# Research Papers — 2025-10 · bundle page 110 of 217

> Full-text markdown of papers #5451–5500 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/110
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/109.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/111.md)

### Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe

Authors: Christophe Roux, Max Zimmer, Alexandre d'Aspremont, Sebastian Pokutta
Published: 2025-10-15
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.13713v1

Pruning is a common technique to reduce the compute and storage requirements of Neural Networks. While conventional approaches typically retrain the model to recover pruning-induced performance degradation, state-of-the-art Large Language Model (LLM) pruning methods operate layer-wise, minimizing the per-layer pruning error on a small calibration dataset to avoid full retraining, which is considered computationally prohibitive for LLMs. However, finding the optimal pruning mask is a hard combinatorial problem and solving it to optimality is intractable. Existing methods hence rely on greedy heuristics that ignore the weight interactions in the pruning objective. In this work, we instead consider the convex relaxation of these combinatorial constraints and solve the resulting problem using the Frank-Wolfe (FW) algorithm. Our method drastically reduces the per-layer pruning error, outperforms strong baselines on state-of-the-art GPT architectures, and remains memory-efficient. We provide theoretical justification by showing that, combined with the convergence guarantees of the FW algorithm, we obtain an approximate solution to the original combinatorial problem upon rounding the relaxed solution to integrality.

---

### Training LLM Agents to Empower Humans

Authors: Evan Ellis, Vivek Myers, Jens Tuyls, Sergey Levine, Anca Dragan, Benjamin Eysenbach
Published: 2025-10-15
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13709v2

Assistive agents should not only take actions on behalf of a human, but also step out of the way and cede control when there are important decisions to be made. However, current methods for building assistive agents, whether via mimicking expert humans or via RL finetuning on an inferred reward, often encourage agents to complete tasks on their own rather than truly assisting the human attain their objectives. Additionally, these methods often require costly explicit human feedback to provide a training signal. We propose a new approach to tuning assistive language models based on maximizing the human's empowerment, their ability to effect desired changes in the environment. Our empowerment-maximizing method, Empower, only requires offline text data, providing a self-supervised method for fine-tuning language models to better assist humans. To study the efficacy of our approach, we conducted an 18-person user study comparing our empowerment assistant with a strong baseline. Participants preferred our assistant 78% of the time (p=0.015), with a 31% higher acceptance rate and 38% fewer suggestions. Additionally, we introduce a new environment for evaluating multi-turn code assistance using simulated humans. Using this environment, we show that agents trained with Empower increase the success rate of a simulated human programmer on challenging coding questions by an average of 192% over an SFT baseline. With this empowerment objective, we provide a framework for useful aligned AI agents at scale using only offline data without the need for any additional human feedback or verifiable rewards.

---

### Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents

Authors: Johan Obando-Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron Courville, Pablo Samuel Castro
Published: 2025-10-15
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.13704v2

Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance. Noting that well-structured representations can improve the generalization and sample efficiency of deep reinforcement learning (RL) agents, we propose the use of simplicial embeddings: lightweight representation layers that constrain embeddings to simplicial structures. This geometric inductive bias results in sparse and discrete features that stabilize critic bootstrapping and strengthen policy gradients. When applied to FastTD3, FastSAC, and PPO, simplicial embeddings consistently improve sample efficiency and final performance across a variety of continuous- and discrete-control environments, without any loss in runtime speed.

---

### Toward an Asymptotic Efficiency Theory on Regular Parameter Manifolds

Authors: Lvfang Sun, Zhenhua Lin, Lin Liu
Published: 2025-10-15
Categories: math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.13703v4

Asymptotic efficiency theory is one of the pillars in the foundations of modern mathematical statistics. Not only does it serve as a rigorous theoretical benchmark for evaluating statistical methods, but it also sheds light on how to develop and unify novel statistical procedures. For example, the calculus of influence functions has led to many important statistical breakthroughs in the past decades. Responding to the pressing challenge of analyzing increasingly complex datasets, particularly those with non-Euclidean/nonlinear structures, many novel statistical models and methods have been proposed in recent years. However, the existing efficiency theory is not always readily applicable to these cases, as the theory was developed, for the most part, under the often neglected premise that both the sample space and the parameter space are normed linear spaces. As a consequence, efficiency results outside normed linear spaces are quite rare and isolated, obtained on a case-by-case basis. This paper aims to develop a more unified asymptotic efficiency theory, allowing the sample space, the parameter space, or both to be Riemannian manifolds satisfying certain regularity conditions. We build a vocabulary that helps translate essential concepts in efficiency theory from normed linear spaces to Riemannian manifolds, such as (locally) regular estimators, differentiable functionals, etc. Efficiency bounds are established under conditions parallel to those for normed linear spaces. We also demonstrate the conceptual advantage of the new framework by applying it to two concrete examples in statistics: the population Frechet mean and the regression coefficient vector of Single-Index Models.

---

### MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion

Authors: Minjung Shin, Hyunin Cho, Sooyeon Go, Jin-Hwa Kim, Youngjung Uh
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13702v2

Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with geometric consistency, whereas customization models lack explicit viewpoint control, making them challenging to unify. Motivated by these gaps, we introduce a novel task, multi-view customization, which aims to jointly achieve multi-view camera pose control and customization. Due to the scarcity of training data in customization, existing multi-view generation models, which inherently rely on large-scale datasets, struggle to generalize to diverse prompts. To address this, we propose MVCustom, a novel diffusion-based framework explicitly designed to achieve both multi-view consistency and customization fidelity. In the training stage, MVCustom learns the subject's identity and geometry using a feature-field representation, incorporating the text-to-video diffusion backbone enhanced with dense spatio-temporal attention, which leverages temporal coherence for multi-view consistency. In the inference stage, we introduce two novel techniques: depth-aware feature rendering explicitly enforces geometric consistency, and consistent-aware latent completion ensures accurate perspective alignment of the customized subject and surrounding backgrounds. Extensive experiments demonstrate that MVCustom achieves the most balanced and consistent competitive performance across multi-view consistency, customization fidelity, demonstrating effective solution of multi-objective generation task.

---

### Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

Authors: Jonghyun Park, Minhyuk Seo, Chaewon Yeo, Jonghyun Choi
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13698v4

Even modern AI models often remain vulnerable to multimodal queries in which harmful intent is embedded in images. A widely used approach for safety alignment is training with extensive multimodal safety datasets, but the costs of data curation and training are often prohibitive. To mitigate these costs, inference-time alignment has recently been explored, but they often lack generalizability across diverse multimodal jailbreaks and still incur notable overhead due to extra forward passes for response refinement or heavy pre-deployment calibration procedures. Here, we identify insufficient visual attention to safety-critical image regions as one of the key causes of multimodal safety failures. Building on this insight, we propose Multimodal Risk-Adaptive Steering (MoRAS), which enhances safety-critical visual attention via concise visual contexts for accurate multimodal risk assessment. This risk signal enables risk-adaptive steering for direct refusals, reducing inference overhead while remaining generalizable across diverse multimodal jailbreaks. Notably, MoRAS requires only a small calibration set to estimate multimodal risk, substantially reducing pre-deployment overhead. We conduct various empirical validations across multiple benchmarks and MLLM backbones, and observe that the proposed MoRAS consistently mitigates jailbreaks, preserves utility, and reduces computational overhead compared to state-of-the-art inference-time defenses.

---

### On Pretraining for Project-Level Code Completion

Authors: Maksim Sapronov, Evgeniy Glukhov
Published: 2025-10-15
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2510.13697v1

Repository-level pretraining is commonly used to enable large language models for code to leverage codebase-wide context. This enhances their ability to generate accurate and context-aware code completions. In this work, we investigate how different repository-processing strategies affect in-context learning in OpenCoder, a 1.5B-parameter model. We extend its context window from 4,096 to 16,384 tokens by training on additional 1B tokens of curated repository-level data. Despite relying on a smaller dataset than competing models (which often use hundreds of billions of tokens), our model achieves comparable performance on the Long Code Arena benchmark. We find that various repository-processing techniques yield similarly strong results, with the primary gain coming from adapting to a new rotary positional embedding (RoPE) scaling parameter. Finally, we show that a simpler file-level training approach at the original sequence length remains highly effective, opening up repository-level code completion research to settings with more constrained data and compute resources.

---

### Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking

Authors: Yuchun Miao, Liang Ding, Sen Zhang, Rong Bao, Lefei Zhang, Dacheng Tao
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13694v1

Despite the success of Reinforcement Learning from Human Feedback (RLHF) in aligning language models with human values, reward hacking-or reward over-optimization-remains a major challenge. We identify two key obstacles to its mitigation: (1) reward misgeneralization in reward modeling, where reward models overfit to spurious, preference-irrelevant features; and (2) the lack of suitable regularization during RL optimization, as existing token-level constraints often over-restrict the policy space. To address these issues, we propose InfoRM, an information-theoretic reward modeling framework based on the Information Bottleneck (IB) principle, which filters out preference-irrelevant information to alleviate reward misgeneralization. We further observe that reward-hacked responses manifest as pronounced outliers in InfoRM's IB latent space, measured by Mahalanobis distance from the SFT-induced distribution. Motivated by this, we introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape while maintaining alignment. We prove that IBL is theoretically equivalent to the pessimistic RL objective within the IB latent space. Finally, we present Mahalanobis Outlier Probability (MOP), a statistical metric for quantifying reward hacking severity, enabling principled hyperparameter tuning and online mitigation such as early stopping. Extensive experiments across diverse LLMs and datasets confirm the generality of our findings, the effectiveness of InfoRM and IBL, and the reliability of MOP as a diagnostic tool-collectively advancing the state of RLHF.

---

### A Modal Logic for Temporal and Jurisdictional Classifier Models

Authors: Cecilia Di Florio, Huimin Dong, Antonino Rotolo
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13691v1

Logic-based models can be used to build verification tools for machine learning classifiers employed in the legal field. ML classifiers predict the outcomes of new cases based on previous ones, thereby performing a form of case-based reasoning (CBR). In this paper, we introduce a modal logic of classifiers designed to formally capture legal CBR. We incorporate principles for resolving conflicts between precedents, by introducing into the logic the temporal dimension of cases and the hierarchy of courts within the legal system.

---

### Generating healthy counterfactuals with denoising diffusion bridge models

Authors: Ana Lawry Aguila, Peirong Liu, Marina Crespo Aguirre, Juan Eugenio Iglesias
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13684v1

Generating healthy counterfactuals from pathological images holds significant promise in medical imaging, e.g., in anomaly detection or for application of analysis tools that are designed for healthy scans. These counterfactuals should represent what a patient's scan would plausibly look like in the absence of pathology, preserving individual anatomical characteristics while modifying only the pathological regions. Denoising diffusion probabilistic models (DDPMs) have become popular methods for generating healthy counterfactuals of pathology data. Typically, this involves training on solely healthy data with the assumption that a partial denoising process will be unable to model disease regions and will instead reconstruct a closely matched healthy counterpart. More recent methods have incorporated synthetic pathological images to better guide the diffusion process. However, it remains challenging to guide the generative process in a way that effectively balances the removal of anomalies with the retention of subject-specific features. To solve this problem, we propose a novel application of denoising diffusion bridge models (DDBMs) - which, unlike DDPMs, condition the diffusion process not only on the initial point (i.e., the healthy image), but also on the final point (i.e., a corresponding synthetically generated pathological image). Treating the pathological image as a structurally informative prior enables us to generate counterfactuals that closely match the patient's anatomy while selectively removing pathology. The results show that our DDBM outperforms previously proposed diffusion models and fully supervised approaches at segmentation and anomaly detection tasks.

---

### How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study

Authors: Matthieu Dubois, François Yvon, Pablo Piantanida
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13681v1

As texts generated by Large Language Models (LLMs) are ever more common and often indistinguishable from human-written content, research on automatic text detection has attracted growing attention. Many recent detectors report near-perfect accuracy, often boasting AUROC scores above 99\%. However, these claims typically assume fixed generation settings, leaving open the question of how robust such systems are to changes in decoding strategies. In this work, we systematically examine how sampling-based decoding impacts detectability, with a focus on how subtle variations in a model's (sub)word-level distribution affect detection performance. We find that even minor adjustments to decoding parameters - such as temperature, top-p, or nucleus sampling - can severely impair detector accuracy, with AUROC dropping from near-perfect levels to 1\% in some settings. Our findings expose critical blind spots in current detection methods and emphasize the need for more comprehensive evaluation protocols. To facilitate future research, we release a large-scale dataset encompassing 37 decoding configurations, along with our code and evaluation framework https://github.com/BaggerOfWords/Sampling-and-Detection

---

### Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise

Authors: Bingbin Liu, Rachit Bansal, Depen Morwani, Nikhil Vyas, David Alvarez-Melis, Sham M. Kakade
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13680v2

Preconditioned methods are central to deep learning optimization. Predominant approaches include computationally light diagonal preconditioners such as Adam, which rely on gradient statistics, and second-order methods such as Gauss-Newton (GN), which capture richer curvature information. Seeking the best of both worlds, we disentangle the preconditioner design space into several factors, separating the choice of diagonal scaling (Adam-style versus GN-style) from 1) the basis choices under which the diagonal scaling operates, and 2) the gradient noises from mini-batching. Our theoretical results show that GN's optimality for linear regression no longer holds under a poorly chosen basis under both population and stochastic updates, or a move from linear regression to a non-convex variant of logistic regression. In these settings, Adam-style methods offer genuine advantages over curvature-inspired preconditioning, rather than serving merely as a tractable proxy. Empirical results on synthetic problems and CIFAR-10 support these findings.

---

### FlashWorld: High-quality 3D Scene Generation within Seconds

Authors: Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, Chunchao Guo, Liujuan Cao
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13678v1

We propose FlashWorld, a generative model that produces 3D scenes from a single image or text prompt in seconds, 10~100$\times$ faster than previous works while possessing superior rendering quality. Our approach shifts from the conventional multi-view-oriented (MV-oriented) paradigm, which generates multi-view images for subsequent 3D reconstruction, to a 3D-oriented approach where the model directly produces 3D Gaussian representations during multi-view generation. While ensuring 3D consistency, 3D-oriented method typically suffers poor visual quality. FlashWorld includes a dual-mode pre-training phase followed by a cross-mode post-training phase, effectively integrating the strengths of both paradigms. Specifically, leveraging the prior from a video diffusion model, we first pre-train a dual-mode multi-view diffusion model, which jointly supports MV-oriented and 3D-oriented generation modes. To bridge the quality gap in 3D-oriented generation, we further propose a cross-mode post-training distillation by matching distribution from consistent 3D-oriented mode to high-quality MV-oriented mode. This not only enhances visual quality while maintaining 3D consistency, but also reduces the required denoising steps for inference. Also, we propose a strategy to leverage massive single-view images and text prompts during this process to enhance the model's generalization to out-of-distribution inputs. Extensive experiments demonstrate the superiority and efficiency of our method.

---

### APRIL: Auxiliary Physically-Redundant Information in Loss -- A physics-informed framework for parameter estimation with a gravitational-wave case study

Authors: Matteo Scialpi, Francesco Di Clemente, Leigh Smith, Michał Bejger
Published: 2025-10-15
Categories: gr-qc, astro-ph.IM, cs.NE, physics.comp-ph
arXiv: https://arxiv.org/abs/2510.13677v2

Physics-Informed Neural Networks (PINNs) embed the partial differential equations (PDEs) governing the system under study directly into the training of Neural Networks, ensuring solutions that respect physical laws. While effective for single-system problems, standard PINNs scale poorly to datasets containing many realizations of the same underlying physics with varying parameters. To address this limitation, we present a complementary approach by including auxiliary physically-redundant information in loss (APRIL), i.e. augment the standard supervised output-target loss with auxiliary terms which exploit exact physical redundancy relations among outputs. We mathematically demonstrate that these terms preserve the true physical minimum while reshaping the loss landscape, improving convergence toward physically consistent solutions. As a proof-of-concept, we benchmark APRIL on a fully-connected neural network for gravitational wave (GW) parameter estimation (PE). We use simulated, noise-free compact binary coalescence (CBC) signals, focusing on inspiral-frequency waveforms to recover the chirp mass $\mathcal{M}$, the total mass $M_\mathrm{tot}$, and symmetric mass ratio $η$ of the binary. In this controlled setting, we show that APRIL achieves up to an order-of-magnitude improvement in test accuracy, especially for parameters that are otherwise difficult to learn. This method provides physically consistent learning for large multi-system datasets and is well suited for future GW analyses involving realistic noise and broader parameter ranges.

---

### Seeing and Knowing in the Wild: Open-domain Visual Entity Recognition with Large-scale Knowledge Graphs via Contrastive Learning

Authors: Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka, Stefan Schmid, Yuqicheng Zhu, Jingcheng Wu, Nadeem Nazer, Steffen Staab
Published: 2025-10-15
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13675v2

Open-domain visual entity recognition aims to identify and link entities depicted in images to a vast and evolving set of real-world concepts, such as those found in Wikidata. Unlike conventional classification tasks with fixed label sets, it operates under open-set conditions, where most target entities are unseen during training and exhibit long-tail distributions. This makes the task inherently challenging due to limited supervision, high visual ambiguity, and the need for semantic disambiguation. We propose a Knowledge-guided Contrastive Learning (KnowCoL) framework that combines both images and text descriptions into a shared semantic space grounded by structured information from Wikidata. By abstracting visual and textual inputs to a conceptual level, the model leverages entity descriptions, type hierarchies, and relational context to support zero-shot entity recognition. We evaluate our approach on the OVEN benchmark, a large-scale open-domain visual recognition dataset with Wikidata IDs as the label space. Our experiments show that using visual, textual, and structured knowledge greatly improves accuracy, especially for rare and unseen entities. Our smallest model improves the accuracy on unseen entities by 10.5% compared to the state-of-the-art, despite being 35 times smaller.

---

### NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

Authors: Xiaoning Liu, Zongwei Wu, Florin-Alexandru Vasluianu, Hailong Yan, Bin Ren, Yulun Zhang, Shuhang Gu, Le Zhang, Ce Zhu, Radu Timofte, Kangbiao Shi, Yixu Feng et al.
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13670v1

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

---

### CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas

Authors: Zian Li, Muhan Zhang
Published: 2025-10-15
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13669v2

Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames, video MAR models often produce highly distorted outputs due to the lack of a structured global prior, especially when using only a few sampling steps. To address this, we propose CanvasMAR, a novel autoregressive video prediction model that predicts high-fidelity frames with few sampling steps by introducing a canvas--a blurred, global one-step prediction of the next frame that serves as a non-uniform mask during masked generation. The canvas supplies global structure early in sampling, enabling faster and more coherent frame synthesis. To further stabilize autoregressive sampling, we propose an easy-to-hard curriculum via a motion-aware sampling order that synthesizes relatively stationary regions before attending to highly dynamic ones. We also integrate compositional classifier-free guidance that jointly strengthens the canvas and temporal conditioning to improve generation fidelity. Experiments on the BAIR, UCF-101, and Kinetics-600 benchmarks demonstrate that CanvasMAR produces higher-quality videos with fewer autoregressive steps. On the challenging Kinetics-600 dataset, CanvasMAR achieves remarkable performance among autoregressive models and rivals advanced diffusion-based methods.

---

### STAR: Decode-Phase Rescheduling for LLM Inference

Authors: Zhibin Wang, Zetao Hong, Xue Li, Zibo Wang, Shipeng Li, Qingkai Meng, Qing Wang, Chengying Huan, Rong Gu, Sheng Zhong, Chen Tian
Published: 2025-10-15
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2510.13668v2

Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalance in the decode phase, particularly for long-output reasoning tasks. Existing systems, such as PD disaggregation architectures, rely on static prefill-to-decode scheduling, which often results in SLO violations and OOM failures under evolving decode workloads. In this paper, we propose STAR, a decode rescheduling system powered by length prediction to anticipate future workloads. Our core contributions include: (1) A lightweight and continuous LLM-native prediction method that leverages LLM hidden state to model remaining generation length with high precision (reducing MAE by 49.42%) and low overhead (cutting predictor parameters by 93.28%); (2) A rescheduling solution in decode phase with a dynamic balancing mechanism that integrates current and predicted workloads, reducing P99 TPOT by 75.1% and achieving 2.63 times higher goodput.

---

### Axial Neural Networks for Dimension-Free Foundation Models

Authors: Hyunsu Kim, Jonggeon Park, Joan Bruna, Hongseok Yang, Juho Lee
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13665v2

The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However, training such models on physics data, including solutions to partial differential equations (PDEs), poses a unique challenge due to varying dimensionalities across different systems. Traditional approaches either fix a maximum dimension or employ separate encoders for different dimensionalities, resulting in inefficiencies. To address this, we propose a dimension-agnostic neural network architecture, the Axial Neural Network (XNN), inspired by parameter-sharing structures such as Deep Sets and Graph Neural Networks. XNN generalizes across varying tensor dimensions while maintaining computational efficiency. We convert existing PDE foundation models into axial neural networks and evaluate their performance across three training scenarios: training from scratch, pretraining on multiple PDEs, and fine-tuning on a single PDE. Our experiments show that XNNs perform competitively with original models and exhibit superior generalization to unseen dimensions, highlighting the importance of multidimensional pretraining for foundation models.

---

### OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wild

Authors: Hongyu Qu, Jianan Wei, Xiangbo Shu, Yazhou Yao, Wenguan Wang, Jinhui Tang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13660v2

Current 3D gaze estimation methods struggle to generalize across diverse data domains, primarily due to i) the scarcity of annotated datasets, and ii) the insufficient diversity of labeled data. In this work, we present OmniGaze, a semi-supervised framework for 3D gaze estimation, which utilizes large-scale unlabeled data collected from diverse and unconstrained real-world environments to mitigate domain bias and generalize gaze estimation in the wild. First, we build a diverse collection of unlabeled facial images, varying in facial appearances, background environments, illumination conditions, head poses, and eye occlusions. In order to leverage unlabeled data spanning a broader distribution, OmniGaze adopts a standard pseudo-labeling strategy and devises a reward model to assess the reliability of pseudo labels. Beyond pseudo labels as 3D direction vectors, the reward model also incorporates visual embeddings extracted by an off-the-shelf visual encoder and semantic cues from gaze perspective generated by prompting a Multimodal Large Language Model to compute confidence scores. Then, these scores are utilized to select high-quality pseudo labels and weight them for loss computation. Extensive experiments demonstrate that OmniGaze achieves state-of-the-art performance on five datasets under both in-domain and cross-domain settings. Furthermore, we also evaluate the efficacy of OmniGaze as a scalable data engine for gaze estimation, which exhibits robust zero-shot generalization on four unseen datasets.

---

### Rethinking Evaluation in the Era of Time Series Foundation Models: (Un)known Information Leakage Challenges

Authors: Marcel Meyer, Sascha Kaltenpoth, Kevin Zalipski, Oliver Müller
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13654v3

Time Series Foundation Models (TSFMs) represent a new paradigm for time-series forecasting, promising zero-shot predictions without the need for task-specific training or fine-tuning. However, similar to Large Language Models (LLMs), the evaluation of TSFMs is challenging: as training corpora grow increasingly large, it becomes difficult to ensure the integrity of the test sets used for benchmarking. An investigation of existing TSFM evaluation studies identifies two kinds of information leakage: (1) train-test sample overlaps arising from the multi-purpose reuse of datasets and (2) temporal overlap of correlated train and test series. Ignoring these forms of information leakage when benchmarking TSFMs risks producing overly optimistic performance estimates that fail to generalize to real-world settings. We therefore argue for the development of novel evaluation methodologies that avoid pitfalls already observed in both LLM and classical time-series benchmarking, and we call on the research community to adopt principled approaches to safeguard the integrity of TSFM evaluation.

---

### What is the objective of reasoning with reinforcement learning?

Authors: Damek Davis, Benjamin Recht
Published: 2025-10-15
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.13651v1

We show that several popular algorithms for reinforcement learning in large language models with binary rewards can be viewed as stochastic gradient ascent on a monotone transform of the probability of a correct answer given a prompt. In particular, the transformation associated with rejection sampling algorithms is the logarithm and that associated with the GRPO algorithm is the arcsine of the square root.

---

### Adversarially Robust Few-Shot Anomaly Detection with Vision Foundation Models

Authors: Akib Mohammed Khan, Bartosz Krawczyk
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13643v2

Vision foundation models such as DINOv2 enable strong few-shot anomaly detection (FSAD) through simple non-parametric k-nearest-neighbor (k-NN) scoring over frozen patch features. Existing robust anomaly detection methods assume large normal-class training sets and adversarial training of the feature extractor. The few-shot regime, where the detector consists of a frozen backbone and a non-parametric scorer, has remained unaddressed despite its widespread deployment. We develop a white-box attack framework adapted to k-NN memory-bank detectors and introduce an adversarially robust FSAD method which is training-free with respect to the backbone. We introduce the DistanceProbe (DP), a lightweight MLP trained by regression to predict per-patch k-NN distance directly from frozen features, providing the differentiable proxy required for gradient-based attacks against non-parametric scorers. We further propose a two-level combined defense that operates using only the normal reference support set images. At the input level, PatchShift (PS) applies random pixel shifts to exploit the misalignment of adversarial perturbations with the encoder's patch grid, aggregating scores across multiple shifted views via element-wise median pooling. At the feature level we employ the FeaturePurifier (FP), a lightweight residual MLP trained on clean and adversarially augmented support features to project perturbed representations back toward the clean feature manifold. Through comprehensive experiments under various adversarial settings, we show that our method exhibits robust detection and localization with performance gains of ~27% image-level AUROC and ~51% pixel-level PRO over the undefended attacked baseline across MVTec-AD, VisA, and MPDD at k=4 shots, while preserving clean accuracy within 3%, matching full-shot adversarially-trained baselines on pixel-level AUROC, and holding under adaptive attack.

---

### Challenges, Advances, and Evaluation Metrics in Medical Image Enhancement: A Systematic Literature Review

Authors: Chun Wai Chin, Haniza Yazid, Hoi Leong Lee
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13638v1

Medical image enhancement is crucial for improving the quality and interpretability of diagnostic images, ultimately supporting early detection, accurate diagnosis, and effective treatment planning. Despite advancements in imaging technologies such as X-ray, CT, MRI, and ultrasound, medical images often suffer from challenges like noise, artifacts, and low contrast, which limit their diagnostic potential. Addressing these challenges requires robust preprocessing, denoising algorithms, and advanced enhancement methods, with deep learning techniques playing an increasingly significant role. This systematic literature review, following the PRISMA approach, investigates the key challenges, recent advancements, and evaluation metrics in medical image enhancement. By analyzing findings from 39 peer-reviewed studies, this review provides insights into the effectiveness of various enhancement methods across different imaging modalities and the importance of evaluation metrics in assessing their impact. Key issues like low contrast and noise are identified as the most frequent, with MRI and multi-modal imaging receiving the most attention, while specialized modalities such as histopathology, endoscopy, and bone scintigraphy remain underexplored. Out of the 39 studies, 29 utilize conventional mathematical methods, 9 focus on deep learning techniques, and 1 explores a hybrid approach. In terms of image quality assessment, 18 studies employ both reference-based and non-reference-based metrics, 9 rely solely on reference-based metrics, and 12 use only non-reference-based metrics, with a total of 65 IQA metrics introduced, predominantly non-reference-based. This review highlights current limitations, research gaps, and potential future directions for advancing medical image enhancement.

---

### Multivariate Time Series Forecasting with Gate-Based Quantum Reservoir Computing on NISQ Hardware

Authors: Wissal Hamhoum, Soumaya Cherkaoui, Jean-Frederic Laprade, Ola Ahmad, Shengrui Wang
Published: 2025-10-15
Categories: cs.LG, cs.ET
arXiv: https://arxiv.org/abs/2510.13634v2

Quantum reservoir computing (QRC) offers a hardware-friendly approach to temporal learning, yet most studies target univariate signals and overlook near-term hardware constraints. This work introduces a gate-based QRC for multivariate time series (MTS-QRC) that pairs injection and memory qubits and uses a Trotterized nearest-neighbor transverse-field Ising evolution optimized for current device connectivity and depth. On Lorenz-63 and ENSO, the method achieves a mean square error (MSE) of 0.0087 and 0.0036, respectively, performing on par with classical reservoir computing on Lorenz and above learned RNNs on both, while NVAR and clustered ESN remain stronger on some settings. On IBM Heron R2, MTS-QRC sustains accuracy with realistic depths and, interestingly, outperforms a noiseless simulator on ENSO; singular value analysis indicates that device noise can concentrate variance in feature directions, acting as an implicit regularizer for linear readout in this regime. These findings support the practicality of gate-based QRC for MTS forecasting on NISQ hardware and motivate systematic studies on when and how hardware noise benefits QRC readouts.

---

### Closing the Gap Between Text and Speech Understanding in LLMs

Authors: Santiago Cuervo, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria Aldeneh
Published: 2025-10-15
Categories: cs.CL, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2510.13632v2

Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counterparts--and even cascaded pipelines--on language understanding tasks. We term this shortfall the text-speech understanding gap: the performance drop observed when a speech-adapted LLM processes spoken inputs relative to when the original text-based LLM processes the equivalent text. Recent approaches to narrowing this gap either rely on large-scale speech synthesis of text corpora, which is costly and heavily dependent on synthetic data, or on large-scale proprietary speech datasets, which are not reproducible. As a result, there remains a need for more data-efficient alternatives for closing the text-speech understanding gap. In this work, we analyze the gap as driven by two factors: (i) forgetting of text capabilities during adaptation, and (ii) cross-modal misalignment between speech and text. Based on this analysis, we introduce SALAD--Sample-efficient Alignment with Learning through Active selection and cross-modal Distillation--which combines cross-modal distillation with targeted synthetic data to improve alignment while mitigating forgetting. Applied to 3B and 7B LLMs, SALAD achieves competitive performance with a strong open-weight model across broad-domain benchmarks in knowledge, language understanding, and reasoning, while training on over an order of magnitude less speech data from public corpora.

---

### AVAR-Net: A Lightweight Audio-Visual Anomaly Recognition Framework with a Benchmark Dataset

Authors: Amjid Ali, Zulfiqar Ahmad Khan, Altaf Hussain, Muhammad Munsif, Adnan Hussain, Sung Wook Baik
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13630v2

Anomaly recognition plays a vital role in surveillance, transportation, healthcare, and public safety. However, most existing approaches rely solely on visual data, making them unreliable under challenging conditions such as occlusion, low illumination, and adverse weather. Moreover, the absence of large-scale synchronized audio-visual datasets has hindered progress in multimodal anomaly recognition. To address these limitations, this study presents AVAR-Net, a lightweight and efficient audio-visual anomaly recognition framework designed for real-world environments. AVAR-Net consists of four main modules: an audio feature extractor, a video feature extractor, fusion strategy, and a sequential pattern learning network that models cross-modal relationships for anomaly recognition. Specifically, the Wav2Vec2 model extracts robust temporal features from raw audio, while MobileViT captures both local and global visual representations from video frames. An early fusion mechanism combines these modalities, and a Multi-Stage Temporal Convolutional Network (MTCN) model that learns long-range temporal dependencies within the fused representation, enabling robust spatiotemporal reasoning. A novel Visual-Audio Anomaly Recognition (VAAR) dataset, is also introduced, serving as a medium-scale benchmark containing 3,000 real-world videos with synchronized audio across ten diverse anomaly classes. Experimental evaluations demonstrate that AVAR-Net achieves 89.29% accuracy on VAAR and 88.56% Average Precision on the XD-Violence dataset, improving Average Precision by 2.8% over existing state-of-the-art methods. These results highlight the effectiveness, efficiency, and generalization capability of the proposed framework, as well as the utility of VAAR as a benchmark for advancing multimodal anomaly recognition research.

---

### LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

Authors: Senyu Fei, Siyin Wang, Junhao Shi, Zihao Dai, Jikun Cai, Pengfang Qian, Li Ji, Xinzhe He, Shiduo Zhang, Zhaoye Fei, Jinlan Fu, Jingjing Gong et al.
Published: 2025-10-15
Categories: cs.RO, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2510.13626v3

Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing controlled perturbations across seven dimensions: objects layout, camera viewpoints, robot initial states, language instructions, light conditions, background textures and sensor noise. We comprehensively analyzed multiple state-of-the-art models and revealed consistent brittleness beneath apparent competence. Our analysis exposes critical weaknesses: models exhibit extreme sensitivity to perturbation factors, including camera viewpoints and robot initial states, with performance dropping from 95% to below 30% under modest perturbations. Surprisingly, models are largely insensitive to language variations, with further experiments revealing that models tend to ignore language instructions completely. Our findings challenge the assumption that high benchmark scores equate to true competency and highlight the need for evaluation practices that assess reliability under realistic variation.

---

### Unlocking Public Catalogues: Instruction-Tuning LLMs for ICD Coding of German Tumor Diagnoses

Authors: Stefan Lenz, Lakisha Ortiz Rosario, Georg Vollmar, Arsenij Ustjanzew, Fatma Alickovic, Thomas Kindler, Torsten Panholzer
Published: 2025-10-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13624v1

Accurate coding of tumor diagnoses with ICD-10-GM and ICD-O-3 is essential for structured cancer documentation in Germany. Smaller open-weight LLMs are appealing for privacy-preserving automation but often struggle with coding accuracy in German-language contexts. This study investigates whether instruction-based fine-tuning on public datasets improves the coding accuracy of open-weight LLMs for German tumor diagnosis texts. The evaluation uses coded diagnoses from the local tumor documentation system as test data. In a systematic data quality assessment, the upper limit for ICD-10 coding performance was estimated at 60-79% for exact and 81-94% for partial (three-character codes only) derivation. As training data, over 500,000 question-answer pairs were created based on the ICD-10-GM, ICD-O-3, and OPS catalogues. Eight open-weight models from the Qwen, Llama, and Mistral families (7-70 B parameters) were fine-tuned. ICD-10-GM accuracy rose from 1.4-24% to 41-58%, and partial accuracy from 31-74% to 73-83%. The accuracy of ICD-O-3 topography coding also improved but started and remained considerably lower with an exact accuracy of 22-40% and a partial accuracy of 56-67% after fine-tuning. Malformed code outputs dropped to 0% for all models. Tumor-diagnosis recognition reached 99%. Accuracy correlated positively with model size, but gaps between small and large models narrowed after fine-tuning. The reasoning mode in Qwen3 generally yielded a lower performance than fine-tuning and was over 100 times slower. Our findings highlight the potential of leveraging public catalogues to build instruction datasets that improve LLMs in medical documentation tasks. The complete training dataset and the best-performing checkpoints of the fine-tuned models are available from https://huggingface.co/datasets/stefan-m-lenz/ICDOPS-QA-2024.

---

### Manifold Decoders: A Framework for Generative Modeling from Nonlinear Embeddings

Authors: Riddhish Thakare, Kingdom Mutala Akugri
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13622v1

Classical nonlinear dimensionality reduction (NLDR) techniques like t-SNE, Isomap, and LLE excel at creating low-dimensional embeddings for data visualization but fundamentally lack the ability to map these embeddings back to the original high-dimensional space. This one-way transformation limits their use in generative applications. This paper addresses this critical gap by introducing a system- atic framework for constructing neural decoder architectures for prominent NLDR methods, enabling bidirectional mapping for the first time. We extend this framework by implementing a diffusion-based generative process that operates directly within these learned manifold spaces. Through experiments on the CelebA dataset, we evaluate the reconstruction and generative performance of our approach against autoencoder and standard diffusion model baselines. Our findings reveal a fundamental trade- off: while the decoders successfully reconstruct data, their quality is surpassed by end-to-end optimized autoencoders. Moreover, manifold-constrained diffusion yields poor-quality samples, suggesting that the discrete and sparse nature of classical NLDR embeddings is ill-suited for the continuous inter- polation required by generative models. This work highlights the inherent challenges in retrofitting generative capabilities onto NLDR methods designed primarily for visualization and analysis.

---

### The Role of Computing Resources in Publishing Foundation Model Research

Authors: Yuexing Hao, Yue Huang, Haoran Zhang, Chenyang Zhao, Zhenwen Liang, Paul Pu Liang, Yue Zhao, Lichao Sun, Saleh Kalantari, Xiangliang Zhang, Marzyeh Ghassemi
Published: 2025-10-15
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.13621v1

Cutting-edge research in Artificial Intelligence (AI) requires considerable resources, including Graphics Processing Units (GPUs), data, and human resources. In this paper, we evaluate of the relationship between these resources and the scientific advancement of foundation models (FM). We reviewed 6517 FM papers published between 2022 to 2024, and surveyed 229 first-authors to the impact of computing resources on scientific output. We find that increased computing is correlated with national funding allocations and citations, but our findings don't observe the strong correlations with research environment (academic or industrial), domain, or study methodology. We advise that individuals and institutions focus on creating shared and affordable computing opportunities to lower the entry barrier for under-resourced researchers. These steps can help expand participation in FM research, foster diversity of ideas and contributors, and sustain innovation and progress in AI. The data will be available at: https://mit-calc.csail.mit.edu/

---

### Fusion Meets Diverse Conditions: A High-diversity Benchmark and Baseline for UAV-based Multimodal Object Detection with Condition Cues

Authors: Chen Chen, Kangcheng Bin, Ting Hu, Jiahao Qi, Xingyue Liu, Tianpeng Liu, Zhen Liu, Yongxiang Liu, Ping Zhong
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13620v1

Unmanned aerial vehicles (UAV)-based object detection with visible (RGB) and infrared (IR) images facilitates robust around-the-clock detection, driven by advancements in deep learning techniques and the availability of high-quality dataset. However, the existing dataset struggles to fully capture real-world complexity for limited imaging conditions. To this end, we introduce a high-diversity dataset ATR-UMOD covering varying scenarios, spanning altitudes from 80m to 300m, angles from 0° to 75°, and all-day, all-year time variations in rich weather and illumination conditions. Moreover, each RGB-IR image pair is annotated with 6 condition attributes, offering valuable high-level contextual information. To meet the challenge raised by such diverse conditions, we propose a novel prompt-guided condition-aware dynamic fusion (PCDF) to adaptively reassign multimodal contributions by leveraging annotated condition cues. By encoding imaging conditions as text prompts, PCDF effectively models the relationship between conditions and multimodal contributions through a task-specific soft-gating transformation. A prompt-guided condition-decoupling module further ensures the availability in practice without condition annotations. Experiments on ATR-UMOD dataset reveal the effectiveness of PCDF.

---

### Message Passing on the Edge: Towards Scalable and Expressive GNNs

Authors: Pablo Barceló, Fabian Jogl, Alexander Kozachinskiy, Matthias Lanzinger, Stefan Neumann, Cristóbal Rojas
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13615v2

Graph neural networks (GNNs) are widely used in graph learning and most architectures propagate information by passing messages between vertices. In this work, we shift our attention to GNNs that perform message passing on edges and introduce EB-1WL, an edge-based color-refinement test, and a corresponding architecture, EB-GNN. Our EB-GNN architecture is inspired by the classic triangle-counting algorithm of Chiba and Nishizeki and passes messages along edges and triangles. Our contributions are as follows: (1) Theoretically, we show that EB-1WL is significantly more expressive than 1WL. We provide a complete logical characterization of EB-1WL in first-order logic, along with distinguishability results via homomorphism counting. To the best of our knowledge, EB-GNN has the strongest theoretical expressivity guarantees among edge-based message-passing GNNs in the literature. (2) Unlike many GNN architectures that are more expressive than 1WL, we prove that EB-1WL and EB-GNN admit near-linear time and memory usage on practical graph learning workloads. (3) We show in experiments that EB-GNN is a highly efficient general-purpose architecture: it substantially outperforms simple MPNNs and remains competitive with task-specialized state-of-the-art GNNs at substantially lower computational cost.

---

### MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning

Authors: Xingyu Tan, Xiaoyang Wang, Qing Liu, Xiwei Xu, Xin Yuan, Liming Zhu, Wenjie Zhang
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13614v3

Large Language Models (LLMs) have achieved impressive reasoning abilities, but struggle with temporal understanding, especially when questions involve multiple entities, compound operators, and evolving event sequences. Temporal Knowledge Graphs (TKGs), which capture vast amounts of temporal facts in a structured format, offer a reliable source for temporal reasoning. However, existing TKG-based LLM reasoning methods still struggle with four major challenges: maintaining temporal faithfulness in multi-hop reasoning, achieving multi-entity temporal synchronization, adapting retrieval to diverse temporal operators, and reusing prior reasoning experience for stability and efficiency. To address these issues, we propose MemoTime, a memory-augmented temporal knowledge graph framework that enhances LLM reasoning through structured grounding, recursive reasoning, and continual experience learning. MemoTime decomposes complex temporal questions into a hierarchical Tree of Time, enabling operator-aware reasoning that enforces monotonic timestamps and co-constrains multiple entities under unified temporal bounds. A dynamic evidence retrieval layer adaptively selects operator-specific retrieval strategies, while a self-evolving experience memory stores verified reasoning traces, toolkit decisions, and sub-question embeddings for cross-type reuse. Comprehensive experiments on multiple temporal QA benchmarks show that MemoTime achieves overall state-of-the-art results, outperforming the strong baseline by up to 24.0%. Furthermore, MemoTime enables smaller models (e.g., Qwen3-4B) to achieve reasoning performance comparable to that of GPT-4-Turbo.

---

### Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity

Authors: Riccardo Santi, Riccardo Salami, Simone Calderara
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13606v1

Nowdays, there are an abundance of portable devices capable of collecting large amounts of data and with decent computational power. This opened the possibility to train AI models in a distributed manner, preserving the participating clients' privacy. However, because of privacy regulations and safety requirements, elimination upon necessity of a client contribution to the model has become mandatory. The cleansing process must satisfy specific efficacy and time requirements. In recent years, research efforts have produced several knowledge removal methods, but these require multiple communication rounds between the data holders and the process coordinator. This can cause the unavailability of an effective model up to the end of the removal process, which can result in a disservice to the system users. In this paper, we introduce an innovative solution based on Task Arithmetic and the Neural Tangent Kernel, to rapidly remove a client's influence from a model.

---

### NOSA: Native and Offloadable Sparse Attention

Authors: Yuxiang Huang, Pengjie Wang, Jicheng Han, Weilin Zhao, Zhou Su, Ao Sun, Hongya Lyu, Hengyu Zhao, Yudong Wang, Chaojun Xiao, Xu Han, Zhiyuan Liu
Published: 2025-10-15
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13602v3

Decoding throughput improvements from larger inference batches are limited by GPU memory, which is largely consumed by the key-value (KV) cache. Prior training-free KV cache offloading alleviates this by keeping redundant context on the CPU and fetching only a sparse subset for attention, but it often degrades long-generation quality due to training-inference mismatch on sparse patterns. Meanwhile, trainable sparse attention is incompatible with efficient offloading, as unconstrained KV accesses may force large CPU-to-GPU transfers and erase throughput gains. To this end, we propose NOSA, a trainable sparse attention mechanism natively designed for KV cache offloading. NOSA explicitly constrains the volume of CPU-GPU KV transfers, thereby achieving low communication overhead and high decoding throughput. We further build NOSI, a KV cache offloading inference system that fully unlocks NOSA's efficiency. Empirical results on 1,3,8B LLMs demonstrate that NOSA outperforms KV cache offloading baselines on general, long-input, and long-generation tasks, while boosting decoding throughput by up to 5.04x, 1.92x, and 1.83x over FullAttn, InfLLMv2, and ShadowKV, respectively. We release our code at https://github.com/thunlp/NOSA.

---

### Physics-augmented Multi-task Gaussian Process for Modeling Spatiotemporal Dynamics

Authors: Xizhuo Zhang, Bing Yao
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13601v1

Recent advances in sensing and imaging technologies have enabled the collection of high-dimensional spatiotemporal data across complex geometric domains. However, effective modeling of such data remains challenging due to irregular spatial structures, rapid temporal dynamics, and the need to jointly predict multiple interrelated physical variables. This paper presents a physics-augmented multi-task Gaussian Process (P-M-GP) framework tailored for spatiotemporal dynamic systems. Specifically, we develop a geometry-aware, multi-task Gaussian Process (M-GP) model to effectively capture intrinsic spatiotemporal structure and inter-task dependencies. To further enhance the model fidelity and robustness, we incorporate governing physical laws through a physics-based regularization scheme, thereby constraining predictions to be consistent with governing dynamical principles. We validate the proposed P-M-GP framework on a 3D cardiac electrodynamics modeling task. Numerical experiments demonstrate that our method significantly improves prediction accuracy over existing methods by effectively incorporating domain-specific physical constraints and geometric prior.

---

### FreshTab: Sourcing Fresh Data for Table-to-Text Generation Evaluation

Authors: Kristýna Onderková, Ondřej Plátek, Zdeněk Kasner, Ondřej Dušek
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13598v1

Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is affected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the-fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contamination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experiment with German, Russian and French in addition to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic metrics, but this does not translate into LLM and human evaluations. Domain effects are visible in all evaluations, showing that a~domain-balanced benchmark is more challenging.

---

### EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis

Authors: Chen Wang, Yansen Wang, Dongqi Han, Zilong Wang, Dongsheng Li
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13592v1

Analyzing stereoelectroencephalography (SEEG) signals is critical for brain-computer interface (BCI) applications and neuroscience research, yet poses significant challenges due to the large number of input channels and their heterogeneous relevance. Traditional channel selection methods struggle to scale or provide meaningful interpretability for SEEG data. In this work, we propose EEGChaT, a novel Transformer-based channel selection module designed to automatically identify the most task-relevant channels in SEEG recordings. EEGChaT introduces Channel Aggregation Tokens (CATs) to aggregate information across channels, and leverages an improved Attention Rollout technique to compute interpretable, quantitative channel importance scores. We evaluate EEGChaT on the DuIN dataset, demonstrating that integrating EEGChaT with existing classification models consistently improves decoding accuracy, achieving up to 17\% absolute gains. Furthermore, the channel weights produced by EEGChaT show substantial overlap with manually selected channels, supporting the interpretability of the approach. Our results suggest that EEGChaT is an effective and generalizable solution for channel selection in high-dimensional SEEG analysis, offering both enhanced performance and insights into neural signal relevance.

---

### Subject Roles in the EU AI Act: Mapping and Regulatory Implications

Authors: Nicola Fabiano
Published: 2025-10-15
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2510.13591v1

The European Union's Artificial Intelligence Act (Regulation (EU) 2024/1689) establishes the world's first comprehensive regulatory framework for AI systems through a sophisticated ecosystem of interconnected subjects defined in Article 3. This paper provides a structured examination of the six main categories of actors - providers, deployers, authorized representatives, importers, distributors, and product manufacturers - collectively referred to as "operators" within the regulation. Through examination of these Article 3 definitions and their elaboration across the regulation's 113 articles, 180 recitals, and 13 annexes, we map the complete governance structure and analyze how the AI Act regulates these subjects. Our analysis reveals critical transformation mechanisms whereby subjects can assume different roles under specific conditions, particularly through Article 25 provisions ensuring accountability follows control. We identify how obligations cascade through the supply chain via mandatory information flows and cooperation requirements, creating a distributed yet coordinated governance system. The findings demonstrate how the regulation balances innovation with the protection of fundamental rights through risk-based obligations that scale with the capabilities and deployment contexts of AI systems, providing essential guidance for stakeholders implementing the AI Act's requirements.

---

### Deflanderization for Game Dialogue: Balancing Character Authenticity with Task Execution in LLM-based NPCs

Authors: Pasin Buakhaw, Kun Kerdthaisong, Phuree Phenhiran, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13586v3

The emergence of large language models (LLMs) has opened new opportunities for creating dynamic non-player characters (NPCs) in gaming environments, enabling both functional task execution and persona-consistent dialogue generation. In this paper, we (Tu_Character_lab) report our participation in the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025 Round 2, which evaluates agents across three tracks: task-oriented dialogue, context-aware dialogue, and their integration. Our approach combines two complementary strategies: (i) lightweight prompting techniques in the API track, including a Deflanderization prompting method to suppress excessive role-play and improve task fidelity, and (ii) fine-tuned large models in the GPU track, leveraging Qwen3-14B with supervisedfinetuning (SFT) and Low-Rank Adaptation(LoRA). Our best submissions ranked 2nd on Task 1, 2nd on Task 3 (API track), and 4th on Task 3 (GPU track).

---

### On the Identifiability of Causal Graphs with the Invariance Principle

Authors: Francesco Montagna
Published: 2025-10-15
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.13583v4

Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution {induced} by a structural causal model, and additional data from (in the best case) \textit{only two} environments that sufficiently differ in the noise statistics, the unique causal graph is identifiable. Notably, this is the first result in the literature that guarantees the entire causal graph recovery with a constant number of environments and arbitrary nonlinear mechanisms. Our only constraint is the Gaussianity of the noise terms; however, we propose potential ways to relax this requirement. Of interest on its own, we expand on the well-known duality between independent component analysis (ICA) and causal discovery; recent advancements have shown that nonlinear ICA can be solved from multiple environments, at least as many as the number of sources: we show that the same can be achieved for causal discovery while having access to much less auxiliary information.

---

### ArtNet: Hierarchical Clustering-Based Artificial Netlist Generator for ML and DTCO Application

Authors: Andrew B. Kahng. Seokhyeong Kang, Seonghyeon Park, Dooseok Yoon
Published: 2025-10-15
Categories: cs.LG, cs.AR
arXiv: https://arxiv.org/abs/2510.13582v2

In advanced nodes, optimization of power, performance and area (PPA) has become highly complex and challenging. Machine learning (ML) and design-technology co-optimization (DTCO) provide promising mitigations, but face limitations due to a lack of diverse training data as well as long design flow turnaround times (TAT). We propose ArtNet, a novel artificial netlist generator designed to tackle these issues. Unlike previous methods, ArtNet replicates key topological characteristics, enhancing ML model generalization and supporting broader design space exploration for DTCO. By producing realistic artificial datasets that moreclosely match given target parameters, ArtNet enables more efficient PPAoptimization and exploration of flows and design enablements. In the context of CNN-based DRV prediction, ArtNet's data augmentationimproves F1 score by 0.16 compared to using only the original (real) dataset. In the DTCO context, ArtNet-generated mini-brains achieve a PPA match up to 97.94%, demonstrating close alignment with design metrics of targeted full-scale block designs.

---

### Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models

Authors: Daniil Gurgurov, Tanja Baeumel, Josef van Genabith, Simon Ostermann
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13580v2

Large language models (LLMs) exhibit substantial performance disparities across languages, particularly between high- and low-resource settings. We propose a framework for improving performance in underrepresented languages while preserving general-purpose capabilities via targeted fine-tuning of sparse, language-associated subnetworks. Our approach identifies language-relevant neurons using Language Activation Probability Entropy (LAPE), an information-theoretic metric that reliably captures language-specific activation patterns, and fine-tunes only the corresponding weights. Experiments on Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B across 12 mid- and low-resource languages show that our method consistently outperforms full fine-tuning, FFN-only fine-tuning, LoRA, IA^3, and random-subset baselines while updating only 0.2-1% of model parameters. We further show that sparse, neuron-targeted fine-tuning can inject new language capabilities without catastrophic forgetting, with potential applicability to other model capabilities. Mechanistic analyses of weight updates and internal representations reveal asymmetric roles of FFN projections in language adaptation and improved cross-lingual alignment. Finally, we release language neuron sets for over 100 languages together with our adaptation pipeline, enabling a cost-effective path for extending LLMs to underrepresented languages.

---

### Selective Adversarial Attacks on LLM Benchmarks

Authors: Ivan Dubrovsky, Anastasia Orlova, Illarion Iov, Nina Gubina, Irena Gureeva, Alexey Zaytsev
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13570v1

Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Prior work on adversarial robustness in NLP has emphasized text attacks that affect many models equally, leaving open the question of whether it is possible to selectively degrade or enhance performance while minimally affecting other models. We formalize this problem and study selective adversarial attacks on MMLU - a widely used benchmark designed to measure a language model's broad general knowledge and reasoning ability across different subjects. Using canonical attacks integrated into TextAttack framework, we introduce a protocol for selectivity assessment, develop a custom constraint to increase selectivity of attacks and propose a surrogate-LLM pipeline that generates selective perturbations. Empirically, we find that selective adversarial attacks exist and can materially alter relative rankings, challenging the fairness, reproducibility, and transparency of leaderboard-driven evaluation. Our results motivate perturbation-aware reporting and robustness diagnostics for LLM evaluation and demonstrate that even subtle edits can shift comparative judgments.

---

### DOLFIN: Balancing Stability and Plasticity in Federated Continual Learning

Authors: Omayma Moussadek, Riccardo Salami, Simone Calderara
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13567v1

Federated continual learning (FCL) enables models to learn new tasks across multiple distributed clients, protecting privacy and without forgetting previously acquired knowledge. However, current methods face challenges balancing performance, privacy preservation, and communication efficiency. We introduce a Distributed Online LoRA for Federated INcremental learning method DOLFIN, a novel approach combining Vision Transformers with low-rank adapters designed to efficiently and stably learn new tasks in federated environments. Our method leverages LoRA for minimal communication overhead and incorporates DualGradient Projection Memory (DualGPM) to prevent forgetting. Evaluated on CIFAR-100, ImageNet-R, ImageNet-A, and CUB-200 under two Dirichlet heterogeneity settings, DOLFIN consistently surpasses six strong baselines in final average accuracy while matching their memory footprint. Orthogonal low-rank adapters offer an effective and scalable solution for privacy-preserving continual learning in federated settings.

---

### XD-RCDepth: Lightweight Radar-Camera Depth Estimation with Explainability-Aligned and Distribution-Aware Distillation

Authors: Huawei Sun, Zixu Wang, Xiangyuan Peng, Julius Ott, Georg Stettinger, Lorenzo Servadei, Robert Wille
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13565v3

Depth estimation remains central to autonomous driving, and radar-camera fusion offers robustness in adverse conditions by providing complementary geometric cues. In this paper, we present XD-RCDepth, a lightweight architecture that reduces the parameters by 29.7% relative to the state-of-the-art lightweight baseline while maintaining comparable accuracy. To preserve performance under compression and enhance interpretability, we introduce two knowledge-distillation strategies: an explainability-aligned distillation that transfers the teacher's saliency structure to the student, and a depth-distribution distillation that recasts depth regression as soft classification over discretized bins. Together, these components reduce the MAE compared with direct training with 7.97% and deliver competitive accuracy with real-time efficiency on nuScenes and ZJU-4DRadarCam datasets. Code: https://github.com/harborsarah/XD_RCDepth

---

### An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET

Authors: Liyang Hu, Chong Chen
Published: 2025-10-15
Categories: physics.med-ph, cs.CV, math.NA
arXiv: https://arxiv.org/abs/2510.13562v1

In positron emission tomography (PET), it is indispensable to perform attenuation correction in order to obtain the quantitatively accurate activity map (tracer distribution) in the body. Generally, this is carried out based on the estimated attenuation map obtained from computed tomography or magnetic resonance imaging. However, except for errors in the attenuation correction factors obtained, the additional scan not only brings in new radiation doses and/or increases the scanning time but also leads to severe misalignment induced by various motions during and between the two sequential scans. To address these issues, based on maximum likelihood estimation, we propose a new mathematical model for simultaneously reconstructing the activity and attenuation sinogram from the time-of-flight (TOF)-PET emission data only. Particularly, we make full use of the exclusively exponential form for the attenuation correction factors, and consider the constraint of a total amount of the activity in some mask region in the proposed model. Furthermore, we prove its well-posedness, including the existence, uniqueness and stability of the solution. We propose an alternating update algorithm to solve the model, and also analyze its convergence. Finally, numerical experiments with various TOF-PET emission data demonstrate that the proposed method is of numerical convergence and robust to noise, and outperforms some state-of-the-art methods in terms of accuracy and efficiency, and has the capability of autonomous attenuation correction.

---

### OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studies

Authors: Peng Di, Faqiang Chen, Xiao Bai, Hongjun Yang, Qingfeng Li, Ganglin Wei, Jian Mou, Feng Shi, Keting Chen, Peng Tang, Zhitao Shen, Zheng Li et al.
Published: 2025-10-15
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.13561v2

The escalating complexity of modern software imposes an unsustainable operational burden on Site Reliability Engineering (SRE) teams, demanding AI-driven automation that can emulate expert diagnostic reasoning. Existing solutions, from traditional AI methods to general-purpose multi-agent systems, fall short: they either lack deep causal reasoning or are not tailored for the specialized, investigative workflows unique to SRE. To address this gap, we present OpenDerisk, a specialized, open-source multi-agent framework architected for SRE. OpenDerisk integrates a diagnostic-native collaboration model, a pluggable reasoning engine, a knowledge engine, and a standardized protocol (MCP) to enable specialist agents to collectively solve complex, multi-domain problems. Our comprehensive evaluation demonstrates that OpenDerisk significantly outperforms state-of-the-art baselines in both accuracy and efficiency. This effectiveness is validated by its large-scale production deployment at Ant Group, where it serves over 3,000 daily users across diverse scenarios, confirming its industrial-grade scalability and practical impact. OpenDerisk is open source and available at https://github.com/derisk-ai/OpenDerisk/

---

### Multi-Objective $\textit{min-max}$ Online Convex Optimization

Authors: Rahul Vaze, Sumiran Mishra
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13560v3

In this paper, we broaden the horizon of online convex optimization (OCO), and consider multi-objective OCO, where there are $K$ distinct loss function sequences, and an algorithm has to choose its action at time $t$, before the $K$ loss functions at time $t$ are revealed. To capture the tradeoff between tracking the $K$ different sequences, we consider the {\it min-max} regret, where the benchmark (optimal offline algorithm) takes a static action across all time slots that minimizes the maximum of the total loss (summed across time slots) incurred by each of the $K$ sequences. An online algorithm is allowed to change its action across time slots, and its {\it min-max} regret is defined as the difference between its {\it min-max} cost and that of the benchmark. The {\it min-max} regret is a stringent performance measure and an algorithm with small regret needs to `track' all loss functions simultaneously. We first show that with adversarial input, {\it min-max} regret scales linearly with the time horizon $T$ for any online algorithm. Consequently, we consider a stochastic i.i.d. input model where all loss functions are i.i.d. generated from an unknown joint distribution and propose a simple algorithm that combines the well-known {\it Hedge} and online gradient descent (OGD) and show via a remarkably simple proof that its expected {\it min-max} regret is $O(\sqrt{T \log (T K)})$. Analogous results are also derived for Martingale difference and Markov input models.

---