, Hubert Okadome Valencia, Ronin Wu

英文摘要：For low-data and resource-constrained regimes typical of quantum chemistry, parameter-efficient learning is a key objective. Here, we propose a topology-aligned inductive bias in which the model architecture mirrors the molecular bond graph: atoms map to a fixed register of computational units, and bonds determine which pairs interact through shared learnable parameters. This principle is instantiated in two architectures: a variational quantum circuit (Iso-QGNN), and a parameter-matched classical message-passing model (Iso-CGNN). The models are benchmarked on HOMO-LUMO and dipole moment binary classification tasks over the QM9 benchmark. With 64 trainable parameters, the implementations achieve test AUCs of approximately 0.88 (quantum) and 0.91 (classical) on the gap task, and close to 0.78 (both) on the dipole task. The models reach 90% of asymptotic performance within about 250 training molecules and gradient norms remain stable throughout training. These results indicate that the topology-aligned inductive bias is the active ingredient driving parameter efficiency at QM9 scale, with implications for matched-baseline benchmarking in quantum machine learning.

AI 总结：利用CMS 2015年D期公开数据，在单Z\(\rightarrow\ell^+\ell^-\)末态通过提取运动学可观测量降维成特征向量，用神经样条流模拟背景和信号密度，构建检验统计量进行暗物质搜索，给出不同媒介子的信号强度参数上限。

链接：https://arxiv.org/abs/2607.13771

机构：VIT-AP University（VIT-AP大学）； Mohan Babu University（莫汉·巴布大学）

作者：Hitesh Rasineni (1), Bhavishya Chebrolu (2) ((1) VIT-AP University, Amaravati, India, (2) Mohan Babu University, Tirupati, India)

英文摘要：We report a search for dark matter (DM) produced in association with a leptonically decaying \(Z\) boson at \(\sqrt{s}=13\) TeV using CMS Run 2015D open data corresponding to an integrated luminosity of \(2.32\,\mathrm{fb}^{-1}\) together with simplified-model Monte Carlo simulation. Events are selected in the mono-\(Z\rightarrow\ell^+\ell^-\) final state in both the \(\mu\mu\) and \(ee\) channels. Forty kinematic observables are extracted from MINIAOD and MINIAODSIM, cleaned with physics-motivated selections, and reduced to a 37-dimensional feature vector. Five Neural Spline Flows are trained independently to model Standard Model background and mediator-specific DM signal densities. The per-event test statistic is constructed from the log-likelihood ratio between the signal and background density estimates, providing sensitivity across the full kinematic phase space without requiring a hard upper \(\mathrm{MET}\) threshold. A simultaneous profile-likelihood fit combining the two channels yields observed (expected) 95\% confidence level upper limits on the signal-strength parameter of \(\mu<0.0177\) (\(0.0018\)) for the scalar mediator, \(\mu<0.0362\) (\(0.0039\)) for the vector mediator, and \(\mu<0.0498\) (\(0.0069\)) for the axial-vector mediator. The observed limits are weaker than expected because of a residual high-\(\mathrm{MET}\) background-modeling discrepancy rather than evidence for a DM signal. To our knowledge, this is the first application of Neural Spline Flow likelihood-ratio scoring to a mono-\(Z\) dark matter search using CMS Run 2015D open data simultaneously in the \(\mu\mu\) and \(ee\) channels.

AI 总结：研究决策树中无关条件删除问题，基于二元分裂使类比例反向移动的结构事实，提出结构IRC删除框架，通过评估预测可靠性诊断相关性，选择性删除无关条件，实现规则显著简化且不牺牲原树可靠性。

链接：https://arxiv.org/abs/2607.13874

作者：Jung-Sik Hong, Jeongeon Lee, Min Kyu Sim, Sangheum Hwang

英文摘要：Decision trees generate interpretable if--then rules, yet they contain irrelevant conditions (IRCs). These IRCs arise from the structural mechanism of tree splitting and persist even in modern optimal sparse tree induction algorithms. Existing IRC deletion methods overlook this structural mechanism; therefore, they either preserve the original tree too loosely to remain reliable, or too strictly to achieve meaningful simplification. This study provides theoretical foundations for reliable IRC deletion by establishing theorems and propositions related to the underlying IRC mechanism. The key finding is that a binary split shifts class proportions in opposite directions relative to the parent. Specifically, an increase in the class-1 proportion along one branch necessitates an increase in the class-0 proportion along its sibling, thereby generating a C1-link and a C0-link. Based on this structural fact, we propose a structural IRC deletion framework. Relative to each leaf, links that increase the leaf-class proportion are matched, whereas links that increase the proportion of the opposite leaf-class are mismatched. These mismatched links are flagged as structurally suspicious IRC candidates. Rather than deleting them outright, the framework rigorously diagnoses their relevance by assessing prediction reliability. It selectively deletes conditions that are structurally and empirically irrelevant, while strictly protecting those whose deletion would reduce the rule's reliability. Experimental results confirm that the proposed framework achieves substantial rule simplification without sacrificing the reliability of the original tree.

AI 总结：针对脑肿瘤进化预测和治疗计划难题，提出人工智能增强自适应数字孪生框架，集成多种模型与方法。实验表明该框架能有效提升预测准确性，降低肿瘤负荷，为患者特异性治疗优化提供统一框架，奠定向现实治疗计划转化基础。

链接：https://arxiv.org/abs/2607.13877

机构：Florida Institute of Technology（佛罗里达理工学院）； Department of Mathematics and Systems Engineering（数学与系统工程系）

作者：Wenxi Liu, Michael Trimboli, Xianqi Li

英文摘要： Brain tumor progression exhibits spatially heterogeneous growth, patient-specific treatment response, and complex interactions with surrounding anatomy, making accurate long-term prediction challenging. We propose an AI-augmented adaptive digital twin (DT) framework for brain tumor evolution prediction and treatment scheduling. The framework integrates an interpretable reaction--diffusion (RD) model, a 3D residual learning module for model-form correction, patient-specific DT updating during recursive rollout, and model predictive control (MPC) for constrained chemotherapy and radiotherapy scheduling. Experiments on 387 synthetic tumor trajectories with 120-step evolution show that the baseline RD model captures tumor location and overall temporal behavior but underestimates heterogeneous tumor burden during long-horizon prediction. Hybrid RD--residual modeling reduces masked voxel-wise mean squared error by 84.3% and increases Dice overlap by 43.5% relative to the RD baseline under dense simulated observations. Online DT updating further reduces mean squared error by 45.9% and improves Dice overlap by 9.6% compared with the non-updated hybrid model. In MPC-based scheduling simulations, the updated DT controller reduces final tumor burden by 22.4% relative to a fixed treatment schedule under the terminal-burden objective. Together, these results demonstrate a unified framework for patient-specific initialization, mechanistic modeling, adaptive learning, and constrained treatment optimization. Although validated using patient-data-informed synthetic trajectories rather than clinical longitudinal data, the proposed framework establishes a foundation for future translation to real-world adaptive treatment planning.

AI 总结：针对数据稀缺雷达应用中多目标检测跟踪难题，PiVoT通过联合推断目标多方面信息，无需外部聚类或检测器，利用变分推断创新实现快速抗杂波跟踪，实验证明其在多方面性能出色，优于现有贝叶斯跟踪器。

链接：https://arxiv.org/abs/2607.13891

机构：Institute for Imaging, Data and Communications (IDCOM), University of Edinburgh（爱丁堡大学成像、数据与通信研究所（IDCOM））； Department of Engineering, University of Cambridge（剑桥大学工程系）； School of Mathematics, University of Edinburgh（爱丁堡大学数学学院）

作者：Runze Gan, Qing Li, Simon J. Godsill, Mike E. Davies, James R. Hopgood

英文摘要：Multi-object detection and tracking from noisy point clouds remain challenging in many data-scarce radar applications. Current Bayesian trackers based on Poisson measurement models offer a training-free solution but struggle to achieve accuracy and efficiency under severe clutter, large object populations, and full-resolution Doppler point clouds. We address this with PiVoT, a fast, clutter-resilient multi-object tracker for both positional and Doppler measurements. PiVoT performs end-to-end detection and tracking of a large and time-varying number of objects without external clustering or detectors, through joint inference of object states, shapes, existence probabilities, data association, and measurement rates. Its efficiency is driven by several variational inference innovations, such as theoretically justified birth pruning, quadratic-to-linear complexity reductions for exact updates, and a computationally efficient Doppler Poisson model. Experiments show that PiVoT substantially outperforms existing Bayesian trackers in challenging scenes, while also demonstrating exceptional scalability to a thousand objects, robustness to clutter visually inseparable from objects, and real-time operation on full-scale modern automotive radar datasets, where it attains performance comparable to a deep-learning detection benchmark as a training-free joint detector and tracker.

AI 总结：研究针对金融序列建模，提出VAIOM这一仅解码器的Transformer。它将输入表示与输出似然分离，采用混合连续输入模型结合多种目标与监督。实验表明其在测试中优于LightGBM基线，验证了连续输入等方法的有效性，提升了回报似然。

链接：https://arxiv.org/abs/2607.13929

作者：Yiming Ma, Xinyu Chen

英文摘要：Financial observations are continuous, heterogeneous, and noisy, whereas decoder-only next-token models are usually built around discrete symbolic inputs. We introduce Vector-Input Autoregressive Inference for Ordinal-Return Modeling (VAIOM), a decoder-only Transformer for probabilistic next-return modeling on one-hour foreign-exchange bars. VAIOM separates input representation from output likelihood: continuous multivariate financial-event vectors preserve numerical structure at the input, while a categorical distribution over the next volatility-normalized return bucket supports cross-entropy training and likelihood evaluation. The selected 0.9M Hybrid Continuous Input model combines continuous event features with categorical asset metadata, a Mixture-of-Market-States return head, Gap, volatility-regime, and Ordinal auxiliary objectives, and full-sequence supervision. Models and preprocessing are fit using pre-2024 Train data; models are selected on 2024H2 Validation and evaluated without refitting on two 2025 Test periods. Across three independent training seeds, every model outperforms fixed single-bar LightGBM baseline in both Test halves. For the canonical checkpoint, paired gains over LightGBM are 0.029 and 0.043 bits per event. Validation experiments show that continuous input improves over discrete-token input under the same categorical return objective, full-sequence supervision improves over last-position training, and auxiliary representation shaping together with a mixture-structured return head improves return likelihood in controlled comparisons. A supporting capacity study finds that the smallest evaluated complete architecture rung achieves the strongest Validation likelihood on the present corpus.

AI 总结：研究利用生物声学数据中心的元数据，将位置、时间等元数据作为辅助监督信号，引入MetaPerch基础模型，提升物种识别性能，还对9种元数据源在17个数据集上的效果做了实证研究。

链接：https://arxiv.org/abs/2607.14072

作者：Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer

英文摘要： Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the form of recording metadata readily available within these community-driven data hubs. In this work, we explore the use of metadata -- such as location and time -- as auxiliary supervision signals, allowing the model to leverage species-metadata correlations in its learned representation. Auxiliary metadata losses provide additional information beyond vocalizations alone that can encourage a richer, more robust representation that generalizes better to species distribution and acoustic domain shifts -- important challenges for deployment in real-world passive acoustic monitoring (PAM) settings. We introduce MetaPerch, a new foundation model that achieves strong species identification performance across multiple challenging domains and present an extensive empirical study of the effects of 9 diverse metadata sources on 17 bioacoustic datasets.