机器学习学术速递[7.2]

AI 总结：本文证明三种流行的语言模型推理训练方法（GRPO、Dr. GRPO、DAPO）本质上是对组标准差的不同操作，并揭示了标准差在训练更新中的核心作用。

链接：https://arxiv.org/abs/2607.00152

机构：University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

作者：Yong Yi Bay, Kathleen A. Yearick

英文摘要：Three of the most popular methods for training language models to reason look like three different tricks. They are not. All three adjust a single number: standard deviation, reflecting how much a prompt's sampled answers disagree. When such a model is trained, it answers each problem many times, and an automatic checker marks every answer right or wrong. The standard deviation of those marks measures the disagreement: largest when the answers split evenly between right and wrong, and zero when they all agree. Group Relative Policy Optimization (GRPO) divides by this number, GRPO Done Right (Dr. GRPO) drops the division, and Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) discards the groups where it is zero. Each is presented as its own fix, yet this paper proves they are three settings of one dial. That dial is not cosmetic: for right-or-wrong rewards, the disagreement is exactly the size of the training update, the group-standard-deviation identity. A split group teaches the most, while a unanimous group teaches nothing and falls silent. The same result says which problems deserve the most weight and how many tries each one needs. This paper confirms the intuition on a large real difficulty dataset (Big-Math) and in a controlled training run. What looks like a harmless normalization step is the dial that decides where learning happens and how strongly.

AI 总结：提出进化神经架构搜索框架EVOTS，通过模块化基因组表示和修复机制自动发现任务自适应的Transformer类架构，在ETT数据集多变量预测中达到竞争性性能。

链接：https://arxiv.org/abs/2607.00154

机构：University of North Carolina Wilmington（北卡罗来纳大学威尔明顿分校）

作者：AbdElRahman ElSaid, Damir Pulatov

英文摘要：Evolutionary neural architecture design for multivariate time-series forecasting remains underexplored, with most approaches relying on fixed Transformer architectures despite substantial variation across tasks and forecasting settings. This paper introduces an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for time-series forecasting (EVOTS). Architectures are encoded using a modular genome representation that enables flexible composition of attention, feed-forward, and projection components, while a repair mechanism enforces structural validity throughout the evolutionary process. This formulation allows effective exploration of a diverse architecture space without relying on hand-crafted design rules. The proposed approach is evaluated on four benchmark datasets from the ETT family (ETTh1, ETTh2, ETTm1, and ETTm2) under multiple forecasting settings, including univariate-to-univariate, multivariate-to-univariate, and multivariate-to-multivariate prediction, with horizons of 96, 192, 336, and 720. In the multivariate-to-multivariate setting, the evolved architectures achieve competitive and, in several cases, improved mean squared error relative to a strong Transformer-based baseline. Additional analyses examine performance differences across forecasting settings and report wall-clock training time to provide a coarse indication of computational cost. Overall, the results demonstrate that evolutionary search can effectively discover flexible and high-performing Transformer-like architectures for multivariate time-series forecasting within practical runtime constraints.

AI 总结：提出分数阶傅里叶专家混合适配器，通过可学习的分数阶在空间域与傅里叶域间连续插值，使每个低秩更新位于最紧凑的域，专家自然去相关，减少干扰并提升多任务组合性能。

链接：https://arxiv.org/abs/2607.00162

机构：University of California, Irvine（加州大学尔湾分校）； University of Washington（华盛顿大学）

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

英文摘要： Parameter-efficient fine-tuning (PEFT) reparameterizes weight updates in a fixed basis: low-rank adapters operate in the spatial domain, while a recent line of spectral methods operates in a fixed Fourier domain. We argue that the choice of domain is itself a design degree of freedom that should be learned, and that no single basis is optimal across tasks, layers, or tokens. We introduce Fractional-Fourier Mixture of Experts, a mixture-of-experts adapter in which every expert carries a learnable fractional-Fourier order that continuously interpolates between the spatial domain (recovering vanilla LoRA) and the Fourier domain (recovering a spectral adapter). Routing tokens through experts that occupy different points on this spatial-spectral continuum lets the model place each low-rank update in the domain where it is most compact, and -- because fractional-Fourier operators of different orders are mutually incoherent -- makes the experts naturally decorrelated, which reduces interference and improves multi-task composition. The order is a single scalar per expert, trained with a separate optimizer, and the transform is computed with an $\mathcal{O}(d\log d)$ chirp--FFT surrogate, so Fractional-Fourier Mixture of Experts adds negligible cost over standard MoE-LoRA. Across commonsense, mathematical, code, and knowledge benchmarks on LLaMA-3.1-8B and Qwen2.5-7B, Fractional-Fourier Mixture of Experts improves over strong MoE-LoRA and spectral baselines -- including FlyLoRA, FourierMoE, and HMoRA -- while keeping the active-parameter budget small, and analysis shows that the learned orders specialize by task and layer in interpretable ways.

AI 总结：提出基于伊辛模型的热力学计算设备可扩展训练算法，通过反向传播训练深度卷积网络，在CIFAR-10/100上分别达到94.9%和76.0%的准确率，并建立了推理成本与精度的理论关系。

链接：https://arxiv.org/abs/2607.00170

作者：Andrew G. Moore

英文摘要：Thermodynamic computing devices based on the Ising model show great promise for low-power AI inference and edge computing, but scalable methods for training large models for such hardware remain limited. Prior theory shows that the time-averaged behavior of high-temperature Gibbs-sampled Ising systems can implement feed-forward neural inference. We turn this theoretical correspondence into a scalable and purely backpropagation-based algorithm for training deep convolutional networks for thermodynamic inference on Ising machine hardware. Our image classification models achieve accuracies of 94.9% on CIFAR-10 and 76.0% on CIFAR-100 under binary Gibbs sampling. We then develop and experimentally validate a mathematical theory relating inference cost to accuracy and controlling autocorrelation times. Subsequently, we calculate asymptotic results showing that inference cost is bounded by a well-controlled tradeoff with performance and exhibit algorithms for computing optimal inference schedules. Finally, we discuss implications for hardware development and the future of high-temperature thermodynamic AI models.

AI 总结：提出StateFlow框架，扩展VARNN为双状态循环骨干，结合隐藏状态轨迹和残差记忆轨迹，通过分块解码器和两阶段优化实现长时域多步预测，在基准上取得竞争性能。

链接：https://arxiv.org/abs/2607.00197

作者：Haroon Gharwi, Yue Dai, Kai Shu

英文摘要：Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation. The Variability-Aware Recursive Neural Network (VARNN) is designed to track such variability by maintaining a residual-memory state driven by one-step prediction errors. However, its original formulation is limited to one-step sequence regression and does not directly support multi-step forecasting. In this work, we extend VARNN to long-horizon forecasting and introduce StateFlow, a recurrent forecasting framework that uses VARNN as a dual-state recurrent backbone to capture two complementary signals from the lookback sequence: a hidden-state trajectory representing primary temporal dynamics, including trend, seasonality, level changes, and recurring patterns, and a residual-memory trajectory representing structured local prediction deviations, driven from a nonlinear recurrent transformation of errors between one-step base predictions and observed values. A chunk-based decoder separately summarizes these trajectories and maps them to the future horizon for direct multi-step forecasting. We further employ a two-stage optimization strategy that first trains the VARNN encoder through a one-step base prediction objective to optimize the internal representations over the lookback sequence, and then trains a horizon-specific decoder for direct multi-step forecasting. Experiments on standard LTSF benchmarks show that StateFlow achieves competitive performance against strong linear, recurrent, convolutional, and Transformer-based baselines while preserving linear recurrent encoding and a compact model design.

AI 总结：针对递归特征机在数据损坏场景下性能低于神经网络的问题，提出K-Inverse-RFM，通过对训练标签进行变换，在噪声、复杂表示和类别不平衡数据中提升学习能力，缩小甚至超越与神经网络的性能差距。

链接：https://arxiv.org/abs/2607.00329

机构：University of California San Diego（加利福尼亚大学圣迭戈分校）

作者：Gil Pasternak

英文摘要：Recursive Feature Machines (RFMs) are a class of kernel machines that utilize the Average Gradient Outer Product (AGOP) as a mechanism for feature learning. They have been shown to effectively replicate the learning dynamics and feature representations of Feedforward Neural Networks (FNNs) across various settings. However, despite comparable capacity for feature learning and the similarities in the features they acquire, RFMs exhibit significantly lower performance than neural networks in certain data-corrupted scenarios. In this work, we investigate these limitations in mathematical problems. As a solution, we introduce a remarkably effective transformation applied to the training labels which promotes learning in noisy, complexly represented, and class-imbalanced data. This simple yet powerful adjustment enables RFMs to close the performance gap with FNNs and, in some cases, even surpass them.

AI 总结：本文从领域泛化角度研究线性Transformer的近似与泛化能力，证明其通过上下文分布到响应函数的映射实现上下文学习，并基于理论提出激活函数与损失函数设计新视角。

链接：https://arxiv.org/abs/2607.00479

机构：School of Mathematics and Statistics, University of Sydney（悉尼大学数学与统计学院）

作者：Peilin Liu, Ding-Xuan Zhou

英文摘要： Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning. With richer context, transformers adapt more effectively to the current use case without any parameter updates. However, the quadratic computational and memory complexity with respect to context length significantly slows data processing in softmax transformers. Linear transformers were proposed to address this issue by reducing the complexity to linear dependence on context length, but the design and understanding of the feature mapping in linear attention, from a theoretical viewpoint, remain unclear. In this paper, we investigate the approximation and generalization abilities of linear transformers under a two-staged sampling process from domain generalization. We show that linear transformers perform in-context learning as learning a mapping from context distributions to response functions. A dimension-independent convergence rate is obtained for our generalization analysis, which also exhibits the tradeoff between the regularities of data distributions and latent features. Guided by our theoretical framework, we propose a new perspective on activation and loss design for linearizing pretrained softmax large language models.

AI 总结：提出原型语言模型架构PRISM，通过稀疏非负原型混合进行预测，在保持下游精度的同时实现快速训练数据归因和可解释性。

链接：https://arxiv.org/abs/2607.00510

作者：Dan Ley, Giang Nguyen, Himabindu Lakkaraju, Julius Adebayo

英文摘要：Knowing which training examples drive outputs is fundamental to auditing, correcting, and understanding language models, yet for modern LLMs this remains expensive, approximate, and largely post-hoc. Standard language models generate tokens through a dense network pathway, causing training data's influence to be distributed across parameters rather than organized along explicit, traceable components. We introduce a prototype language model architecture, Prototypes for Interpretable Sequence Modeling (PRISM), that forms each prediction via a sparse, non-negative mixture of learned prototypes, trained with clustering objectives that anchor each prototype to coherent neighborhoods of training examples. Across architectures from 130M to 1.6B parameters trained on up to 50B tokens, prototype language models either surpass or remain within 2.5 percentage points on average downstream accuracy of matched dense baselines. We show that sparse prototype structure localizes curvature in the loss landscape, yielding a more tractable Hessian and enabling training data attribution that is ~500x faster than post hoc baselines when consuming equivalent memory. Calibrating linear prototype controllers can improve downstream accuracy by roughly 3 points while tracing those corrections back to training neighborhoods, and targeted prototype suppression can remove model behaviors without finetuning or measurable loss in generation quality.

AI 总结：针对庞加莱ResNet优化困难及标准双曲网络无法处理空间变换等变性的问题，提出结合双曲几何与离散对称群的等变庞加莱ResNet，通过几何安全的张量重塑、左正则置换和联合定向批归一化，实现边界约束下的快速收敛和空间群等变性。

链接：https://arxiv.org/abs/2607.00556

作者：Aiden Durrant, Rahul Baburajan, Georgios Leontidis

英文摘要：While recent advancements like the Poincaré ResNet have demonstrated the potential of learning visual representations directly in hyperbolic space, their optimisation remains hampered by the computationally intensive nature of Riemannian gradients and the strict boundaries of the manifold. Furthermore, standard hyperbolic networks treat spatial transformations of the same object as distinct hierarchical concepts, leading to redundant parameter usage and vanishing signals. We propose Equivariant Poincaré ResNets, combining hyperbolic geometry with discrete symmetry groups ($C_4$ and $D_4$). We identify critical roadblocks in applying Euclidean equivariance to hyperbolic space and propose geometrically safe tensor reshaping, left-regular permutations for hyperbolic group convolutions, and joint-orientation Poincaré Midpoint Batch normalisation. Empirically, embedding equivariance drastically reduces the optimisation space, accelerating convergence while accelerating convergence while respecting the boundary constraints of the Poincaré ball and preserving spatial-group equivariance.

AI 总结：提出损失平滑方法，通过在自适应初期插值源与目标训练目标，实现平滑过渡，保留有用特征，在多种分布偏移场景下提升性能。

链接：https://arxiv.org/abs/2607.00634

机构：Chandar Research Lab（Chandar 研究实验室）； Mila – Quebec AI Institute（Mila – 魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； Polytechnique Montréal（蒙特利尔理工学院）； Canada CIFAR AI Chair（加拿大 CIFAR 人工智能主席）

作者：Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu, Sarath Chandar

英文摘要：In settings such as fine-tuning and reinforcement learning, neural networks are often adapted under distribution shift. Standard adaptation methods typically optimize the target objective directly, inducing an abrupt change from the source training objective. This abrupt transition can distort learned representations, including features that may still be useful for the new task. We investigate whether a more gradual transition can improve adaptation. We propose loss smoothing, a simple approach that interpolates between the source and target training objectives at the start of adaptation. This smooth transition helps to preserve useful features from the source distribution while still enabling the model to specialize to the target distribution. Across controlled supervised shifts, pretrained vision adaptation, offline-to-online and online reinforcement learning, and language model fine-tuning, we find that loss smoothing consistently improves performance, suggesting that smoother objective transitions are a broadly useful tool for model adaptation.

AI 总结：提出文本提示提升（TPB）框架，通过AdaBoost策略将每个文本提示分类器视为弱学习器，顺序集成以聚焦难分类样本，提升少样本分类精度并实现跨模型迁移。

链接：https://arxiv.org/abs/2607.00684

机构：KT Corporation（KT公司）； Pohang University of Science and Technology (POSTECH)（浦项科技大学）； National AI Research Lab（国家人工智能研究实验室）

作者：Seokhee Jin, Changhwan Sung, Sunung Mun, Hoyoung Kim, Jungseul Ok

英文摘要： The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts. Handcrafted templates and Large Language Model (LLM)-generated descriptions not only make predictions more interpretable, but also enable reuse of the same prompts across heterogeneous VLMs. Recent works construct task-adapted text prompts with a small number of labeled images. However, existing few-shot text prompting methods do not explicitly focus on misclassified examples during prompt construction, leading to only marginal improvements even as more shots become available. To fully exploit few-shot supervision, we propose Text Prompt Boosting (TPB), an AdaBoost-inspired framework that treats each text-prompt-based classifier as a weak learner and sequentially aggregates them into a strong ensemble by explicitly targeting hard, misclassified examples. Extensive experiments show that TPB preserves task-intrinsic, model-agnostic cues in text space, enabling robust cross-model transfer. Across eleven classification benchmarks, TPB improves accuracy on the source model and preserves shot-driven gains when transferred to larger, more capable VLMs, where existing methods struggle to sustain such improvements.

AI 总结：提出几何自适应积分自编码器(GAIA)，通过几何令牌和交叉注意力机制，统一处理任意几何上的正问题和反问题，在七个基准上取得最优结果。

链接：https://arxiv.org/abs/2607.01128

作者：Meenakshi Krishnan, Pranav Pulijala, Ke Chen, Haizhao Yang, Ramani Duraiswami

英文摘要：Operator learning for partial differential equations (PDEs) on arbitrary geometries builds fast neural surrogates for large-scale simulation. Although recent geometry-adaptive neural operators have made substantial progress, they are mainly designed for forward problems in which inputs and outputs share the same spatial domain. This limits their applicability for boundary value problems (BVPs) and inverse problems, where inputs and outputs may live on different domains. We introduce the Geometry-Adaptive Integral Autoencoder (GAIA), an operator learning model that encodes the domain boundary and the interior field distribution into geometry tokens, and conditions integral transform layers on these tokens via cross-attention, allowing the kernel to adapt locally to geometric features. This yields a single architecture for forward (including BVPs) and inverse problems on arbitrary domains in one pass, without retraining, iterative optimization, or graph construction. We evaluate GAIA on seven 2D and 3D benchmarks, four of which are new or substantially extended benchmarks for inverse problems and BVP: electrical impedance tomography, optical tomography, 3D Darcy flow on varying geometries, and a modified setting of Poisson BVP on mechanical components benchmark (MCB). GAIA sets new state-of-the-art results on every inverse and BVP task, reducing median relative $L^2$ error by 64% on airfoil flow reconstruction and 27% on EIT relative to the next best amortized method, and outperforming all baselines on every shape category of MCB. On other forward problems, GAIA is competitive with specialized solvers while maintaining stable accuracy across point resolutions on which transformer-based baselines degrade.

AI 总结：针对样本生成模型训练目标忽视下游决策成本的问题，提出将可微决策损失与能量分数结合，实现决策感知训练，在保持完整概率预测的同时提升成本敏感区域性能。

链接：https://arxiv.org/abs/2607.01171

机构：University of Augsburg, Germany（奥格斯堡大学）

作者：Kornelius Raeth, Nicole Ludwig

英文摘要：Sample-based generative models are increasingly used for probabilistic forecasting in high-stakes decision settings, yet their training objectives are blind to the decision maker's cost structure. These models are commonly trained with strictly proper scoring rules, such as the energy score, which allocate their training signal in proportion to data density, with no awareness of where forecast errors are most costly for downstream decisions. We therefore propose decision-aware training for sample-based generative models, augmenting the energy score objective with a differentiable decision loss that directly penalises the cost incurred by acting on the model's forecast. This combined loss is theoretically grounded, as the decision loss is itself a proper scoring rule. We validate our method on one synthetic and two real-world tasks, showing targeted improvements in cost-sensitive regions while retaining full probabilistic forecasts.

AI 总结：发现RL训练收益高度集中在少数Transformer层，仅训练单层即可恢复大部分全参数RL收益，且高贡献层集中在模型中部。

链接：https://arxiv.org/abs/2607.01232

机构：University of Minnesota（明尼苏达大学）； Peking University（北京大学）； Amazon（亚马逊）

作者：Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li, Chung-Yiu Yau, Hongzhou Lin, Mingyi Hong

英文摘要：Reinforcement learning (RL) has become a central component of post-training large language models (LLMs), yet little is understood about how RL adaptation is distributed across transformer layers. Existing approaches typically update all model parameters uniformly, implicitly assuming that every layer contributes similarly to the gains obtained during RL post-training. In this work, we challenge this assumption through a systematic layer-wise study of RL training. Surprisingly, we find that training a single transformer layer can recover most of the gains achieved by full-parameter RL training, and in some cases even surpass it. To quantify this phenomenon, we introduce the quantity layer contribution, which measures the fraction of full RL improvement recovered by training a layer in isolation. Across seven models spanning two model families (Qwen3, Qwen2.5), three RL algorithms (GRPO, GiGPO, Dr. GRPO), and multiple task domains including mathematical reasoning, code generation, and agentic decision-making, we observe a remarkably stable pattern: RL gains are highly concentrated in a small subset of, and in many cases even a single, transformer layers. More strikingly, the same structural pattern consistently emerges: high-contribution layers concentrate in the middle of the transformer stack, while layers near the input and output ends contribute substantially less. The resulting layer rankings remain strongly correlated across datasets, tasks, model families, and RL algorithms.

AI 总结：提出自监督任务相关表示解耦算法T2RD，通过表示一致性、交叉重建和交叉动态预测分离任务相关与无关特征，在控制任务中实现SOTA泛化性能。

链接：https://arxiv.org/abs/2607.00796

机构：Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, School of Computer Science & Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院交通数据挖掘与具身智能北京市重点实验室）； CSSC Intelligent Innovation Research Institute（中国船舶集团智能创新研究院）； Zhejiang University（浙江大学）

作者：Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv

英文摘要：Visual Reinforcement Learning (VRL) has achieved considerable success in solving control tasks. However, generalizing learned policies to new environments remains a major challenge, as agents often overfit to task-irrelevant features in the training environment. To solve this problem, we introduce the concept of decoupling observations into task-relevant and task-irrelevant representations. Building on this idea, we propose a self-supervised Task-Relevant Representation Decoupling (T2RD) algorithm for VRL. This algorithm consists of three components: task-relevant representation consistency, cross-reconstruction, and cross-dynamic prediction. The first two components achieve the decoupling of content and style features, but the resulting content representations are not necessarily task-relevant. To further refine task-relevant features from content representations, we design the third component that introduces dynamic prediction. T2RD achieves State-Of-The-Art (SOTA) generalization performance and sample efficiency in the DeepMind Control Suite and Robotic Manipulation tasks.

AI 总结：提出解构-重组范式（DRP），通过解构全局运动为原子动作学习局部运动表示，再重组以加速下游策略学习，在机器人控制任务中显著提升样本效率。

链接：https://arxiv.org/abs/2607.00808

机构：Beijing Jiaotong University（北京交通大学）； Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通数据挖掘与具身智能重点实验室）

作者：Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv

英文摘要：Pre-training on large-scale videos to improve reinforcement learning efficiency is promising yet remains challenging. Existing methods typically treat the agent as an indivisible entity, modeling motion patterns globally. Such global modeling is tightly coupled with the morphology, hindering transfer across domains. In contrast, despite the vast disparity in global motions, the local components exhibit similar motion patterns across different agents. Building on this insight, we propose a novel Deconstruct-Recompose Paradigm (DRP) for learning transferable local motion representations. Specifically, in the Deconstruct phase, we identify multiple local points and track their frame-wise motions, defining each as an Atomic Action. We introduce a Dual-Attention Encoder (DAE) to learn local motion representations from these Atomic Actions, capturing their spatiotemporal relationships. In the Recompose phase, we compose local motion representations with a learnable Motion Aggregation Token [MAT] via latent dynamics model learning. Additionally, an adapter bridges local motion and downstream action-specific dynamics to accelerate policy learning. Extensive experiments demonstrate that our method effectively transfers to diverse robotic control and manipulation tasks, significantly improving sample efficiency and performance.

AI 总结：提出多尺度时间对比学习（MTCL）方法，通过建模时间相关性平衡像素空间中各元素的注意力，学习信息更丰富的表示，提升下游强化学习任务的样本效率和性能。

链接：https://arxiv.org/abs/2607.00811

机构：School of Computer Science & Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）； Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University（北京交通大学交通数据挖掘与具身智能北京市重点实验室）； Beijing Jiaotong University（北京交通大学）

作者：Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, Kai Lv

英文摘要：Unsupervised pre-training on large-scale datasets has demonstrated significant potential for improving the sample efficiency and performance of Reinforcement Learning (RL). Given the large-scale action-free internet videos, existing methods utilize single-step transition prediction and image reconstruction to learn representations. However, these methods prefer to preserve large-proportion stationary information in the pixel space, neglecting small but crucial information. To preserve enough information in the representation, it is essential to pay equal attention to each element in videos. Specifically, we propose a temporal correlation space to distinguish each element. For implementation, we introduce the Multi-scale Temporal Contrastive Learning (MTCL) method to model multi-scale temporal correlations separately. This approach can balance the attention of different elements and yield more informative representations, effectively supporting policy learning in various downstream tasks. Experimental results demonstrate that our method improves sample efficiency and asymptotic performance across various downstream tasks.

AI 总结：提出LeNEPA，一种无需数据增强的下一潜在预测架构，通过SIGReg正则化和轻量投影空间，在固定配方测试中跨数据集保持性能，优于ECG调优的JEPA。

链接：https://arxiv.org/abs/2607.00958

机构：Langotime South Africa（Langotime南非）； Griffith University Australia（澳大利亚格里菲斯大学）； Brown University United States（美国布朗大学）

作者：Alexander Chemeris, Ming Jin, Randall Balestriero

英文摘要： Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances. We study how an SSL recipe behaves when its method-specific configuration is reused unchanged after the pretraining signal family changes, framing this as a fixed-recipe stress test rather than a comparison against optimally tuned methods. We introduce Latent Euclidean Next-Embedding Prediction Architecture (LeNEPA), a no-augmentation next-latent-token objective with a causal backbone. LeNEPA replaces the stop-gradient/EMA stabilization used by vanilla NEPA with SIGReg-based isotropy regularization and computes the predictive loss in a lightweight projected space that is discarded for evaluation. We compare LeNEPA with an ECG-tuned JEPA recipe under a fixed-horizon frozen-probe protocol on PTB-XL and Diag, a synthetic diagnostic corpus generated with Aionoscope. Both methods are retrained independently on each dataset while keeping their method-specific recipes unchanged. In this protocol, the ECG-tuned JEPA recipe is strong in-domain on PTB-XL but weaker when reused unchanged on Diag, whereas LeNEPA preserves useful frozen-probe gains on both datasets. Learning curves suggest faster early representation acquisition: LeNEPA reaches 80% of its final AUROC/AUPRC gain after 2--5k updates, compared with 5--10k updates for the faster JEPA readout. As a separate external frozen-encoder check, a CauKer-pretrained LeNEPA variant reaches 77.65% mean UCR-128 Random-Forest accuracy in a single-seed, best-checkpoint run, within 1.16 points of Mantis and within 0.24 points of MOMENT (77.89%). Overall, the results support no-augmentation latent prediction as a useful candidate recipe for low-retuning time-series SSL.

AI 总结：提出ER-JEPA，一种轻量级自监督学习框架，通过层次化联合嵌入预测架构对多变量时间序列进行表征学习，在心电图数据上实现高效预训练和下游任务最优性能。

链接：https://arxiv.org/abs/2607.01145

机构：Research Institute of Basic Sciences, Seoul National University（首尔大学基础科学研究院）

作者：Siwon Kim

英文摘要：Data analysis in the medical domain often encounters scenarios involving a limited target dataset and a large, unannotated dataset with a general distribution. Under such circumstances, self-supervised learning (SSL) methods are highly effective for utilizing large datasets, making them a popular choice for electrocardiogram (ECG) analysis. This work presents the Event Reconstruction Joint-Embedding Predictive Architecture (ER-JEPA), a lightweight SSL framework for multivariate time series, whose name and two-fold hierarchical structure are inspired by the diagnostic approach of cardiologists. At its core, ER-JEPA features: (1) a two-stage structure that constructs representations for each time interval and subsequently processes these representations as a univariate time series, (2) the hierarchical integration of two Joint-Embedding Predictive Architectures (JEPAs), and (3) a Vision Transformer (ViT) backbone. The structural concatenation of two JEPAs categorizes the model as a Hierarchical JEPA (H-JEPA), designed to encode multiple levels of abstract representations for enhanced prediction on complex tasks. This study reports a successful application of H-JEPA to 12-lead ECG data as a multivariate time series alongside an analysis of the sensitivity of hierarchical representation during the pretraining stage. Pretrained on approximately 180,000 10-second recordings, the model achieves state-of-the-art downstream performance on the ST-MEM benchmark, with rapid computation and minimal resource usage.

AI 总结：提出GenDa框架，通过技能重标定缓解非平稳性，并引入互补信息瓶颈增强泛化性，实现数据高效且鲁棒的无监督强化学习预训练。

链接：https://arxiv.org/abs/2607.00392

机构：Department of Computer Science and Engineering, Sungkyunkwan University（成均馆大学计算机科学与工程系）

作者：Jongchan Park, Seungjun Oh, Seungho Baek, Yusung Kim

英文摘要：Unsupervised Reinforcement Learning (URL) aims to pre-train scalable, skill-conditioned policies without extrinsic rewards, serving as a foundation for downstream control tasks. Despite recent progress, we argue that current off-policy URL methods are limited by two critical, overlooked bottlenecks: (1) non-stationary skill semantics and (2) brittle generalization. To address these challenges, we propose GenDa (Generalizable Data-efficient Agent), a unified framework for robust unsupervised reinforcement learning. First, we introduce a skill relabeling mechanism to mitigate non-stationarity and significantly improve data efficiency for pre-training. Second, we propose a Complementary Information Bottleneck (CIB), encouraging the learned skill policy to focus on ego-centric features and become robust to distribution shifts for downstream tasks. Through various experiments, we demonstrate that GenDa significantly enhances the scalability of URL with superior generalizability and data efficiency. Our code and videos are available at this https URL.

AI 总结：提出用谱有效秩熵衡量评论家模型复杂度，在TD3和PPO实验中追踪复杂度与回报、偏差的关系，并通过谱熵惩罚实现复杂度控制。

链接：https://arxiv.org/abs/2607.00452

机构：Peking University（北京大学）

作者：Konstantin Garbers

英文摘要：Actor-critic methods depend on learned critics, but critic quality is often evaluated only indirectly through return, temporal-difference error, or value loss. Critic complexity is introduced as an additional diagnostic and intervention dimension for actor-critic reinforcement learning. The analysis uses spectral effective-rank entropy, a rank-like summary of the singular-value distributions of critic weight matrices, to assess critic model complexity. Across TD3 and PPO experiments, critic complexity is tracked together with return and Monte Carlo value-estimation bias. The results show that critic complexity is measurable throughout training and is systematically associated with training behavior, while also making clear that the relationship is heterogeneous across algorithms, tasks, and hyperparameters. A direct complexity-control intervention is then evaluated by adding a spectral-entropy penalty to the critic loss. This intervention reliably changes the targeted spectral quantity, demonstrating that critic complexity can be controlled rather than only observed. Return effects are treated as task-dependent evidence rather than as a general performance claim, because overall complexity-control results vary.

AI 总结：提出Active-GRPO方法，通过主动模仿-强化和主动参考机制，在分子优化中自适应平衡模仿与自我改进，显著提升性能。

链接：https://arxiv.org/abs/2607.00531

机构：School of Medicine, Stanford University（斯坦福大学医学院）； Data Science Institute, University of Chicago（芝加哥大学数据科学研究所）； Pritzker School of Molecular Engineering, University of Chicago（芝加哥大学普利兹克分子工程学院）； Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）； Argonne National Laboratory（阿贡国家实验室）

作者：Xuefeng Liu, Mingxuan Cao, Qinan Huang, Thomas Brettin, Rick Stevens, Le Cong

英文摘要：Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge. We study this problem in instruction-based molecular optimization, where answer-only supervised fine-tuning (SFT) collapses multi-step reasoning and reinforcement learning with verifiable rewards (RLVR) suffers from sparse feedback. Reference-guided Policy Optimization mitigates both by anchoring policy updates to dataset-provided references, but its effectiveness is tightly coupled to reference quality: weak or misaligned references impose a performance ceiling. To overcome this ceiling, we propose active reasoning, a paradigm in which the policy actively decides, on a per-instance basis, when to imitate a reference and when to reinforce its own discoveries, while continuously upgrading what it imitates. We instantiate this paradigm as Active Group Relative Policy Optimization (Active-GRPO), realized through two coupled mechanisms: active imitate-reinforce and active referencing. The former performs imitation learning when the reference still outperforms the policy's own candidates, and shifts to self-improvement via reinforcement learning once the policy has generated molecules that surpass the reference. The latter continuously upgrades the reference itself by replacing it with the best policy-generated candidate discovered so far, progressively raising the imitation target and ensuring that reference guidance remains informative-rather than restrictive-throughout training. Across TOMG-Bench MOLOPT, Active-GRPO improves average SRxSim from 0.0959 for GRPO and 0.1665 for RePO to 0.1773 under matched three-seed evaluation, with statistically significant gains on LogP, MR, and QED.

AI 总结：针对量子核高斯过程赌博机优化，提出投影量子核与经典核近似技术以降低特征维度，推导了误设定GP赌博机算法的遗憾界，平衡了近似误差与信息增益。

链接：https://arxiv.org/abs/2607.01080

机构：National University of Singapore（新加坡国立大学）； University of Birmingham（伯明翰大学）

作者：Yuqi Huang, Vincent Y. F. Tan, Sharu Theresa Jose

英文摘要：We investigate Gaussian process (GP) bandit optimization with quantum kernels, assuming the mean reward function lies in the reproducing kernel Hilbert space (RKHS) induced by the quantum kernel. This setting is motivated by NISQ-era tasks such as quantum control, state preparation and variational quantum algorithms. While quantum kernels can offer a `quantum advantage' via domain-specific inductive biases, naïvely using full, high-dimensional kernels increases model complexity and information gain, leading to higher cumulative regret and poor learnability. To address this, we propose projected quantum kernels and classical kernel approximation techniques that reduce feature dimensionality while preserving key quantum properties. Using these approximate kernels, we develop misspecified GP bandit algorithms and derive regret bounds that characterize the trade-off between approximation error and information gain. The regret bounds provide principled guidance for selecting the optimal model complexity. Empirically, our methods outperform full quantum kernels in sample efficiency, while substantially reducing computational overhead, enabling scalable GP optimization for quantum-native applications.

AI 总结：研究异步GRPO中陈旧rollout的影响，推导出陈旧度与学习率之间的缩放定律，揭示稳定性受累积漂移和陈旧度约束的双重条件。

链接：https://arxiv.org/abs/2607.01083

机构：The University of Hong Kong（香港大学）； Shanghai Jiao Tong University（上海交通大学）； Gradient； University of Southern California（南加州大学）； The Hong Kong Polytechnic University（香港理工大学）

作者：Jingwei Song, Haofeng Xu, Jie Xiao, Chengke Bao, Jingwei Shi, Pengbin Feng, Weixun Wang, Yuhang Han, Chuan Wu, Linfeng Zhang, Bill Shi

英文摘要：High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the effect of such staleness in asynchronous GRPO. We make the behavior policy explicit in the GRPO surrogate objective and distinguish between the surrogate-gradient mapping used by the learner and the true total derivative of a distribution-dependent population objective. Under assumptions of local boundedness, distributional smoothness, and behavior-policy smoothness, we show that stale rollouts introduce a per-step surrogate-gradient bias of order O(S * eta), where S denotes the maximum rollout lag and eta denotes the learning rate. We further derive a conditional collapse-time scaling law: when within-cycle drift remains below a batch-level clipping radius, collapse is governed primarily by cumulative learner drift T * eta; when the stale-rollout constraint is active, stability instead depends explicitly on S * eta. This yields a two-constraint stability condition eta << min{R_batch / (S * G_upd), R_crit / (T * G_upd)}, explaining why the maximum stable learning rate may appear weakly dependent on staleness in the horizon-limited regime.

AI 总结：提出对抗生成器-判别器框架，在可验证奖励基础上加入人类演示信号，同时优化任务准确性和非可验证属性，在代码修复、故事生成等任务中提升人类相似度并减少奖励黑客行为。

链接：https://arxiv.org/abs/2607.01181

机构：MIT EECS（麻省理工学院电气工程与计算机科学系）

作者：Mehul Damani, Isha Puri, Idan Shenfeld, Jacob Andreas

英文摘要： RL with verifiable rewards (RLVR) has emerged as a powerful paradigm for training LMs on tasks with well-defined success metrics, such as code generation and mathematical reasoning. However, current RLVR methods optimize only what can be objectively scored, often neglecting subjective, non-verifiable aspects of human-like outputs, such as style and structure. This limitation leads to well-documented failure modes such as diversity collapse, unnatural-sounding responses, and reward hacking. We propose an adversarial generator-discriminator framework that augments verifiable rewards with a learned signal from human demonstrations. A generator model is trained using RL to maximize both task accuracy and an adversarial reward derived from a discriminator. The discriminator, trained alongside the generator policy, learns to distinguish human-written outputs from model-generated ones. The discriminator serves as a learned proxy for the human output distribution, providing feedback on aspects of generation that are difficult to formalize as scalar rewards. Across diverse domains, including bug fixing and open-ended generation, our approach consistently improves non-verifiable properties while preserving the accuracy gains of RLVR. In bug fixing, our method produces solutions with significantly lower edit distance compared to RLVR baselines while matching end performance. In story generation, our method significantly improves win rate while producing stories that are diverse and more human-like. And in a simple reward hacking benchmark, our method nearly eliminates model misbehavior while maintaining high benchmark scores. Together, these results show that our approach bridges RL and SFT, offering a scalable path toward jointly optimizing the verifiable and non-verifiable properties of a task.

AI 总结：提出语言批评框架，用自然语言作为结构化监督信号从次优演示中学习策略，避免压缩为标量，在连续控制任务上优于基线方法。

链接：https://arxiv.org/abs/2607.01225

机构：Graduate Institute of Communication Engineering, National Taiwan University (NTU)（国立台湾大学电信工程学研究所）； University of Utah（犹他大学）； National Yang Ming Chiao Tung University（国立阳明交通大学）； NTU Artificial Intelligence Center of Research Excellence（国立台湾大学人工智能卓越研究中心）

作者：Chih-Han Yang, Dai-Jie Wu, Yun-Ping Huang, Ping-Chun Hsieh, Kenneth Marino, Shao-Hua Sun

英文摘要：Prior work on imitation learning from suboptimal demonstrations typically relies on compressed supervision signals such as confidence estimates, discriminator scores, or importance weights. These scalar signals are inherently limited, as they cannot explicitly express intermediate reasoning about task progress, failure modes, or corrective actions. We propose a language-critique framework for imitation learning from suboptimal demonstrations that instead leverages natural language as a structured supervision signal, avoiding the collapse of expressive feedback into scalars. Our method first constructs language labels from demonstrations that explicitly describe current progress, identify suboptimal behaviors, and provide fine-grained corrective guidance. We then introduce a language-critique loss that directly trains policies using these structured signals without reducing them to scalars, and instantiate it for both behavior cloning and diffusion policies, yielding LC-BC and LC-DP. We further provide a theoretical result showing that the proposed objective upper-bounds the expert performance gap under standard assumptions. Empirically, we evaluate on diverse continuous control tasks spanning navigation, manipulation, and gameplay, where our methods consistently outperform strong imitation learning and offline reinforcement learning baselines. These results demonstrate that language can serve as a powerful and structured form of supervision for learning robust policies from suboptimal data.

AI 总结：针对物理约束生成模型推理时投影计算昂贵的问题，提出利用块稀疏雅可比和KKT系统结构，结合GPU稀疏优化实现高效非线性约束投影，加速约束采样。

链接：https://arxiv.org/abs/2607.00095

作者：Alaina Kolli, Theodoros Xenakis, Utkarsh Utkarsh, Pengfei Cai, Rafael Gomez-Bombarelli, Alan Edelman, Christopher Vincent Rackauckas

英文摘要：Generative models have emerged as scalable surrogates for physical simulation, yet they offer no guarantee that their outputs respect the conservation laws, boundary conditions, and nonlinear invariants that govern the underlying physics. Constrained sampling closes this gap, enforcing such constraints exactly at inference time without retraining, but at a computational cost: projection, correction, and trajectory-optimization steps are repeated during sampling, with these steps becoming expensive for nonlinear constraints. Standard ML frameworks exacerbate this: their dense tensor algebra and limited sparse solver composability obscure the structure that physical constraints naturally induce, making efficient batched nonlinear optimization difficult to realize in practice. We address this bottleneck by exploiting the structure that sample-wise batching and local PDE couplings induce in the projection subproblems -- namely, block-sparse Jacobian and KKT systems -- exposing this structure using this http URL and solving the resulting sparse nonlinear programs with this http URL and GPU sparse factorization. Applied to Physics-Constrained Flow Matching (PCFM), on PDE benchmarks with linear, nonlinear, one-dimensional, and two-dimensional constraints, this approach accelerates nonlinear constraint projection while maintaining constraint satisfaction. These results show that sparse GPU nonlinear optimization is a practical foundation for constrained generative sampling in scientific machine learning.

AI 总结：提出FoGS方法，通过从多个生成器中采样并用真实数据训练的生存模型评分过滤，以样本选择替代生成，在16个数据集上平均C-index提升2.17，IBS提升0.67，匹配或超越真实数据训练效果。

链接：https://arxiv.org/abs/2607.00127

作者：Niccolò Maria Rizzi, Eugenio Lomurno, Alberto Archetti, Matteo Matteucci

英文摘要： Survival analysis models time-to-event data, but in clinical settings training data are costly and scarce: events accrue over years of follow-up, cohorts are small, and privacy regulations restrict sharing across institutions. Tabular generative models promise augmentation and privacy-preserving cohort sharing, yet are themselves data-hungry -- on the small cohorts typical of survival analysis, a single generator rarely characterizes the population well enough for downstream models trained on its output to match real-data performance. FoGS (Filtered Mixture-of-Generators for Survival analysis) reframes synthetic-data construction as sample selection rather than generation. A candidate pool is drawn from four architecturally distinct tabular generators, and each sample is scored by an ensemble of seven survival models trained on real data, using proper scoring rules as a per-sample plausibility proxy. A two-level pipeline optimizes, in its outer loop, a selection policy -- generator quotas, scorer weights, a random complement, and stratified balancing on event time and censoring -- against held-out downstream performance, while an inner loop tunes the downstream model (XGBoost-Cox). On 16 public datasets under train-on-synthetic, test-on-real (C-index and IBS, $0$--$100$ scale), FoGS yields mean improvements of $+2.17$ in C-index and $+0.67$ in IBS, improving both metrics on 9 of 16 datasets and at least one on 13 (one-sided Wilcoxon $p=0.039$ and $p=0.035$). It matches or exceeds real-data training on most cohorts, with no significant change in nearest-neighbour privacy margin relative to unfiltered sampling. Sample filtering over a heterogeneous generator pool is thus a viable substitute for real-data training in privacy-restricted clinical settings.

AI 总结：提出Latent Maps of Performance框架，通过引导变分自编码器在星际争霸II职业比赛数据中学习潜在空间，生成反事实路径以提供多粒度反馈，帮助业余玩家提升至获胜配置。

链接：https://arxiv.org/abs/2607.00190

机构：Warsaw University of Technology（华沙理工大学）； Silesian University of Technology（西里西亚理工大学）； University of British Columbia（不列颠哥伦比亚大学）

作者：Andrzej Białecki, Adam Mastalerz, Han Zhou

英文摘要：Recent advances in reinforcement learning have produced superhuman agents across a wide range of competitive games. As a byproduct, researchers have begun studying how these agents play, extracting behavioral representations, analyzing decision structure, and modeling the latent geometry of expert performance. However, this growing body of work has overwhelmingly focused on defeating human players rather than providing feedback, leaving a critical gap in creating model solutions to improve human players. Unlike chess and Go, where AI has become integral to player training, real-time strategy (RTS) games lack principled frameworks for translating expert knowledge into actionable feedback. We introduce Latent Maps of Performance, a framework for counterfactual path generation. We focus on StarCraft~II data to model player improvement as an algorithmic recourse within a learned representation space. As inspiration for our work, we have looked at the championship model used in sports science. We trained a Guided Variational Autoencoder model on 23,305 professional tournament replays, enabling counterfactual traversal between losing and winning gameplay profiles. To fulfill our goal, we have devised and verified four traversal strategies on out-of-distribution (OOD) data randomly sampled from a dataset of amateur replays, namely linear interpolation, iterative optimal transport, density-regularized gradient ascent, and neural flow matching, each designed to generate multi-step improvement trajectories that remain grounded in observed expert behavior while moving a player's profile toward winning configurations. Feedback is extracted at multiple granularities to support players at different stages of improvement. Finally, we conclude that there is a trade-off between the path-finding methods we employ and hope that future research will focus on developing model solutions for human improvement.

AI 总结：提出量子流匹配（QFM）模型，利用自旋Wigner函数和函数流匹配学习多量子比特量子分布，有效捕获物理量如纯度、纠缠熵。

链接：https://arxiv.org/abs/2607.00301

作者：Jaehoon Hahm, Tak Hur, Joonseok Lee, Daniel K. Park

英文摘要：The emergence of powerful deep generative models based on diffusion and flow matching has enabled the learning and modeling of complex distributions. Learning quantum distributions, however, remains challenging due to the inherent difficulty of accurately modeling the meaningful physical properties of quantum states. We propose Quantum Flow Matching (QFM), a novel generative model designed to learn quantum distribution by utilizing spin Wigner function and flow matching. By converting density matrix into the spin Wigner function and leveraging functional flow matching to learn distributions in function space, QFM enables accurate and effective learning of multi-qubit quantum distributions. We demonstrate the effectiveness of our method by evaluating physical quantities such as trace, purity, and entanglement entropy of the generated quantum states, accurately capturing the underlying physics of the given quantum distributions.

AI 总结：提出PAPA方法，无需参数化奖励模型，通过实时用户反馈直接优化扩散模型，实现高效的偏好对齐，并基于理论提出加速微调的EPAPA策略。

链接：https://arxiv.org/abs/2607.00486

机构：Washington University in St. Louis（圣路易斯华盛顿大学）； Oak Ridge National Laboratory（橡树岭国家实验室）

作者：Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, Yevgeniy Vorobeychik

英文摘要：Diffusion models are highly effective at modeling complex data distributions, including images and text. However, in applications like personalized recommender systems, the objective often shifts to modeling specific regions of the distribution that maximize user preferences-initially unknown but gradually uncovered through interactive feedback. This can naturally be framed as a reinforcement learning problem, where the goal is to fine-tune a diffusion model to maximize a reward function based on preferences. However, the main challenge lies in learning a parameterized reward model, which typically requires large-scale preference data-something that is often not feasible in practice. In this work, we introduce Personalized Active Preference Alignment PAPA, a novel method that bypasses the requirement for a parametrized reward model by directly optimizing the diffusion model using real-time user feedback. PAPA enables feedback-efficient preference alignment, drawing inspiration from the variational inference framework. We demonstrate PAPA's effectiveness through extensive experiments and ablation studies across diverse class-conditioned and fine-grained alignment tasks. Additionally, based on theoretical insights, we propose an enhanced fine-tuning strategy, referred to as EPAPA, that requires less computational budget and accelerates the fine-tuning process, further boosting PAPA's suitability for real-world deployment. Our code is made publicly available at this https URL.

AI 总结：提出Flow-Map GRPO框架，通过锚定随机流映射组合（ASFMC）对确定性少步流映射生成器进行随机化，使其适用于强化学习后训练，并在FLUX文本到图像生成器上提升奖励和感知指标。

链接：https://arxiv.org/abs/2607.00535

机构：Georgia Institute of Technology（佐治亚理工学院）

作者：Zhiqi Li, Wen Zhang, Bo Zhu

英文摘要：Few-step flow-map generators, such as consistency models and MeanFlow, accelerate sampling by directly learning long-range transport maps between noise and data. However, these models are typically deterministic, which makes them difficult to optimize with reinforcement learning (RL) post-training methods that require stochastic trajectories and well-defined likelihood ratios. Existing SDE-based stochasticization techniques are designed for velocity-based samplers with infinitesimal or finely discretized transitions, and therefore do not directly apply to long-range flow maps. In this work, we propose Flow-Map GRPO, an online RL post-training framework for deterministic few-step flow-map generators. The key component is Anchored Stochastic Flow Map Composition (ASFMC), a path-preserving stochasticization mechanism that introduces randomness through anchor-based conditional resampling while preserving the original marginal probability path of the deterministic flow map. We derive GRPO objectives for both single-time and two-time flow-map parameterizations. Experiments on few-step FLUX-based text-to-image generators, including MeanFlow and sCM, show that Flow-Map GRPO improves pretrained deterministic flow-map models across reward-based, perceptual, and task-level evaluation metrics. Our results demonstrate that deterministic few-step flow-map generators can be effectively aligned with RL post-training without modifying their original model parameterization or retraining them as native stochastic models.

AI 总结：提出SPARROW算法，通过解耦生成先验与奖励信号，利用固定结构化提议算子进行基于排名的引导，在极低评估预算下实现复杂几何空间和不可靠奖励信号的有效优化。

链接：https://arxiv.org/abs/2607.00691

机构：CVLab EPFL（瑞士洛桑联邦理工学院计算机视觉实验室）

作者：Edouard R. Dufour, Pascal Fua

英文摘要：Black-box optimization is a fundamental science and engineering tool that makes it possible to optimize objectives without gradient information. Unfortunately, as it often requires many function evaluations, it can be challenging when each one is costly. This is especially true when the evaluation function is noisy or failure-prone, and when high-performing solutions are confined to thin, curved, or disconnected regions of the search space. Existing methods leveraging generative models to navigate these subspaces are built to sample from reward-aligned distributions. As a result, they require a large number of evaluations to align their sampler effectively, making them impractical in low-budget settings. We propose SPARROW, an algorithm that completely decouples the generative prior from the reward signal. SPARROW can use any sampler with a known corruption process and trained on unevaluated data, as a fixed, structured proposal operator. Optimization proceeds by rank-based guidance over an archive of evaluated candidates. SPARROW can navigate complex geometries, handle unreliable reward signals, and perform effective optimization under very low evaluation budgets. We provide asymptotic convergence guarantees over the sampler support and demonstrate strong empirical performance on problems with unreliable rewards and geometrically complex landscapes.

AI 总结：提出基于连续时间马尔可夫链框架的并行τ-leaping算法，利用Picard迭代实现时间并行采样加速，将复杂度从O(d log S)降至O(log(d log S)·log d)，在合成和真实数据上实现7-9倍加速。

链接：https://arxiv.org/abs/2607.00773

机构：The University of Tokyo（东京大学）； The University of Sydney（悉尼大学）； RIKEN AIP（日本理化学研究所革新智能研究中心）； The Institute of Statistical Mathematics（统计数理研究所）

作者：Yu Yao, Huanjian Zhou, Andi Han, Wei Huang, Masashi Sugiyama

英文摘要：Discrete diffusion models are widely used for learning and generating discrete distributions. As the generation process is inherently sequential, the acceleration of sampling is of significant importance. In this work, we parallelize the mainstream $\tau$-leaping algorithm for absorbing discrete diffusion in a Continuous-Time Markov Chain (CTMC) framework. By leveraging the continuous-time stochastic integral form of the $\tau$-leaping algorithm and the Picard iteration method, we achieve parallel-in-time sampling acceleration and provide a proof of exponential-factorial convergence for our algorithm. We improve the overall time complexity of $\tau$-leaping under absorbing settings from ${\mathcal{O}}(d \log S)$ to ${\mathcal{O}}(\log (d\log S)\cdot \log d)$ with respect to NFE. Empirically, our method shows consistent acceleration across synthetic and real-data settings. The new sampler achieves at most $7$--$9\times$ runtime speedup for synthetic distribution, and maintains the same quality with $50\%$ fewer NFE and $1.45$--$1.86\times$ runtime speedups in image/text tasks on a single GPU. Our research expands the potential of discrete diffusion models for efficient parallel inference, with broader implications for applications such as molecular structure and language generation.

AI 总结：提出Valdi框架，结合端到端在线训练与潜在扩散动力学模型，在CarRacing环境中使用单步扩散达到与确定性MLP基线相当的性能，揭示了预测多模态与控制性能之间的权衡。

链接：https://arxiv.org/abs/2607.00917

作者：Christopher Lindenberg, Kashyap Chitta

英文摘要：World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain futures. Diffusion models offer a natural mechanism for modeling uncertain dynamics, yet their iterative inference procedure makes them difficult to use for low-latency latent planning. We bridge this gap with Value Diffusion World Models (Valdi), combining end-to-end online training for MPC with a latent diffusion dynamics model. In preliminary experiments on the CarRacing environment, we show that Valdi, using a single diffusion step at both training and inference, matches a deterministic MLP baseline. Our experiments expose a trade-off between predictive multimodality and control performance in this setup. Code is available at this https URL.

AI 总结：提出流提议粒子滤波（FPPF），通过学习条件生成模型作为提议分布，逼近方差最小化最优提议，结合贝叶斯更新和局部化策略，在非线性、非高斯和高维系统中优于统计基线和生成方法。

链接：https://arxiv.org/abs/2607.01012

机构：University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； NVIDIA（英伟达）

作者：Chandni Nagda, Mayank Shrivastavam Gudrun Thorkelsdottir, Gan Zhang, Morteza Mardani, Arindam Banerjee

英文摘要：Data assimilation models state dynamics conditioned on sequential observations, and has wide-ranging scientific applications. In the filtering setting, the goal is to model the posterior over the current state given all observations so far. Classical solutions typically make simplifying distributional or functional assumptions, e.g., linear-Gaussian systems, which can be inaccurate in many scenarios. In principle, particle filters (PFs) remove these assumptions, yet often collapse in high dimensions. Recent generative approaches learn conditional state transitions, but without principled Bayesian updates they do not recover the correct filtering posterior and can accumulate error over long horizons. In this work, we introduce Flow Proposal Particle Filters (FPPF), which learn a conditional generative model based proposal approximating the variance-minimizing optimal proposal for particle propagation. Conditioning on observations steers particles toward high-likelihood regions before weighting, reducing weight variance and delaying degeneracy. Since our proposal admits tractable likelihood evaluation, FPPF computes accurate importance weights and retains a Bayesian update step. We further extend FPPF to high-dimensional problems through localization strategies, adressing another standard PF failure mode. Extensive experiments on a variety of dynamical systems show that FPPF outperforms statistical baselines and other generative methods in non-linear, non-Gaussian, and high-dimensional regimes.

AI 总结：提出SynLaD框架，结合潜在扩散与反应约束生成，在3D药效团条件下同时优化分子可合成性和形状匹配，优于现有基线。

链接：https://arxiv.org/abs/2607.01105

作者：Miruna Cretu, John Bradshaw, Patricia Suriana, Saeed Saremi, Omar Mahmood, Kirill Shmilovich, Kangway Chuang, Vishnu Sresht, Colin Grambow

英文摘要：We present SynLaD, a latent diffusion framework for small-molecule generation that unifies ligand-based drug design objectives (what to make) with synthetic accessibility (how to make it). Current models typically optimize one objective at the expense of the other, creating a bottleneck for discovering high-scoring and synthesizable molecules. SynLaD combines reaction-constrained generation with pharmacophore-conditioned 3D design by learning a latent space that decodes to both 3D structures and synthesis pathways. An encoder maps molecules to a latent representation used by two decoder heads: (i) a geometric head that reconstructs atom types and coordinates and (ii) an autoregressive synthesis head that outputs synthetic routes in a serialized, reaction-based notation. A diffusion transformer generates novel latents in the learned space, conditioned on pharmacophore profiles. Across analogue generation tasks for bioactive ligands, SynLaD outperforms existing baselines in synthesizable and diverse hit generation, demonstrating that a single model can produce shape-aligned molecules with feasible synthesis plans.

AI 总结：提出序列控制交互式多粒子流图（IMPFM），通过多粒子交互和流图驱动的后验样本共享机制，实现在线反馈驱动搜索中的全局探索与偏好对齐，避免模式崩溃和权重退化。

链接：https://arxiv.org/abs/2607.01144

机构：Uppsala University（乌普萨拉大学）

作者：Binglin Ji, Anindya Sarkar, Hengchang Lu, Jens Sjölund, Yevgeniy Vorobeychik

英文摘要：While generative models have enabled training-free reward alignment, current methods typically excel in local exploration within narrow regions of the underlying distribution. These approaches struggle when preferences are unknown a priori and only revealed through sequential feedback-a scenario demanding broad exploration to uncover high-utility regions. To address this, we propose Sequentially-Controlled Interactive Multi-Particle Flow-Maps (IMPFM), a framework for sample-efficient online feedback-driven search. IMPFM progressively transports a group of interactive particles toward the target distribution, maintaining the broad coverage essential for heterogeneous preference alignment. IMPFM introduces a principled and efficient posterior sample sharing mechanism across particles powered by flow maps. By correcting individual particle drift with the collective posterior samples of the entire ensemble at each resampling step, the framework maximizes sample utility to enable global exploration while actively mitigating reward over-optimization, typical of standard control frameworks. Paired with a principled exploration-exploitation reweighting mechanism involving multi-particle interaction, this sequentially corrected multi-particle dynamics explicitly preserves structural diversity and overcomes the weight degeneracy inherent to standard SMC samplers. Crucially, we prove that the resulting sampling framework yields a multi-particle interaction-aware Feynman-Kac corrector that progressively steers the multi-particle system toward a KL-tilted target distribution, facilitating global exploration and preventing mode collapse. Extensive empirical evaluations and rigorous ablations across diverse search and alignment tasks confirm the efficacy of IMPFM over existing baselines.

AI 总结：提出一种基于块Lewis权重的算法，通过求解少量线性系统获得群体分布鲁棒最小二乘问题的近似最优解，在中等精度下优于内点方法。

链接：https://arxiv.org/abs/2607.00252

机构：TTIC（丰田工业大学芝加哥分校）； Institute for Foundations of Data Science, Yale University（耶鲁大学数据科学基础研究所）

作者：Naren Sarayu Manoj, Kumar Kshitij Patel

英文摘要： We present an algorithm for the group distributionally robust (GDR) least squares problem. Given $m$ groups, a parameter vector in $\mathbb{R}^d$, and stacked design matrices and responses $\mathbf{A}$ and $\mathbf{b}$, our algorithm obtains a $(1+\varepsilon)$-multiplicative optimal solution using $\widetilde{O}(\min\{\mathsf{rank}(\mathbf{A}),m\}^{1/3}\varepsilon^{-2/3})$ linear-system-solves of matrices of the form $\mathbf{A}^{\top}\mathbf{B}\mathbf{A}$ for block-diagonal $\mathbf{B}$. Our technical methods follow from a recent geometric construction, block Lewis weights, that relates the empirical GDR problem to a carefully chosen least squares problem and an application of accelerated proximal methods. Our algorithm improves over known interior point methods for moderate accuracy regimes and matches the state-of-the-art guarantees for the special case of $\ell_{\infty}$ regression. We also give algorithms that smoothly interpolate between minimizing the average least squares loss and the distributionally robust loss.

AI 总结：提出一种无需下降和对齐的方法，从训练网络的单次冻结检查点中，通过方向Fisher率恢复每个死方向的阶数k，并分类奇异方向与平规范对称性，适用于多种网络层。

链接：https://arxiv.org/abs/2607.00603

机构：IIIT, Hyderabad（海得拉巴国际信息技术学院）

作者：Tejas Pradeep Shirodkar

英文摘要：We give a descent-free, alignment-free measurement of singular structure on trained networks. At a single frozen checkpoint the read recovers the order $k$ of each dead direction from the directional-Fisher rate, the master invariant from which the per-direction learning coefficient $1/(2k)$ follows exactly, in whatever basis the optimizer left. The same read classifies each direction, separating a genuine singularity, whose order the architecture fixes, from a flat gauge symmetry; the directional-Fisher magnitude settles the cases the order cannot. A pluggable detector supplies the directions for transformer, convolutional, and normalisation layers. The read recovers the architecture-predicted order across constructed cells and trained networks, including a fine-tuned vision transformer whose dead structure is the LayerNorm-kernel gauge and a from-scratch one whose compressed MLP forms a node-death at its activation order. Where the singular structure enumerates, the per-direction orders assemble, through the typed intersection of the loci, into the global coefficient $(\lambda, m)$ matching the closed form. The method removes the canonical-alignment and descent preconditions of the underlying rate result, turning order-recovery into a deterministic, architecture-general reading. We then map its reach into the Watanabe triple: the order determines the universal singular fluctuation $\nu(k)$, though a trained network's realized $\nu$ falls below it as the live structure absorbs the dead direction's data fluctuation, and the multiplicity recovers from the dominant structure under a single-locus assumption.

AI 总结：针对划分拟阵约束下的分布式在线子模最大化问题，提出统一算法框架，在全信息和赌博机反馈下实现次线性(1-1/e)-遗憾，并通过有界随机管道舍入方案使采样违规概率渐近消失。

链接：https://arxiv.org/abs/2607.00680

机构：College of Automation Engineering, Nanjing University of Aeronautics and Astronautics（南京航空航天大学自动化学院）； School of Artificial Intelligence and Automation at the Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院）； School of Aeronautics and Astronautics, Purdue University（普渡大学航空航天学院）

作者：Bin Du, Chang Liu, Dingqi Zhu, Lintao Ye, Dengfeng Sun

英文摘要：We study distributed online submodular maximization under partition matroid constraints, in which multiple agents select a limited number of actions from their own subsets sequentially to maximize the cumulative value of a sequence of objective functions. We develop a unified algorithmic framework that accommodates full-information and bandit feedback models. For both feedback models, we prove that the proposed algorithms achieve sublinear $(1-1/e)$-regret guarantees, which are comparable to those achieved by existing centralized counterparts. Furthermore, to tackle the sampling violation issue caused by continuous relaxation and rounding, we develop a bounded stochastic pipage rounding scheme and show that the probability of sampling violation vanishes asymptotically. As a result, the cumulative sampling violation remains sublinear in $T$, which is further shown to be not improvable under certain conditions. Numerical results validate the theoretical findings in this paper.

AI 总结：针对可行域小且存在辅助数据源的约束优化问题，提出多源框架扩展约束最大熵搜索，通过捕获源间相关性平衡成本与信息增益，在弱相关辅助数据下仍高效找到可行最优解。

链接：https://arxiv.org/abs/2607.00865

机构：TU Delft（代尔夫特理工大学）； University of Oxford（牛津大学）

作者：Hauke Maathuis, Roeland De Breuker, Saullo Castro, Maike Osborne

英文摘要：Bayesian Optimisation (BO) under unknown constraints is particularly challenging when feasible regions are small. In such settings, existing methods that typically rely solely on evaluations of the true objective and constraints struggle to efficiently explore the design space. However, many real-world applications offer auxiliary data sources (e.g. surrogate models or simplified simulations) that can support early exploration. Despite this potential, their integration into constrained BO remains largely unexplored. We propose a general multi-source framework that extends constrained Max-value Entropy Search, capturing inter-source correlation while balancing evaluation cost and information gain. Experiments on both synthetic and physics-based benchmarks show that our method efficiently identifies feasible and optimal solutions, even when auxiliary data are only weakly correlated. The proposed approach consistently outperforms existing methods, particularly in early-stage exploration.

AI 总结：提出微分同胚优化方法，利用扩散/流模型将数据流形映射到简单基空间进行梯度下降，等价于流形上的黎曼梯度下降，并扩展到SO(3)和SE(3)群，在蛋白质设计中显著提升二级结构靶向、肽结合亲和力和Rosetta能量优化。

链接：https://arxiv.org/abs/2607.00947

机构：Microsoft Research AI4Science（微软研究院AI4Science）； Prescient Design, Genentech Roche（Prescient Design, 基因泰克/罗氏）

作者：Ludwig Winkler, Andrew Leaver-Fay, Joseph Kleinhenz, Pan Kessel

英文摘要： Generative models learn data distributions that reside on a low-dimensional manifold within a higher-dimensional ambient space. Optimizing differentiable objectives on this manifold is challenging: the ambient loss landscape is high-dimensional, rugged, and non-convex. Direct gradient descent, blind to the manifold's geometry, quickly drifts off it. Diffeomorphic optimization starts from the observation that diffusion and flow models provide a map from the data manifold to a much simpler base space in which we perform gradient descent. Using differential geometry, we show this is equivalent to Riemannian gradient descent on the data manifold up to $\mathcal{O}(\lambda^2)$ corrections, keeping trajectories on-manifold by construction and yielding a smoother optimization surface. For protein design, we extend diffeomorphic optimization to the matrix Lie groups $\mathrm{SO}(3)$ and $\mathrm{SE}(3)$, deriving an autograd-compatible $\mathrm{SO}(3)$ gradient and a generalized adjoint-state method for backpropagation through Lie-group ODE solvers. Diffeomorphic optimization improves over tuned guidance on secondary-structure targeting with FrameFlow ($91.3\%$ vs. $63.3\%$ of residues in the Ramachandran target), outperforms OC-Flow on peptide binding affinity at $2\times$ the speed, and reduces Rosetta energies by thousands of units across the PDB test set for structures with hundreds of residues.

AI 总结：提出 Muon 优化器可视为训练中的隐式残差连接，通过正交化更新牺牲即时梯度保真度以改善下游层表示保留，并在线性优化中验证其平衡局部下降与下游可用性的机制。

链接：https://arxiv.org/abs/2607.01124

作者：Hao Huang

英文摘要：Muon has recently emerged as one of the most effective optimizers for training large neural networks, yet its empirical success has been explained from several different perspectives. In this paper, we propose a simple mechanistic interpretation: Muon can be understood as an implicit residual connection during training. Specifically, orthogonalizing the update can sacrifice some immediate gradient fidelity while improving representation preservation for downstream layers. We study this trade-off in controlled linear optimization settings, where Muon can learn representations that are slower to fit a local target but easier for downstream layers to exploit. Our results suggest a conceptual explanation for Muon and a design perspective for optimizers that balance local descent with downstream usability.

AI 总结：提出神经证书定价（NCP）方法，利用无监督学习预测证书级对偶价格，通过结构化恢复层构建原始边际，实现摊销分离，在三个组合优化问题上显著优于或匹配现有方法，且泛化性强。

链接：https://arxiv.org/abs/2607.01185

机构：Rice University（莱斯大学）

作者：Jingyi Chen, Xinyuan Zhang, Xinwu Qian

英文摘要：Combinatorial optimization (CO) problems are difficult because certifiable discrete structure induces exponential search. One needs to search over the set exponentially many candidates to certify optimality, however, the structural feasibility of a path, packing, or cover can be verified in polynomial time once supplied. In this study, we introduce Neural Certificate Pricing (NCP) that exploits this asymmetry under an unsupervised learning framework. A neural network is trained to predict certificate-level dual prices, while a structured recovery layer constructs the induced primal marginal. NCP can be viewed as amortized separation: instead of enumerating violated inequalities, it learns the residual prices through which their aggregate effect enters recovery. When the certificate-consistency condition holds, the recovered marginal is globally feasible, and a local theory shows that first-order errors in the predicted price induce only second-order loss in objective value. Across three classes of CO problems, NCP either outperforms state-of-the-art neural baselines by large margins or matches them at a fraction of the computation time, and shows stronger out-of-distribution generalization.

AI 总结：提出MosaicKV系统，利用动态二维KV缓存压缩解决长上下文服务中的内存瓶颈，通过细粒度稀疏性和压缩管理实现高吞吐和低延迟，在H800 GPU上取得最高16倍注意力加速和3倍内存节省。

链接：https://arxiv.org/abs/2607.00760

机构：Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University（上海交通大学并行与分布式系统研究所）

作者：Sheng Qiang, Ruiwei Chen, Yinpeng Wu, Jinyu Gu, Zhichao Hua, Yubin Xia, Binyu Zang, Haibo Chen

英文摘要：Long-context LLM services now sustain prompts with hundreds of thousands to millions of tokens, making the key-value (KV) cache a first-order serving cost. Because the cache grows linearly with context length, it can exhaust GPU memory, force smaller batches, and reduce serving throughput. Prior KV cache compression techniques typically target only the sequence dimension or only the channel dimension, which leaves limited headroom as context windows scale. Compressing both dimensions promises higher memory reduction, but applying the two forms of compression directly leads to significant accuracy loss. This paper introduces MosaicKV, a dynamic two-D (dimensional) KV cache compression system for extremely long-context serving. MosaicKV uses dynamic two-D compression to address the accuracy challenge, exploiting the non-uniform importance distribution of elements within the KV cache. Instead of applying one compression pattern globally, MosaicKV identifies important elements for each KV vector and selects compression strategies at the granularity of KV cache segments. To address the performance challenge, where fine-grained sparsity and compression management overhead can offset the gains from compression, MosaicKV introduces compressed KV cache management. This mechanism uses underutilized GPU and CPU resources to maintain compressed KV caches and accelerate attention computation. Evaluation on an H800 GPU with multiple LLMs shows that MosaicKV delivers up to 16x attention speedup, 4.8x lower decode latency, and 7.3x higher throughput than the uncompressed baseline. At the same time, it reduces memory usage by 3x and incurs only 1.76% average accuracy loss on LongBench and RULER.

AI 总结： 本文揭示混合精度量化中的困惑度幻觉和对齐-多样性权衡，提出TASA框架联合优化校准数据组成和比特分配，在3.5比特平均精度下匹配或超越4比特基线。

链接：https://arxiv.org/abs/2607.00908

机构：South China University of Technology（华南理工大学）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）； Ocean University of China（中国海洋大学）； Center for AI Theoretical Foundation and Systems, Shenzhen Loop Area Institute（深圳环区研究所人工智能理论基础与系统中心）

作者：Fei Wang, Chao Xue, Taoran Liu, Li Shen, Ye Liu, ChangXing Ding

英文摘要：Mixed-precision quantization (MPQ) has become a key technique for deploying large language models under stringent memory and compute constraints. We first identify a phenomenon that we term the Perplexity Illusion: layers ranked as important by perplexity-based sensitivity show little rank correlation with those that are most influential for complex reasoning performance, with Kendall $\tau \approx 0$ in our analysis. We further reveal an Alignment-Diversity Tradeoff: using only target-task calibration data can degrade post-quantization performance, whereas incorporating general-domain data stabilizes sensitivity estimation and improves robustness across tasks. Based on these observations, we propose TASA (Task-Aware Sensitivity Analysis), a two-level framework that jointly optimizes calibration-data composition and mixed-precision bit allocation. Specifically, TASA searches for a calibration-data mixture using a training-free gradient-trace alignment criterion, and then aggregates perplexity and reasoning-oriented sensitivity signals to guide both inter-layer and intra-layer bit allocation. Experiments on LLaMA-3-8B and Qwen2.5-7B reveal a precision inversion: appropriately allocated 3.5-bit models can match or surpass less task-aware 4-bit baselines. At an average precision of 3.5 bits, TASA matches or outperforms several competitive 4-bit uniform baselines in aggregate accuracy, and improves over the strongest W3 baseline on GSM8K by more than 20 absolute points on LLaMA-3-8B. These results show that calibration-data composition substantially affects task-sensitive quantization, a factor underexplored in prior work.

AI 总结：针对大语言模型KV缓存压缩中向量量化导致的方向保持问题，提出增益-形状K均值（GSKM）替代标准K均值，并构建增益-形状残差量化（GSRQ），在1比特下将LongBench平均准确率从11.34提升至33.54。

链接：https://arxiv.org/abs/2607.01065

作者：Soosung Kim, Minjae Park, Eui-Young Chung, Jaeyong Chung

英文摘要：The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrained by the linear growth of Key-Value (KV) cache memory. Vector Quantization (VQ), particularly Residual Quantization (RQ), is a promising approach for pushing KV cache storage toward the sub-1-bit regime by progressively encoding residuals with small codebooks. However, most VQ methods still rely on standard $\ell_2$ $K$-means as the core codebook-learning primitive. We identify a subtle high-dimensional issue of this primitive: Euclidean centroid averaging can induce centroid shrinkage, which weakens the angular alignment term in the $\ell_2$ distortion and makes directional preservation harder. To address this issue, we propose Gain-Shape $K$-means (GSKM), a drop-in replacement for $K$-means that improves directional fidelity while matching, and in some regimes improving, $\ell_2$ distortion. We then build Gain-Shape Residual Quantization (GSRQ) by incorporating a weighted extension of GSKM into an RQ pipeline. On LLaMA-3-8B, GSRQ substantially improves over strong KV cache quantization baselines across bit rates. At 1-bit, it improves the average accuracy across LongBench tasks from 11.34 to 33.54, a gain of 22.20 percentage points over VQLLM.

AI 总结：提出ZO-Act方法，利用输入激活构建固定低秩子空间，仅优化系数矩阵，降低扰动维度并支持Adam优化器，实现高效零阶微调，在多个LLM上取得一致提升。

链接：https://arxiv.org/abs/2607.01125

机构：University at Albany, SUNY（纽约州立大学奥尔巴尼分校）； IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）

作者：Xun Dong, Yibo Xu, Naigang Wang, Xin Li, Penghang Yin, Zi Yang

英文摘要：Zeroth-order (ZO) optimization enables fine-tuning large language models when backpropagation is unavailable or memory-prohibitive, but existing methods often perturb full model weights or randomly constructed low-dimensional subspaces, yielding high-variance estimates and limited performance. We propose ZO-Act, an activation-informed ZO fine-tuning method that restricts perturbations to a fixed low-rank subspace derived from input activations. For each linear layer, ZO-Act computes a small activation basis once at initialization and optimizes only lightweight coefficient matrices using forward-only loss evaluations. This reduces the effective perturbation dimension, exposes explicit trainable variables compatible with momentum-based optimizers such as Adam, and naturally supports quantized LLM fine-tuning by keeping low-bit weights frozen. We analyze ZO-Act as zeroth-order optimization over a restricted coefficient space and show that perturbing the low-dimensional coefficients reduces both the variance-dependent convergence term and the finite-difference error of the ZO estimator, at the cost of a controlled subspace approximation bias that is mitigated by the low-rank structure of LLM activations and gradients. Experiments on Llama-3-8B, OPT-13B, and INT4 Llama-3-8B show consistent gains over strong ZO fine-tuning baselines across language understanding, question answering, and commonsense reasoning.

AI 总结：提出基于三维高斯原语的显式模型压缩体积数据，通过加权聚合重建标量场，无需网格存储，在非结构化体积上全面超越隐式神经表示。

链接：https://arxiv.org/abs/2607.01164

作者：Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar

英文摘要： Recent work has shown that implicit neural representations (INRs) can be trained to effectively compress structured and unstructured volume data, allowing for direct data querying with a reduced memory footprint. However, as existing INRs for unstructured volumes do not encode geometry, they require partial mesh storage for later sampling, limiting achievable compression. At the same time, novel view synthesis methods have shown that explicit collections of 3D Gaussians can be used to accurately visualize volume data. In this work, we introduce an explicit model for volume data compression based on 3D Gaussian primitives. We reinterpret collections of 3D Gaussians as an explicit representation of a scalar field and use a sampling strategy that reconstructs scalar values at spatial locations through weighted aggregation of intersecting Gaussians. We develop optimized CUDA-accelerated pipelines for structured and unstructured model sampling, loss functions that encourage accurate domain encoding by our models, and a novel sampling-error based densification strategy. Our explicit formulation naturally encodes domain geometry, eliminating the need for mesh storage in unstructured volumes and introducing significantly higher compression opportunities. Compared to existing INRs, we demonstrate that our explicit model achieves competitive reconstruction quality with significant training speedups on structured volumes, while markedly outperforming in all metrics on unstructured volumes.

AI 总结：提出QuasiMoTTo方法，利用准蒙特卡洛相关采样替代独立同分布采样，在推理和强化学习中减少冗余，以更少样本达到相同性能。

链接：https://arxiv.org/abs/2607.01179

机构：Stanford University（斯坦福大学）

作者：Michael Y. Li, Anthony Zhan, Kanishk Gandhi, Noah D. Goodman, Emily B. Fox

英文摘要：Scaling inference compute, by generating many parallel attempts per problem, is a costly but reliable lever for improving language model capabilities. By default these attempts are generated independently, wasting inference compute on redundant solutions. This waste seems unavoidable. After all, independence is what makes parallel sampling trivial to scale. However, this tradeoff is not fundamental: there is a rich design space of samplers that generate correlated but exact samples entirely in parallel. We explore this design space as an avenue for improving sample efficiency in scaling inference compute and reinforcement learning (RL). Concretely, we introduce QuasiMoTTo, which uses correlated samples as a drop-in replacement for i.i.d. samples. To generate these samples, QuasiMoTTo uses a reparameterization of autoregressive sampling as inverse-CDF sampling and draws the underlying uniforms with quasi-Monte Carlo (QMC); because QMC spreads the uniforms out more evenly than i.i.d., the resulting samples cover the output space with far less redundancy. Even though the batch is correlated, each sample is marginally distributed according to the language model, so we can use the batch for policy-gradient training. Our empirical analysis focuses on understanding how efficiently QuasiMoTTo can turn compute into performance. To evaluate correlated samplers, whose dependence breaks standard pass@k estimators, we first develop an unbiased bootstrap estimator. Across four reasoning benchmarks, QuasiMoTTo matches i.i.d. pass@k accuracy with 25-47% fewer samples. Strikingly, QuasiMoTTo often saturates an upper bound on pass@k that holds for any marginal-preserving sampler. We also apply QuasiMoTTo to policy-gradient RL (GRPO) where it matches i.i.d. performance with 50% fewer training steps. These gains come from higher coverage, which yields a stronger learning signal per batch.

AI 总结：针对联邦学习中模型大小和类别数导致的通信瓶颈，提出TallyTrain方法，通过传输argmax类别索引将每个探针的通信量压缩至⌈log₂C⌉比特，在非独立同分布训练下优于软标签蒸馏，并在标准基准上匹配或超越软标签蒸馏，通信量降低三个数量级。

链接：https://arxiv.org/abs/2607.00173

机构：Cisco Systems Inc（思科系统公司）

作者：Radhakrishna Achanta, Will Reed

英文摘要：Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often parameter-averaging methods can afford to merge, and class count, which makes per-probe soft-label distillation prohibitive at large vocabularies. Both ceilings tighten as modern systems scale. We collapse the class-count axis to $\lceil \log_2 C \rceil$ bits per probe by transmitting only each peer's $\arg\max$ class index, where $C$ is the number of output classes. The resulting protocol, TallyTrain, is not merely compressed: under non-IID training it can be preferable to soft-label distillation, because under-trained peers are confidently wrong and majority voting filters this noise where soft-label averaging amplifies it. Across standard benchmarks, TallyTrain matches or beats soft-label distillation at up to three orders of magnitude less communication. We also relax the model-size axis: we compose the cheap hard-label consensus with sparse parameter merges to obtain a bandwidth-bridge variant, which Pareto-dominates every tested operating point of the standard FedAvg, FedProx and FedDF baselines.

AI 总结：针对数据稀缺联邦学习中稀疏模型发现困难，提出熵正则化概率门方法，通过维持门分布不确定性避免过早稀疏承诺，在异质性和稀疏性下提升统计性能与稀疏恢复精度。

链接：https://arxiv.org/abs/2607.00275

机构：Department of Engineering and Information Technology, Åbo Akademi University（奥布大学工程与信息技术系）

作者：Krishna Harsha Kovelakuntla Huthasana, Alireza Olama, Andreas Lundell

英文摘要：Federated Learning (FL) is a distributed machine learning (ML) paradigm with collaboration among multiple clients without sharing data. FL is challenging under data heterogeneity and partial client participation. Learning sparse models is useful for communication and computational efficiency in FL, but it is especially difficult in the small-sample high-dimensional regime (d >> N) where optimization can yield parameter configurations that fail to generalize to unseen test data. While magnitude-based pruning doesn't account for uncertainty exploration in the parameter space, a formulation with probabilistic gates and an L0 constraint allows sampling from competing sparse configurations during training. In this work, we study entropy regularization of gate distributions as a mechanism to maintain uncertainty in sparse federated optimization by preventing early commitment to sparse support. We examine its impact under data heterogeneity, client participation heterogeneity, and sparsity. Experiments on synthetic and real-world benchmarks show consistent improvements over federated iterative hard thresholding (Fed-IHT) and pruning after dense federated averaging (FedAvg) training, both in statistical performance on test data and in sparsity recovery accuracy.

AI 总结：针对概率预测中奖励信号噪声导致校准退化的问题，提出基于历史结果的无标签可验证奖励，结合梯度掩码保持推理链，使7B模型达到博彩市场校准水平。

链接：https://arxiv.org/abs/2607.00164

作者：Sadanand Singh, Allam Reddy, Manan Chopra

英文摘要：Reinforcement learning with verifiable rewards can in principle train calibrated probabilistic forecasters, since a proper scoring rule such as the Brier score is computed from outcomes alone and is minimized in expectation by the true probability. In practice it degrades calibration, and existing remedies address epistemic uncertainty, where a model's confidence accompanies a verifiably correct or incorrect answer. We study aleatoric forecasting, where the forecast itself is the output and the label is one stochastic outcome, taking NFL in-game win probability as a testbed with the betting market as a reference. Rewarding the realized per-play outcome fails, because the single outcome is a noisy target and the policy gradient corrupts the chain of thought. We introduce a verifiable, label-free reward, a state-conditioned empirical win rate estimated from past outcomes, that removes the label noise, and we keep the gradient off the reasoning, by direct prediction or a gradient mask, so it cannot be corrupted. Trained with this reward alone, without human labels or supervised fine-tuning, a 7B model reaches the calibration of the betting market by direct prediction and is better calibrated than a zero-shot frontier model. That frontier model and a tabular estimator reach the same Brier score as this model, identifying the market's small remaining edge as live in-game information beyond their shared inputs. Masking the gradient, rather than dropping the chain of thought, preserves reasoning from which the forecast follows, which ordinary chain-of-thought training corrupts.

AI 总结：研究通过七种训练方法构建54个模式生物，发现模式生物可解释性强烈依赖于训练目标、目标行为、模型架构和数据生成流程，集成训练通常比事后方法更不可解释，质疑当前模式生物作为可解释性代理的有效性。

链接：https://arxiv.org/abs/2607.01033

作者：Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere, Nikita Menon, Stefan Heimersheim

英文摘要：Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54 $\verb|OLMo2-1B|$- and $\verb|gemma-3-1b-it|$-based MOs trained with seven different techniques, including standard post-hoc SFT, post-hoc DPO, and more realistic integration of MO data into the OLMo post-training DPO phase. We use these MO variants to benchmark activation oracles, activation steering, logit lens, and sparse autoencoders. Our findings show that (i) MO interpretability depends strongly on training objective, target behaviour, model architecture, and training data generation pipeline; (ii) substantial variance remains even after controlling for differences in the strength of target behaviour expression; and (iii) our more realistic $\textit{integrated training}$ often yields less interpretable MOs than standard post-hoc methods. Our results cast substantial doubt on the validity of current MOs as interpretability proxies.

AI 总结：提出结构感知最优传输框架，利用最优传输理论捕获全局节点对应关系，结合跨任务知识蒸馏，在连续图学习中保持关系结构，显著提升分类准确率。

链接：https://arxiv.org/abs/2607.00377

作者：Yuting Zhang, Yanbei Liu, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang

英文摘要：Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce stability of individual node (or node-pair) embeddings. Due to optimizing nodes in isolation, these methods fail to maintain global relational structure, causing inter-node correspondences to progressively distort under continual learning. To this end, we propose a novel Structure-Aware Optimal Transport (SAOT) framework that explicitly captures and preserves relational structure within graph representations across sequential tasks. Specifically, SAOT leverages optimal transport theory to capture global inter-node correspondences, thereby facilitating and enhancing graph representation learning. Simultaneously, SAOT incorporates a cross-task knowledge distillation mechanism to preserve the previous structural knowledge. Extensive experiments on four CGL benchmark datasets demonstrate that SAOT outperforms existing self-supervised baselines. In particular, SAOT achieves significant performance gains, improving average accuracy by up to 5% on CoraFull-CL and over 15% on Products-CL compared with state-of-the-art methods in the Class-IL setting.

AI 总结：提出标签影响传播（LIP）模型，通过分解GNN的消息传递为传播和变换操作，量化标签间影响，构建标签影响图传播高阶影响，动态调整学习过程，在多标签节点分类任务上超越现有方法。

链接：https://arxiv.org/abs/2607.00671

机构：Zhejiang University（浙江大学）； National University of Singapore（新加坡国立大学）； Capital One； GrabTaxi Holdings Pte. Ltd.（GrabTaxi控股私人有限公司）

作者：Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony, Jia Chen, Bingsheng He

英文摘要： Graphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include proteins in PPI networks with multiple functions and users in social or e-commerce networks exhibiting diverse interests. Tackling multi-label node classification (MLNC) on graphs has led to the development of various approaches. Some methods leverage graph neural networks (GNNs) to exploit label co-occurrence correlations, while others incorporate label embeddings to capture label proximity. However, these approaches fail to account for the intricate influences between labels in non-Euclidean graph data. To address this issue, we decompose the message passing process in GNNs into two operations: propagation and transformation. We then conduct a comprehensive analysis and quantification of the influence correlations between labels in each operation. Building on these insights, we propose a novel model, Label Influence Propagation (LIP). Specifically, we construct a label influence graph based on the integrated label correlations. Then, we propagate high-order influences through this graph, dynamically adjusting the learning process by amplifying labels with positive contributions and mitigating those with negative influence. Finally, our framework is evaluated on comprehensive benchmark datasets, consistently outperforming SOTA methods across various settings, demonstrating its effectiveness on MLNC tasks.

AI 总结：针对新设备布局缺乏大规模数据集的问题，提出Device Passport通道嵌入技术，通过功能活动与元数据混合建模，实现跨布局迁移，在耳部脑电图等任务中优于基线。

链接：https://arxiv.org/abs/2607.00249

作者：Geeling Chau, Ran Liu, Juri Minxha, Wenhui Cui, Erdrin Azemi, Ellen L. Zippi, Behrooz Mahasseni, Christopher M. Sandino

英文摘要：New device layouts pose a challenging modeling problem due to the lack of large datasets for each specific layout. Biosignal foundation models offer a plausible solution if they are able to generalize to new layouts effectively. To improve cross-layout transfer, we study how different channel embedding techniques behave when pretraining layouts differ substantially from the downstream decoding layout. We propose Device Passport, a new channel embedding technique that learns experts and mixture models that take each channel's functional activity and metadata as input. This contrasts with prior embedding methods, which typically use only functional information or only metadata to look up learned or fixed positional embeddings. Across controlled subset-transfer experiments and realistic transfer to ear-EEG, Device Passport is competitive overall and improves over the strongest learned baseline in the layout-transfer regimes that motivate this work. These results suggest that channel embedding design is a key consideration when reusing large-scale pretrained biosignal models on new devices.

AI 总结：提出生成式元学习与人类反馈框架，通过专家直觉引导数据合成，利用条件神经ODE和强化学习迭代优化生成轨迹，理论证明分布对齐降低泛化误差，实验验证在分布偏移下提升鲁棒性。

链接：https://arxiv.org/abs/2607.00926

机构：School of Computer Science, University of Sheffield（谢菲尔德大学计算机科学学院）； Centre for Machine intelligence, University of Sheffield（谢菲尔德大学机器智能中心）； ELLIS Institute Finland（芬兰ELLIS研究所）； Department of Computer Science, Aalto University（阿尔托大学计算机科学系）

作者：Midhun Parakkal Unni, Samuel Kaski

英文摘要：Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF), a novel framework that bridges this domain gap by leveraging expert intuition to guide data synthesis. Grounded in a theoretical analysis of generalization error, we derive bounds demonstrating that aligning the distribution of generated data with human beliefs regarding the target physics significantly mitigates risk. GMHF operationalizes this insight by employing a Conditional Neural ODE (cNODE) as a generative digital twin, coupled with a Reinforcement Learning (RL) agent. The agent iteratively refines the latent physical parameters of the generated trajectories based on feedback, effectively steering the meta-learner toward the unobserved target distribution. Empirical validation on a nonlinear Duffing oscillator shows that GMHF substantially reduces deployment loss as expert reliability increases, and that the divergence between generated and target data falls under reliable feedback, directly corroborating the divergence-minimisation mechanism predicted by our theory. Further experiments on a non-dynamical probabilistic model confirm that the framework extends beyond ODE-governed systems, establishing human-AI collaboration as a rigorous catalyst for robust generalisation under distribution shift.

AI 总结：提出TRIE评估框架，用于检验随机PDE代理模型是否再现不变测度、提供可信预测不确定性并实现高效概率生成，在两类混沌SPDE上验证了生成模型优于点估计和近似不确定性方法。

链接：https://arxiv.org/abs/2607.00196

机构：Stevens Institute of Technology（史蒂文斯理工学院）； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）

作者：Bharat Srikishan, Javier E. Santos, Nikhil Muralidhar, Charles D. Young

英文摘要： Many scientific systems exhibit uncertainty from stochastic forcing, unresolved degrees of freedom, or imperfect observations, making reliable surrogate forecasting fundamentally distributional rather than pointwise. For such systems, deterministic neural surrogates fail to capture statistical measures and forecast uncertainty. We introduce TRIE, an evaluation framework for stochastic PDE surrogates that asks whether models reproduce invariant measures, provide trustworthy predictive uncertainty, and scale to efficient probabilistic generation. We demonstrate TRIE on two stationary chaotic spatially extended SPDEs, stochastic Kuramoto--Sivashinsky and stochastic Kolmogorov flow, across 11 parameter values. Our evaluation shows that standard pointwise-trained neural surrogates can produce plausible short rollouts while failing to match long-time statistical structure. Approximate uncertainty methods such as Monte Carlo dropout and heteroscedastic Gaussian likelihoods produce stochastic forecasts, but are often miscalibrated and overconfident under temporal and spatial uncertainty diagnostics. Across these criteria, generative models provide the most consistent performance, accurately capturing invariant measure statistics and achieving the lowest CRPS in all reported probabilistic settings. Finally, we show that latent generative models with automatic dimension discovery retain much of this statistical fidelity while reducing Kolmogorov inference time by roughly $12\times$. We release our code and data at this https URL to support reproducible evaluation of stochastic PDE forecasting models.

AI 总结：本研究在十个复杂系统上评估三十多种候选度量，发现只有包含未映射变量忠实性检验的因果度量能可靠区分有效与无效抽象，并提出了因果抽象误差（CAE）作为通用有效性度量。

链接：https://arxiv.org/abs/2607.00267

作者：Maxime Méloux, Tiago Pimentel, François Portet, Maxime Peyrard

英文摘要：A central goal of science is to produce valid explanations of complex systems: high-level causal accounts that faithfully reflect the behavior of lower-level mechanisms. Yet no consensus exists on how to measure whether a proposed high-level explanation is actually valid. We introduce a benchmark of ten complex systems spanning both discrete and continuous state spaces, as well as static and dynamical regimes, each equipped with consensual ground-truth causal explanations and invalid contrastive conditions. Within a unified causal abstraction framework, we systematically evaluate over thirty candidate metrics drawn from observational, functional, information-theoretic, and causal families. Our results show that only the latter reliably discriminates valid from invalid abstractions, and only when incorporating faithfulness testing over unmapped variables. Building on these findings, we introduce the Causal Abstraction Error (CAE), a continuous validity metric with an explicit faithfulness test, which passes all discrimination tests across every system and can converge with as few as 30 sampled interventions. We offer it as a general-purpose metric for the discovery and validation of high-level explanations.

AI 总结：提出四阶段诊断方法评估LLM在陌生物理框架中的推理能力，在三个平行世界测试发现定性-定量不对称及自我审查薄弱。

链接：https://arxiv.org/abs/2607.00276

作者：Dong Zhang

英文摘要：Current large-language-model (LLM) physics benchmarks are usually scored by answer accuracy, which cannot distinguish genuine reasoning from recall of familiar problem patterns and reveals little about where a model's reasoning breaks down. We introduce an auditable four-stage diagnostic that evaluates whether an LLM can reason inside an unfamiliar physics framework through induction, formulation, prediction, and review. The diagnostic combines locked pre-registrations, fresh sessions between stages, dual-LLM judging, and a human-audit pathway, and we apply it to three parallel physics worlds: a single-equation counterfactual world ($F=mv$), a historical framework (Aristotelian mechanics), and a four-domain counterfactual world (Decay World). Across Claude Opus 4.7, GPT-5.5, and Gemini 3.1 Pro, the three worlds yield composite PASS rates are 6/15, 6/15, and 0/15 respectively (content $\land$ structural for $F=mv$ and Aristotelian, content axis only for Decay World where the structural axis is out of scope). The most pointed empirical pattern is a qualitative-versus-quantitative asymmetry: in Decay World, models almost never predict the wrong direction of change, but frequently compute the wrong ratio by slipping back to standard-physics relations. The protocol also surfaces two methodology findings: LLM-judge reliability does not transfer across frameworks, and Stage 4 self-review is weak in every framework, with the model's own review wrongly reporting no earlier error in at least two-thirds of the trials that actually contained one. We release the full prompts, responses, verdicts, and audit records.

AI 总结：提出EPC协议，通过四阶段隔离范式标准化测量LLM智能体系统中评估者偏好耦合现象，并提供参考快照和版本约定以支持复现、比较和衰减检测。

链接：https://arxiv.org/abs/2607.00297

作者：Zewen Liu

英文摘要：When LLM agents use evaluator feedback to adapt their behavior in closed loops, evaluator biases propagate through the agent's strategy distribution -- a phenomenon known as evaluator preference coupling. Prior work has documented coupling across multiple evaluator families and model versions, but the field lacks a standardized protocol that enables third-party researchers to (i) reproduce coupling measurements, (ii) compare results across evaluators and time points, and (iii) detect measurement decay as proprietary evaluators silently update. This paper provides the protocol. We specify EPC (Evaluator Preference Coupling) -- a detailed, RFC-style protocol specification for the four-phase isolation paradigm, covering executor and evaluator configuration, strategy and task design, the TTRL update rule, metric computation (gamma, JSD, ECE, Brier), and output schema. We accompany the protocol with a versioned Reference Snapshot v1.0: coupling measurements for eight evaluator conditions (N=122 unique experimental repetitions across GPT-4o, Qwen, DeepSeek, and others) derived from five independent studies, annotated with evaluator version identifiers, API endpoints, and measurement dates. The snapshot is explicitly time-bound: all values are conditional on specific model versions and are expected to decay as proprietary evaluators update. We define a versioning convention (vX.Y-Z, encoding protocol version, snapshot version, and evaluator generation) and provide a usage guide covering adoption, interpretation, and known pitfalls. The protocol, reference snapshot, and implementation code are released as open infrastructure.

AI 总结：通过扩展至11种评估条件，实证验证了LLM评估系统中评估器耦合、策略多样性与小样本测量可靠性之间的权衡，并发布了标准化基准数据集。

链接：https://arxiv.org/abs/2607.00304

作者：Zewen Liu

英文摘要： The bias-reliability tradeoff conjectures that LLM evaluation systems are constrained in (gamma, H, CV) space, where evaluator coupling (gamma), strategy diversity (H), and small-sample measurement reliability (CV(N)) cannot be simultaneously optimized at fixed sample size N. Prior evidence rests on n=5 conditions with complete metrics from a single study. We expand the empirical base to 11 conditions, measuring gamma and H for all 11 (nine with valid weight vectors) and CV(N=5) for seven with sufficient seeds (N >= 5). Five conditions provide the complete (gamma, H, CV) triple. The data confirm the trade-off: conditions with low evaluator coupling (gamma < 0.2) exhibit high measurement noise (CV(N=5) > 1.0), while conditions with strong coupling (gamma > 0.9) achieve low noise (CV(N=5) < 0.16). The correlation r(H, gamma) = -0.989 (n=5, excluding GPT-4o conditions) confirms that evaluator coupling suppresses strategy diversity. Four GPT-4o conditions show gamma=0.000 and H=1.000 across all seeds -- a pattern we attribute to version drift in the June 2026 GPT-4o API. No condition occupies the region {gamma < 0.2, CV(N=5) < 0.3}. We release all per-condition metrics as a standardized benchmark dataset for evaluator comparison.

AI 总结：针对生成模型训练数据成员推断难题，提出基于水印的数据集推断方法，在子集暴露充分时达到与传统损失法相当的检测性能。

链接：https://arxiv.org/abs/2607.00325

机构：University of Maryland（马里兰大学）； Lawrence Livermore National Labs（劳伦斯利弗莫尔国家实验室）

作者：John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein

英文摘要：A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output watermarking techniques are the right gadget to make training membership tests for generative models more tractable, based on prior results showing that language models exhibit residual watermark "radioactivity" under partially watermarked training datasets. We pit a watermark-based dataset inference approach head-to-head against traditional loss-based membership inference methods and show that watermarking can achieve comparable membership detection performance when subset exposure is high enough, under an alternate set of assumptions.

AI 总结：针对健康信号数字孪生的预测模型，提出TimeSynth框架，通过生理信号生成器和保真度诊断，揭示点式指标无法检测的相位、频率等动态特性丢失问题，并指导模型选择。

链接：https://arxiv.org/abs/2607.00431

机构：Scientific Computing and Imaging Institute, University of Utah（犹他大学科学计算与成像研究所）； Kahlert School of Computing, University of Utah（犹他大学卡勒特计算学院）； Department of Psychiatry, University of Utah（犹他大学精神病学系）

作者：Md Rakibul Haque, Shireen Elhabian, Warren Woodrich Pettine

英文摘要：Forecasting models for health-signal digital twins must preserve the oscillatory, frequency, phase, and state-transition dynamics of physiological signals, yet the pointwise metrics used to benchmark them cannot detect when these fundamental properties are lost. We show that this blind spot misranks models: across 11 architectures, models with comparable pointwise error diverge by up to 53° in phase accuracy, equivalent to roughly 123 ms for a 1.2 Hz cardiac rhythm and invisible to standard metrics. To enable development of models that escape such failures, we introduce TimeSynth, a controlled benchmarking framework with two reusable components: a physiologically grounded generator producing signals with analytically known ground-truth dynamics from parametric models fitted to real electroencephalography, electrocardiography and photoplethysmogram signals, along with diagnostics quantifying amplitude, frequency, phase, and state-transition fidelity. Linear and full-sequence attention models systematically lose frequency and phase information despite acceptable amplitude error, whereas architectures with localized temporal structure better preserve dynamical fidelity and adapt to observable state transitions; none, however, reliably preserves stochastic switching. Because the dominant determinant of fidelity is architectural, model choice becomes a principled, use-case-driven decision rather than a search for a single winner. TimeSynth thus supplies the controlled preclinical stress test missing before models are coupled to patient data, with a reusable generator and diagnostics for fidelity-aware development.

AI 总结：提出MolSafeEval基准，通过构建分子安全知识图谱和基于大语言模型的推理，系统评估四类分子生成模型的安全风险，揭示当前方法的漏洞。

链接：https://arxiv.org/abs/2607.00464

机构：Zhejiang University（浙江大学）； ZJU-Hangzhou Global Scientific and Technological Innovation Center（浙大-杭州全球科技创新中心）； University of Oxford（牛津大学）

作者：Tong Xu, Xinzhe Cao, Zhihui Zhu, Keyan Ding, Huajun Chen

英文摘要：Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern: the potential safety risks of AI-generated molecules. In practice, many generative models may produce molecules with toxic, reactive, or otherwise hazardous characteristics - posing hidden dangers that remain insufficiently addressed. To address this gap, we introduce MolSafeEval, a benchmark dedicated to evaluating and analyzing the safety risks of molecular generation. Unlike prior approaches that rely on narrow toxicity predictors, MolSafeEval integrates heterogeneous safety knowledge - ranging from toxicological databases to hazard rules - into a structured molecular safety knowledge graph. This graph serves as a foundation for large language model-based reasoning, enabling systematic detection and explanation of unsafe features in generated compounds. We further categorize molecular generative models into four representative task types - unconditional generation, property optimization, target protein-based design, and text-based generation - and provide standardized datasets and safety evaluation protocols for each. By systematically revealing the safety vulnerabilities of current generative approaches, MolSafeEval offers a new lens for benchmarking molecular models and provides essential guidance toward safer, more trustworthy molecular design.

AI 总结：本研究基于KKBox数据集，通过九窗口充分性曲线发现手动续费用户早期行为在45-90天窗口内对流失预测提升显著，但曲线随实验设计（如移动目标、特征集）变化，强调窗口充分性声明需明确队列构建、目标定义和特征族。

链接：https://arxiv.org/abs/2607.00473

机构：Goizueta Business School（戈伊苏埃塔商学院）； College of Computing（计算机学院）； Pratt School of Engineering（普拉特工程学院）； Emory University（埃默里大学）； Georgia Institute of Technology（佐治亚理工学院）； Duke University（杜克大学）

作者：Xiao Han, Yao Xiao, Chenyu Wu, Tongchen Zhang

英文摘要：How many days of early behavior suffice for subscription churn prediction? In the public KKBox dataset, the early indicator of churn is typically an indicator of someone's contract status; however, when looking in the heavily churned manual-renewal segment, having access to early behavior creates a substantial increase in prediction for that specific segment (PR +0.10 at 120 days). A nine-window sufficiency curve shows a diminishing-returns knee in a 45-90 day band. However, stress-testing over three cohort/task designs shows that this curve is singular to the design being tested; for example, in our test with a moving target, the curve inverts and can shift depending on the feature set used. Therefore, any window-sufficiency claim should state its cohort construction, target definition, and feature families. All evidence is from one music-streaming dataset; the mechanism should generalize but the magnitudes may not.

AI 总结：在IEEE-CIS欺诈数据集上比较7种分类编码方法，实体嵌入在AUC-ROC上最优（0.9612），与CatBoost（0.9602）无显著差异，优于其他编码器；CatBoost在AUC-PR上领先（0.822 vs 0.793），无编码器同时主导两个指标。

链接：https://arxiv.org/abs/2607.00477

作者：Xiao Han, Jingjing Liu, Moxuan Zheng, Zhen Zhang, Chenyu Wu

英文摘要：A total of seven categorical encoding methods were tested on the IEEE-CIS fraud benchmark dataset (590,540 records, 3.5% positives, 8 high-cardinality columns). The encoders were evaluated using a stratified 5-fold cross-validation (CV) with three repetitions. Five of the encoders had identical frozen LightGBM learners in the downstream phase, allowing for controlled comparisons of their performance to each other. CatBoost and TabNet were included as comparisons across paradigms using different learners. The entity embeddings produced the highest AUC-ROC (0.9612), with a statistically significant tie with that of CatBoost (0.9602) and statistically superior to tier group encoding (0.9548), whereas target encoding was only 0.0023 worse than tier group encoding and the auditor-friendly tier boundaries were maintained. Off-the-shelf TabNet did not outperform tree-based pipelines and collapsed under data scarcity. On AUC-PR, CatBoost leads (0.822 vs. 0.793); no encoder dominated both metrics. Per-column analysis confirmed the embedding advantage arises from joint multi-column representation.

AI 总结：研究通过分析13种指标与拼写速率的相关性，发现Brier分数、MCC、ROC AUC、PR AUC、AP和pAUC最能反映ERP-BCI中的拼写性能。

链接：https://arxiv.org/abs/2607.00794

机构：Intelligent Systems Research Laboratory (LARESI)（智能系统研究实验室 (LARESI)）； USTOMB（奥兰科技大学）

作者：Okba Bekhelifi, Naoual El Djouher Mebtouche

英文摘要：For predictive models, the often-reported performance metrics are the loss and accuracy. In synchronous Brain- Computer Interface (BCI) systems, these metrics are informative for most BCI paradigms; however, for Event-Related Potential (ERP) applications the spelling rate, which measures the number of characters correctly selected is more important as it influences the estimation of information transfer rate (ITR) and any related metric measuring spelling performance. Moreover, ERP-based BCIs hold imbalanced data class distributions, which require reporting metrics that can handle the imbalance, such as the area under the receiver operating characteristic curve (ROC AUC). In this work, we study the correlation of the spelling rate with 13 metrics to identify which among them best reflect user spelling performance and how they are affected by trial repetition. The Results of two datasets (a private LARESI ERP dataset and the public OpenBMI ERP dataset) favor the Brier score, Matthews Correlation Coefficient (MCC), and the metrics that account for class imbalance in binary classification: ROC AUC, area under the Precision-Recall curve (PR AUC), Average Precision (AP), and partial AUC (pAUC). These findings encourage researchers and practitioners to report those metrics in ERP-based BCI experiments.

AI 总结：提出Aionoscope，一种基于生成器的诊断工具，用于调试冻结时间序列表示中的潜在状态可访问性，揭示粗粒度和细粒度可访问性之间的不匹配。

链接：https://arxiv.org/abs/2607.00956

机构：Langotime South Africa（Langotime 南非）； Griffith University（格里菲斯大学）； Brown University（布朗大学）

作者：Alexander Chemeris, Ming Jin, Randall Balestriero

英文摘要：Time-series models are often evaluated by what they can forecast or classify, but those scores do not show whether their representations preserve the process state a user may want to inspect: event timing, phase, amplitude, frequency, or regime variables. We introduce Aionoscope, a generator-based diagnostic tool for debugging latent-state accessibility in frozen time-series representations. Aionoscope separates process generation from observation rendering, producing seeded synthetic streams with exact categorical and dense labels across mixture complexity and nuisance variation. We instantiate Aionoscope as Primitive Process Mixtures and evaluate 37 model-plus-adapter systems with a common pooled linear-probe protocol. The main result is a mismatch between coarse and fine-grained accessibility. Most systems make component presence easy to recover, but expose dense process state much less reliably: the highest observed dense-probe row reaches 0.689 mean masked $R^2$, while a dense-feature oracle reaches 0.999. This is the failure mode Aionoscope is designed to surface: a representation can look informative at the level of "what kind of signal is present" while hiding the timing, phase, amplitude, frequency, or regime variables needed for debugging.

AI 总结：提出Seahorse统一框架，通过编码-演化-解码接口标准化神经时空点过程，实现公平比较与诊断分析，并引入合成压力测试套件揭示各模型族的归纳偏差。

链接：https://arxiv.org/abs/2607.01022

机构：German Research Center for Artificial Intelligence (DFKI), Data Science and its Applications Research Group, Kaiserslautern, Germany（德国人工智能研究中心（DFKI），数据科学及其应用研究组，凯泽斯劳滕，德国）； Department of Computer Science, Rhineland-Palatinate Technical University of Kaiserslautern-Landau (RPTU), Kaiserslautern, Germany（计算机科学系，莱茵兰-普法尔茨凯泽斯劳滕-兰道工业大学（RPTU），凯泽斯劳滕，德国）

作者：Yahya Aalaila, Gerrit Großmann, Sebastian Vollmer

英文摘要：Spatiotemporal point processes (STPPs) model event data in continuous time and space, with applications in mobility, epidemiology, and public safety. Recent neural STPPs span expressive intensity models, conditional density models, continuous-time latent dynamics, normalizing-flow spatial decoders, and score-based generative mechanisms. Yet comparison remains fragile because implementations differ in preprocessing, coordinate normalization, splits, likelihood conventions, and evaluation protocols. We present SEAHORSE, a unified framework for reproducible STPP experimentation. SEAHORSE formalizes neural STPPs through a common encode-evolve-decode interface and trains, tunes, and evaluates every model family under a single executable benchmark protocol with raw-coordinate likelihood reporting. This enables fair comparisons but, more importantly, controlled diagnostic studies. We pair SEAHORSE with HawkesNest, a synthetic stress-test suite, and show that increasing event-pattern complexity exposes each family's inductive bias, degrading some models sharply and leaving others stable. Code: this https URL.

AI 总结：提出CausalMix框架，将数据混合优化视为因果推断问题，通过条件平均处理效应估计最优混合比例，在7B模型上提升多任务性能，并具备可解释性。

链接：https://arxiv.org/abs/2607.01104

机构：Tsinghua University（清华大学）； Ant Group（蚂蚁集团）； Renmin University of China（中国人民大学）

作者：Zinan Tang, Yukun Zhang, Shaomian Zheng, Zhuoshi Pan, Qizhi Pei, Dingnan Jin, Jun Zhou, Yujun Wang, Biqing Huang

英文摘要：In Large Language Model (LLM) training, data mixing plays a pivotal role in determining model performance. Recent methods optimize mixture weights via proxy models, but they rely on the assumption of static data distributions. As a result, when the underlying data pool shifts, these methods require costly retraining from scratch. This limitation restricts their ability to scale seamlessly from small settings to larger data pools and model sizes. In this paper, we propose CausalMix to address this limitation by casting data mixture optimization as a causal inference problem. We formulate the statistical features of the data pool as covariates and the domain mixture as the treatment. After fitting a causal model on 512 runs of Qwen2.5-0.5B to estimate the Conditional Average Treatment Effect (CATE), we extrapolate the optimal mixture for an 800K data pool and apply it to train a 7B model. Furthermore, we successfully generalize the framework to long chain-of-thought data on Qwen3-4B-Base. By leveraging causal modeling to isolate confounding biases, CausalMix dynamically infers state-dependent optimal data mixtures. Extensive experiments show that the mixture guided by CausalMix consistently improves performance across multiple downstream tasks, outperforming RegMix and other baselines. In addition, we use the CATE Interpreter to provide visual analysis of the learned mixing strategy. Overall, CausalMix offers a causal and interpretable framework for optimizing LLM data mixtures.

AI 总结：提出基于 xLSTM 的循环时间序列基础模型 TiRex-2，通过记忆中心设计实现多变量预测与流式处理，在零样本任务上达到最优性能。

链接：https://arxiv.org/abs/2607.01204

机构：ELLIS Unit Linz, LIT AI Lab & Institute for Machine Learning, JKU Linz, Austria（ELLIS 林茨单元，LIT AI 实验室与机器学习研究所，林茨约翰·开普勒大学，奥地利）； NXAI Lab, Linz, Austria（NXAI 实验室，林茨，奥地利）； NXAI GmbH, Linz, Austria（NXAI 有限公司，林茨，奥地利）； Interdisciplinary Transformation University Austria, Linz, Austria（奥地利跨学科转型大学，林茨，奥地利）

作者：Patrick Podest, Marco Pichler, Elias Bürger, Levente Zólyomi, Bernhard Voggenberger, Wilhelm Berghammer, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter

英文摘要：We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-centric recurrent design that operates at constant per-patch cost under streaming. The model combines a bidirectional time mixer with an asymmetric grouped-attention variate mixer, enabling the integration of future-known covariates while preserving strict causality over target variables. To our knowledge, this is the first time series foundation model that achieves this combination of properties. To support scalable multivariate pretraining, we propose a synthetic coupling pipeline that composes diverse multivariate samples on the fly from large univariate corpora. Empirically, TiRex-2 achieves state-of-the-art zero-shot performance on GIFT-Eval and fev-bench, remains stable when streamed to arbitrary context lengths, and maintains constant inference cost per patch. The model uses 38.4M active parameters in univariate mode, with an additional 44.1M parameters activated for multivariate forecasting.

AI 总结：针对含噪数据学习动力系统问题，提出弱形式核岭回归（WKRR），结合弱形式滤波与核方法，实现噪声鲁棒性，在混沌系统和真实流体数据中优于基线方法。

链接：https://arxiv.org/abs/2607.00257

机构：The Pennsylvania State University（宾夕法尼亚州立大学）； Department of Mathematics（数学系）； Institute for Computational and Data Sciences（计算与数据科学研究所）； Department of Aerospace Engineering（航空航天工程系）

作者：Max Kreider, John Harlim, Daning Huang

英文摘要： Accurate prediction of complex dynamical systems from noisy measurements remains a significant challenge in scientific computing. Kernel ridge regression learning strategies are often effective when applied to clean data, but have limited success with noisy data. Recent work has observed that a weak formulation can act to filter noisy data, and different learning strategies have achieved increased noise robustness with a weak-form framework. In this manuscript, we give an overview of the filtering mechanism behind the weak formulation and provide a bias-variance error decomposition. Using these insights, we combine a weak formulation with a kernel learning strategy to propose Weak-form Kernel Ridge Regression (WKRR) for learning dynamical systems. The proposed framework is simple to implement, effective for both clean and noisy data, and outperforms several baseline methods. We demonstrate the performance of WKRR on chaotic benchmark systems in up to 64 dimensions, as well as 15,000-dimensional real-world fluid data.

AI 总结：结合经济建模与因果推断，分析客人对价格等因素的响应及偏好异质性，以优化定价工具和个性化推荐，提升市场匹配效率。

链接：https://arxiv.org/abs/2607.00280

作者：Yufei Wu, Daniel Schmierer

英文摘要：Airbnb is a community based on connection and belonging -- many hosts on Airbnb are everyday people who share their worlds to provide guests with the feeling of connection and being at home; Airbnb strives to connect people and places. Among our efforts to connect guests and hosts, we provide tools to enable hosts to set competitive prices, which helps improve affordability for guests while helping hosts get more bookings. We also personalize the guest experience to show them the listings that match their needs. To help inform these efforts, we combine economic modeling and causal inference techniques to understand how guests book stays based on the prices hosts set, among other factors, and how that preference varies across different guests and listings. Such understanding helps us identify opportunities for Airbnb to support the marketplace and better connect guests and hosts. For example, understanding how much guests respond to different prices helps optimize the tools that we provide to hosts, in order to enable hosts to choose and set competitive prices that further balance demand and supply. As another example, understanding heterogeneity in guest preferences helps us personalize the guest experience and better match them with the listings that meet their needs, based on how much they respond to different prices and other factors.

AI 总结：提出PRISM框架，通过可微分通道加权和置信度过滤伪标签的半监督域适应，解决脑电情绪识别中的通道冗余和跨被试差异问题，在三个数据集上超越现有方法。

链接：https://arxiv.org/abs/2607.00358

作者：Xin Zhou, Xiang Zhang, Hao Deng, Lijun Yin

英文摘要：Electroencephalogram (EEG) captures endogenous brain activity with high temporal fidelity and holds substantial promise for precise emotion decoding. However, channel redundancy and pronounced inter-subject variability remain key obstacles to scalable generalization. To address these limitations, we propose a novel framework termed PRioritized channel Importance with Semi-supervised doMain adaptation (PRISM), enabling label-efficient cross-subject emotion decoding. On the channel side, PRISM assigns differentiable, data-dependent channel weights via a lightweight expert ensemble, amplifying reliable electrodes while suppressing distractors. On the domain side, PRISM leverages unlabeled data through confidence-filtered pseudo-labels to drive consistency regularization and domain alignment, mitigating subject-specific heterogeneity. Extensive experiments show that PRISM surpasses state-of-the-art methods on DEAP, DREAMER, and SEED datasets, achieving robust cross-subject generalization given limited annotations.

AI 总结：提出端到端决策聚焦学习框架，通过可微凸优化层和平滑top-k算子直接优化投资组合性能，在四个主要股票市场取得优于基线的样本外夏普比率。

链接：https://arxiv.org/abs/2607.00581

作者：Haeun Jeon, Seunghoon Choi, Hyunglip Bae, Yongjae Lee, Woo Chang Kim

英文摘要：Sparse tangent portfolio optimization aims to learn an interpretable, low-cardinality portfolio in the tangency direction of the mean-variance frontier. However, the associated cardinality-constrained formulation is NP-hard, and standard predict-then-optimize pipelines often misalign forecasting accuracy with downstream portfolio quality. We propose an end-to-end decision-focused learning framework that reformulates Sharpe ratio maximization as a Disciplined Parametrized Programming (DPP)-compliant convex programming layer and replaces discrete selection with a smooth top-$k$ operator enforcing an exact cardinality $k$. This enables gradient flow through prediction, asset selection, and re-optimization, allowing the predictive model to directly optimize portfolio performance. Across four major equity markets, our method achieves competitive and often superior out-of-sample Sharpe ratios compared with historical and prediction-focused baselines, with particularly strong gains in larger asset universes. Our \href{ this https URL }{code} is publicly available.

AI 总结：提出一种结合主动学习的框架，通过掩码重建反馈和极小极大学习策略，增强无监督模型对细微噪声异常的检测能力，在28个测试案例中AUC提升12.39%。

链接：https://arxiv.org/abs/2607.00720

机构：LG CNS； Department of Industrial & Management Engineering, Korea University（高丽大学产业与管理工程系）； Department of Industrial Engineering, Seoul National University（首尔大学工业工程系）

作者：Seung Hun Han, Hyeongwon Kang, Jinwoo Park, Pilsung Kang

英文摘要： Despite the increasing sophistication of industrial AI systems, the ability to reliably detect subtle and noisy anomalies in complex time series data remains a critical yet unresolved challenge. In large-scale industrial applications, labeling time series data is often prohibitively expensive and time-consuming, making unsupervised learning a practical and widely adopted approach. However, existing unsupervised methods frequently struggle to distinguish near-normal anomalies from normal patterns and are vulnerable to noise contamination within normal samples. To address these limitations, we propose a novel framework that leverages active learning to iteratively enhance the performance of unsupervised models. Our framework's core contributions are (1) a masked time-series reconstruction feedback strategy that forces the model to learn robust temporal dependencies, and (2) a minimax learning strategy that promotes robustness by differentially treating normal and abnormal samples. This process encourages the model to better capture the dynamics of subtle and noisy patterns. The proposed framework is evaluated across 28 test cases involving four multivariate time-series datasets and seven unsupervised backbone models. Experimental results demonstrate a 12.39% improvement in AUC compared to the original models, confirming that our method can be readily integrated into existing unsupervised reconstruction-based anomaly detection systems to significantly enhance their performance.

AI 总结：提出AgentODE框架，利用LLM提出候选ODE结构，并通过工具增强的推理代理仅基于群体级汇总统计量迭代优化参数分布，实现从稀疏、噪声数据中发现可解释的ODE结构。

链接：https://arxiv.org/abs/2607.00733

机构：Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center, University of Freiburg（弗莱堡大学医学中心与医学院医学统计与生物统计研究所）； Department of Dermatology, Medical Faculty and Medical Center, University of Freiburg（弗莱堡大学医学中心与医学院皮肤科）； Prior Labs, University of Freiburg（弗莱堡大学Prior实验室）

作者：Hanning Yang, Meropi Karakioulaki, Lennart Purucker, Tim Litwin, Cristina Has, Moritz Hess

英文摘要：Mechanistic modeling via ordinary differential equations (ODEs) provides interpretable descriptions of complex dynamics and enables inference of underlying mechanisms, which is particularly valuable in clinical settings. However, in rare diseases, both the structure and parameters of the model are typically unknown, while individual-level data is scarce, noisy, heterogeneous, and subject to privacy constraints. In such settings, population-level summary statistics provide a practical privacy-preserving data representation, while capturing heterogeneity further requires modeling parameters as distributions rather than fixed values. Yet no existing method jointly discovers ODE structure and refines parameter distributions solely from summary statistics. We present AgentODE, an end-to-end framework that addresses this gap. An LLM proposes candidate ODE structures, while a tool-augmented inference agent iteratively refines parameter distributions through a diagnosis--update loop, operating on population-level summary statistics alone. We evaluate AgentODE on three benchmark problems across different fields and two clinical datasets, including the rare disease recessive dystrophic epidermolysis bullosa (RDEB), with only 231 observations across 46 patients. AgentODE recovers functionally consistent ODE structures across all settings, and experiments on RDEB demonstrates that in sparse and noisy data settings reasoning from summary statistics promotes mechanistically principled structure discovery, whereas baselines with individual-level data access recover implausible structures despite better predictive performance. AgentODE opens new possibilities for mechanistic modeling of rare diseases directly from population-level summary statistics, where data scarcity and privacy constraints have traditionally limited such analyses.

AI 总结：提出机器学习方法，利用便携式MyNIR设备获取的NIR光谱数据，结合SG滤波、NIPALS异常值去除等预处理和堆叠集成学习模型，实现Oxisol和Inceptisol土壤中碳氮含量的快速定量，RPD>2.0且过拟合低。

链接：https://arxiv.org/abs/2607.00834

机构：Graduate Program in Electrical and Computer Engineering, Federal University of Technology - Paraná（巴拉那联邦科技大学电气与计算机工程研究生项目）； Academic Department of Chemistry, Federal University of Technology-Paraná（巴拉那联邦科技大学化学系）； Graduate Program in Production and Systems Engineering, Federal University of Technology-Paraná（巴拉那联邦科技大学生产与系统工程研究生项目）

作者：Vinicius Herique Kieling, Guilherme Macedo Baggio, Felipe Augusto Bueno Rossi, Marco Antonio de Castro Barbosa, Dalcimar Casanova, Larissa Macedo dos Santos Tonial, Jefferson Tales Oliva

英文摘要：Near-Infrared (NIR) spectroscopy has emerged as a promising alternative to traditional soil analysis methods, offering advantages such as speed, low cost, and non-destructive testing. This work proposes a machine learning (ML) approach to calibrate predictive models for carbon (C) and nitrogen (N) content in Oxisols and Inceptisols, utilizing NIR spectral data acquired with a portable MyNIR device. Various preprocessing methods were evaluated, with the most effective being the Savitzky-Golay (SG) filter and a robust outlier removal method based on the Nonlinear Iterative Partial Least Squares (NIPALS) algorithm coupled with a Huber loss function. Multiple validation strategies were compared, including 10-fold cross-validation, leave-one-out, and holdout via the Kennard-Stone method, followed by standardization. Stacking ensemble learning models were employed, using Partial Least Squares (PLS), Support Vector Regression (SVR), and Ridge as base models, with linear regression as the meta-model. The models were evaluated using R2, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Ratio of Performance Deviation (RPD) metrics. The performance gap between soil types suggests the influence of pedological characteristics. Furthermore, the models achieved an RPD > 2.0 with low overfitting, validating the potential of this approach for rapid C and N quantification. This study contributes to the optimization of sustainable agricultural practices, aligning with the demand for efficient and environmentally friendly analytical methods. The developed technique enables faster decision-making for producers and consultants based on organic matter content, fertility indicators, and nutrient availability.

AI 总结：提出ILLUME+框架，通过多形式解释超越单基因重要性评分，提高基因重要性稳定性，恢复已知药物-基因关联并发现新分子信号。

链接：https://arxiv.org/abs/2607.00931

机构：University of Pisa（比萨大学）； EMBL-EBI（欧洲分子生物学实验室-欧洲生物信息学研究所）； ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）

作者：Martino Ciaperoni, Margherita Lalli, Simone Piaggesi, Martina Varisco, Francesco Carli, Riccardo Guidotti, Dino Pedreschi, Francesco Raimondi, Fosca Giannotti

英文摘要： Predicting cancer drug response from transcriptomic profiles is a cornerstone of precision oncology, yet the scientific value of machine learning models hinges not solely on predictive accuracy, but also on their capacity to generate reliable biological insights. Current explainability approaches in this setting are computationally costly, lack robustness, and reduce complex drug response to univariate gene importance scores, overlooking the coordinated gene activity that drives sensitivity and resistance. In this work, we present ILLUME+, a scalable post-hoc explainability framework that moves beyond single-gene assessments to capture multiple, complementary forms of explanation. Integrated into our end-to-end pipeline, ILLUME+ produces more stable gene importance scores than existing baselines, recovers established drug-gene associations and mechanisms of action, and enables AI-assisted hypothesis generation to uncover novel interaction-driven molecular signals in cancer biology.

AI 总结：研究通过语音自动区分压力与非压力情境，并预测生理和情感压力反应，使用TSST实验数据，结合说话人分割和机器学习模型，实现了高于基线的检测性能。

链接：https://arxiv.org/abs/2607.00986

机构：Human-Centered Artificial Intelligence Group, Faculty of Technology, Bielefeld University（比勒费尔德大学技术学院人本人工智能研究组）； Department of Cognitive Psychology, Faculty of Psychology, Ruhr University Bochum（波鸿鲁尔大学心理学院认知心理学系）

作者：Hanna Drimalla, Wieland R. Cremer, Christine Kraus, Oliver T. Wolf

英文摘要：Automatically detecting stress in speech provides an unobtrusive way to gain insights relevant to behavioral research or clinical assessment. This study investigates the automatic differentiation between a stressful and non-stressful situation, and the prediction of physiological and affective stress responses. Speech data was collected from 50 participants who either completed the Trier Social Stress Test (TSST) or a non-stressful control condition. With a processing pipeline that included speaker diarization and machine learning models, we achieved stress detection performance significantly above a mean baseline. Moreover, relevant physiological and affective stress responses were partially predictable from acoustic-prosodic features. Feature-importance analyses identified the most informative predictors contributing to model performance. The findings demonstrate that speech can serve as a meaningful and unobtrusive indicator of multiple dimensions of the human stress response.

AI 总结：研究利用AlphaEarth嵌入作为空间上下文，在事件历史稀疏时提升时空点过程模型的跨区域预测性能，实验表明在短历史下预测误差降低2-6倍。

链接：https://arxiv.org/abs/2607.01082

机构：German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）； Université Mohammed VI Polytechnique（穆罕默德六世理工大学）； University of Oxford（牛津大学）； Imperial College London（帝国理工学院）； Rhineland-Palatinate Technical University of Kaiserslautern-Landau (RPTU)（莱茵兰-普法尔茨凯泽斯劳滕-兰道工业大学）

作者：Yahya Aalaila, Mouad Elhamdi, Gerrit Großmann, Daniel Jenson, Elizaveta Semenova, Sebastian Vollmer

英文摘要：Spatio-temporal point-process models must often generalise across space when local event histories are sparse. We study whether exogenous spatial context can compensate in such regimes. Using a fixed log-Gaussian Cox process backbone, we compare an event-only model with the same model augmented by AlphaEarth embeddings as linear spatial context. We evaluate spatial transfer on emergency medical services (EMS) forecasting across eight held-out regions, fixed forecast anchors, and a sweep over history length $w$, using only AlphaEarth (AE) embeddings available strictly before each anchor. AE improves out-of-region predictive performance across all history regimes, with the largest gains under scarce histories: approximately $2$--$6\times$ multiplicative improvements at $1-2$ weeks, tapering to roughly $10$--$20\%$ at $w=20$--$104$ weeks. These results show that contextual information can substantially stabilise spatially transferred point-process forecasts when event history is limited.

AI 总结：提出 Manifestation Unit 协议，将组件分析结果组织为结构化字段，通过混合检索实现可重用和可查询，在视觉和语言模型上验证了其优于非结构化基线，并揭示了核心字段。

链接：https://arxiv.org/abs/2607.00089

机构：Ubiquitous Computing Systems Laboratory, Nara Institute of Science and Technology, Nara, Japan（奈良先端科学技术大学院大学普适计算系统实验室）

作者：Hussein Chouman, Wataru Sasaki, Tomokazu Matsui, Hirohiko Suwa, Keiichi Yasumoto

英文摘要：Mechanistic interpretability has produced a rich inventory of component-level analyses that characterise what neural-network components encode and how they interact. Their outputs, however, are not easily reusable: selectivity tables, circuit diagrams, and feature lists remain locked in per-study notebooks - non-composable, not queryable in natural language, and not directly actionable for downstream audit or intervention. We study the representation layer that sits between these analyses and downstream use as a bottleneck that can be evaluated independently, and introduce Manifestation Units, a typed tuple protocol (E, S, R, D, G) extended with attention-head primitives (T) for transformer architectures, organising per-component statistics into structured fields populated automatically and queried through hybrid retrieval. Instantiated across generative vision (beta-VAE), discriminative vision (CNN), and language (GPT-2), the protocol supports two findings: typed structure substantially outperforms unstructured baselines on retrieval, and CNN filters retrieved by the schema satisfy causal sufficiency and necessity criteria under matched-budget controls. The schema absorbs attention-head primitives without modification, set-recovers known IOI circuit members under retrieval-budget-matched controls, and reveals an irreducible two-field core (S+R) with remaining fields either redundant or actively interfering. We present this as schema infrastructure for mechanistic interpretability rather than frontier-scale validation.

AI 总结：针对半监督安全分类中黑盒使用导致性能增益归因不清的问题，提出SemiScope分析工具，通过贝叶斯优化联合调优SSL设置、置信过滤、过采样和分类器，并与仅调优分类器的对照实验对比，发现分类器超参数优化可恢复大部分增益。

链接：https://arxiv.org/abs/2607.00113

机构：North Carolina State University（北卡罗来纳州立大学）； ShanghaiTech University（上海科技大学）

作者：Rui Shu, Tianpei Xia, Jingzhu He

英文摘要：Background. Labeled data for security classification is scarce. Semi-supervised learning (SSL) propagates labels from a small labeled pool to larger unlabeled pools. Yet security applications often use SSL as a black box: default parameters, a fixed classifier, and no handling of pseudo-label-induced class imbalance. Aims. Recent work reports sizeable gains from optimizing SSL pipelines via joint search, AutoML, or per-component tuning. These gains are hard to attribute: they may reflect useful SSL-classifier interactions, or mostly from simply tuning the downstream classifier. We disentangle these effects for binary tabular security data with classical SSL and tree-based classifiers. Method. We build SemiScope as an analysis instrument, not a deployment recommendation. It uses Bayesian Optimization to jointly tune SSL settings, confidence filtering, oversampling, and the classifier. The key control, Tuned-Clf, fixes SSL to defaults but gets the same 100-trial classifier budget and validation-set threshold tuning as SemiScope. At 10% labels, we compare them with paired TOST using a +/-1.0 g-measure smallest effect of interest. Results. SemiScope beats every default SSL baseline on all five datasets, improving over the strongest by 0.7-12.7 points. Under the equal-budget control, Tuned-Clf is statistically equivalent to the full pipeline on 4 of 5 datasets; Phishing is inconclusive. Classifier HPO alone recovers a median 86% of SemiScope's gain over Default Self-Training (ST) + Random Forest (RF). Conclusions. The reusable contribution is the decomposition protocol. A simpler recipe suffices: use Self-Training, tune the classifier with Bayesian Optimization, and tune the decision threshold on validation data. It reaches within 1 g-measure of Supervised RF at 20-30% labels on four datasets and 40% on Drebin, at the same or lower label rate than Default ST + RF on every dataset.

AI 总结：提出一个分阶段鲁棒性分析框架，结合SEM、OLS和双机器学习，通过FinTech数字客户亲密调查模型验证，识别稳定与需谨慎解释的关系，并提供可复现模板。

链接：https://arxiv.org/abs/2607.00512

作者：Ka Ching Chan, Qiana Liu, Sanjib Tiwari, Ranga Chimhundu

英文摘要：Structural equation modelling (SEM) is widely used in survey-based business and information systems research to assess latent constructs and theory-driven structural relationships. However, SEM path significance is obtained within a particular model specification and may not show whether findings remain stable under alternative estimation frameworks. This study develops and demonstrates a staged robustness analysis framework that connects SEM, ordinary least squares (OLS) regression, and Double Machine Learning (DML). SEM is first used to refine the measurement structure and estimate the robustness-baseline SEM model, in which the full theory-specified structural path system is retained for downstream robustness analysis before final structural path evaluation. OLS regression is then applied to SEM-derived construct scores as a transparent regression benchmark. Finally, DML-style residualisation is used to examine whether each tested focal relationship remains stable after flexible machine-learning-based adjustment for observed controls. Learner-sensitivity checks compare Random Forest, Gradient Boosting, and Support Vector Machine learners, and selected reverse-direction diagnostics are used to examine directional sensitivity. The framework is demonstrated using a FinTech Digital Customer Intimacy survey model. The findings identify which relationships are stable across SEM, OLS, and DML-style checks, and which require more cautious interpretation. A reproducible Google Colab workbook and generated result files are publicly available, providing a reusable template that researchers and students can adapt to other survey-based latent-construct studies. The paper contributes a practical robustness workflow and interpretation guide for survey-based researchers seeking to complement SEM with conventional and machine-learning-based robustness checks.

AI 总结：通过七组监督学习和强化学习模型的实证比较，发现当前量子机器学习模型在预测性能、策略稳定性和训练时间上尚未超越经典基线，但在噪声过滤和假阳性控制方面具有潜力。

链接：https://arxiv.org/abs/2607.01197

机构：Hebei Normal University（河北师范大学）； Kyushu University（九州大学）； University of Luxembourg（卢森堡大学）

作者：Chuanming Yu, Jiaming Liu, Zihao Ge, Xiongfei Wu, Lulu Zhu, Pengzhan Zhao, Jianjun Zhao

英文摘要：Quantum computing has emerged as a promising computational paradigm for machine learning (ML), with the potential to offer computational advantages over classical approaches. At this stage, the evidence supporting the performance and advantages of quantum machine learning (QML) models relative to classical models is this http URL address this gap, this paper presents an empirical study on the performance of QML models and their classical counterparts. We compare seven model pairs spanning supervised learning and reinforcement learning. Our results indicate that the evaluated quantum machine learning models do not yet surpass the classical baselines in overall prediction performance, policy stability, or training time. Nevertheless, QML remains a promising approach for filtering noise and controlling false positives. Our research findings summarize the challenges facing quantum machine learning across hardware environments, training efficiency, and convergence stability, providing a foundation for research into the robustness and parameter optimization of QML. This work is publicly available at this https URL.