# Research Papers — 2025-10 · bundle page 81 of 217

> Full-text markdown of papers #4001–4050 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/81
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/80.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/82.md)

### Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples

Authors: Sidney Bender, Ole Delzer, Jan Herrmann, Heike Antje Marxfeld, Klaus-Robert Müller, Grégoire Montavon
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17524v1

Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-supervised models. Group distributional robustness methods, such as Deep Feature Reweighting (DFR) rely on explicit group labels to upweight underrepresented subgroups, but face key limitations: (1) group labels are often unavailable, (2) low within-group sample sizes hinder coverage of the subgroup distribution, and (3) performance degrades sharply when multiple spurious correlations fragment the data into even smaller groups. We propose Counterfactual Knowledge Distillation (CFKD), a framework that sidesteps these issues by generating diverse counterfactuals, enabling a human annotator to efficiently explore and correct the model's decision boundaries through a knowledge distillation step. Unlike DFR, our method not only reweights the undersampled groups, but it also enriches them with new data points. Our method does not require any confounder labels, achieves effective scaling to multiple confounders, and yields balanced generalization across groups. We demonstrate CFKD's efficacy across five datasets, spanning synthetic tasks to an industrial application, with particularly strong gains in low-data regimes with pronounced spurious correlations. Additionally, we provide an ablation study on the effect of the chosen counterfactual explainer and teacher model, highlighting their impact on robustness.

---

### Curiosity Meets Cooperation: A Game-Theoretic Approach to Long-Tail Multi-Label Learning

Authors: Canran Xiao, Chuangxin Zhao, Zong Ke, Fei Shen
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17520v1

Long-tail imbalance is endemic to multi-label learning: a few head labels dominate the gradient signal, while the many rare labels that matter in practice are silently ignored. We tackle this problem by casting the task as a cooperative potential game. In our Curiosity-Driven Game-Theoretic Multi-Label Learning (CD-GTMLL) framework, the label space is split among several cooperating players that share a global accuracy payoff yet earn additional curiosity rewards that rise with label rarity and inter-player disagreement. These curiosity bonuses inject gradient on under-represented tags without hand-tuned class weights. We prove that gradient best-response updates ascend a differentiable potential and converge to tail-aware stationary points that tighten a lower bound on the expected Rare-F1. Extensive experiments on conventional benchmarks and three extreme-scale datasets show consistent state-of-the-art gains, delivering up to +4.3% Rare-F1 and +1.6% P@3 over the strongest baselines, while ablations reveal emergent division of labour and faster consensus on rare classes. CD-GTMLL thus offers a principled, scalable route to long-tail robustness in multi-label prediction.

---

### MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models

Authors: Yongshun Zhang, Zhongyi Fan, Yonghang Zhang, Zhangzikang Li, Weifeng Chen, Zhongwei Feng, Chaoyue Wang, Peng Hou, Anxiang Zeng
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17519v2

In recent years, large-scale generative models for visual content (\textit{e.g.,} images, videos, and 3D objects/scenes) have made remarkable progress. However, training large-scale video generation models remains particularly challenging and resource-intensive due to cross-modal text-video alignment, the long sequences involved, and the complex spatiotemporal dependencies. To address these challenges, we present a training framework that optimizes four pillars: (i) data processing, (ii) model architecture, (iii) training strategy, and (iv) infrastructure for large-scale video generation models. These optimizations delivered significant efficiency gains and performance improvements across all stages of data preprocessing, video compression, parameter scaling, curriculum-based pretraining, and alignment-focused post-training. Our resulting model, MUG-V 10B, matches recent state-of-the-art video generators overall and, on e-commerce-oriented video generation tasks, surpasses leading open-source baselines in human evaluations. More importantly, we open-source the complete stack, including model weights, Megatron-Core-based large-scale training code, and inference pipelines for video generation and enhancement. To our knowledge, this is the first public release of large-scale video generation training code that exploits Megatron-Core to achieve high training efficiency and near-linear multi-node scaling, details are available in https://github.com/Shopee-MUG/MUG-V.

---

### SAFE-D: A Spatiotemporal Detection Framework for Abnormal Driving Among Parkinson's Disease-like Drivers

Authors: Hangcheng Cao, Baixiang Huang, Longzhi Yuan, Haonan An, Zihan Fang, Xianhao Chen, Yuguang Fang
Published: 2025-10-20
Categories: cs.LG, cs.HC
arXiv: https://arxiv.org/abs/2510.17517v1

A driver's health state serves as a determinant factor in driving behavioral regulation. Subtle deviations from normalcy can lead to operational anomalies, posing risks to public transportation safety. While prior efforts have developed detection mechanisms for functionally-driven temporary anomalies such as drowsiness and distraction, limited research has addressed pathologically-triggered deviations, especially those stemming from chronic medical conditions. To bridge this gap, we investigate the driving behavior of Parkinson's disease patients and propose SAFE-D, a novel framework for detecting Parkinson-related behavioral anomalies to enhance driving safety. Our methodology starts by performing analysis of Parkinson's disease symptomatology, focusing on primary motor impairments, and establishes causal links to degraded driving performance. To represent the subclinical behavioral variations of early-stage Parkinson's disease, our framework integrates data from multiple vehicle control components to build a behavioral profile. We then design an attention-based network that adaptively prioritizes spatiotemporal features, enabling robust anomaly detection under physiological variability. Finally, we validate SAFE-D on the Logitech G29 platform and CARLA simulator, using data from three road maps to emulate real-world driving. Our results show SAFE-D achieves 96.8% average accuracy in distinguishing normal and Parkinson-affected driving patterns.

---

### SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors

Authors: Tiancheng Hu, Joachim Baumann, Lorenzo Lupo, Nigel Collier, Dirk Hovy, Paul Röttger
Published: 2025-10-20
Categories: cs.CL, cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.17516v4

Large language model (LLM) simulations of human behavior have the potential to revolutionize the social and behavioral sciences, if and only if they faithfully reflect real human behaviors. Current evaluations of simulation fidelity are fragmented, based on bespoke tasks and metrics, creating a patchwork of incomparable results. To address this, we introduce SimBench, the first large-scale, standardized benchmark for a robust, reproducible science of LLM simulation. By unifying 20 diverse datasets covering tasks from moral decision-making to economic choice across a large global participant pool, SimBench provides the necessary foundation to ask fundamental questions about when, how, and why LLM simulations succeed or fail. We show that the best LLMs today achieve meaningful but modest simulation fidelity (score: 40.80/100), with performance scaling log-linearly with model size but not with increased inference-time compute. We discover an alignment-simulation tradeoff: instruction tuning improves performance on low-entropy (consensus) questions but degrades it on high-entropy (diverse) ones. Models particularly struggle when simulating specific demographic groups. Finally, we demonstrate that simulation ability correlates most strongly with knowledge-intensive reasoning (MMLU-Pro, r = 0.939). By making progress measurable, we aim to accelerate the development of more faithful LLM simulators.

---

### The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Authors: Hoang Pham, The-Anh Ta, Tom Jacobs, Rebekka Burkholz, Long Tran-Thanh
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17515v1

Sparse neural networks promise efficiency, yet training them effectively remains a fundamental challenge. Despite advances in pruning methods that create sparse architectures, understanding why some sparse structures are better trainable than others with the same level of sparsity remains poorly understood. Aiming to develop a systematic approach to this fundamental problem, we propose a novel theoretical framework based on the theory of graph limits, particularly graphons, that characterizes sparse neural networks in the infinite-width regime. Our key insight is that connectivity patterns of sparse neural networks induced by pruning methods converge to specific graphons as networks' width tends to infinity, which encodes implicit structural biases of different pruning methods. We postulate the Graphon Limit Hypothesis and provide empirical evidence to support it. Leveraging this graphon representation, we derive a Graphon Neural Tangent Kernel (Graphon NTK) to study the training dynamics of sparse networks in the infinite width limit. Graphon NTK provides a general framework for the theoretical analysis of sparse networks. We empirically show that the spectral analysis of Graphon NTK correlates with observed training dynamics of sparse networks, explaining the varying convergence behaviours of different pruning methods. Our framework provides theoretical insights into the impact of connectivity patterns on the trainability of various sparse network architectures.

---

### AWARE: Audio Watermarking with Adversarial Resistance to Edits

Authors: Kosta Pavlović, Lazar Stanarević, Petar Nedić, Elena Nešović Slavko Kovačević, Igor Djurović
Published: 2025-10-20
Categories: cs.SD, cs.LG, cs.MM, eess.AS
arXiv: https://arxiv.org/abs/2510.17512v2

Prevailing practice in learning-based audio watermarking is to pursue robustness by expanding the set of simulated distortions during training. However, such surrogates are narrow and prone to overfitting. This paper presents AWARE (Audio Watermarking with Adversarial Resistance to Edits), an alternative approach that avoids reliance on attack-simulation stacks and handcrafted differentiable distortions. Embedding is obtained through adversarial optimization in the time-frequency domain under a level-proportional perceptual budget. Detection employs a time-order-agnostic detector with a Bitwise Readout Head (BRH) that aggregates temporal evidence into one score per watermark bit, enabling reliable watermark decoding even under desynchronization and temporal cuts. Empirically, AWARE attains high audio quality and speech intelligibility (PESQ/STOI) and consistently low BER across various audio edits, often surpassing representative state-of-the-art learning-based systems.

---

### Annotation-Efficient Universal Honesty Alignment

Authors: Shiyu Ni, Keping Bi, Jiafeng Guo, Minghao Tang, Jingtong Wu, Zengxin Han, Xueqi Cheng
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17509v3

Honesty alignment-the ability of large language models (LLMs) to recognize their knowledge boundaries and express calibrated confidence-is essential for trustworthy deployment. Existing methods either rely on training-free confidence estimation (e.g., token probabilities, self-consistency) or training-based calibration with correctness annotations. While effective, achieving universal honesty alignment with training-based calibration requires costly, large-scale labeling. To support annotation-efficient training, we introduce Elicitation-Then-Calibration (EliCal), a two-stage framework that first elicits internal confidence using inexpensive self-consistency supervision, then calibrates this confidence with a small set of correctness annotations. To support a large-scale study, we release HonestyBench, a benchmark covering ten free-form QA datasets with 560k training and 70k evaluation instances annotated with correctness and self-consistency signals. Experiments show that EliCal achieves near-optimal alignment with only 1k correctness annotations (0.18% of full supervision) and better alignment performance on unseen MMLU tasks than the calibration-only baseline, offering a scalable solution toward universal honesty alignment in LLMs.

---

### Convergence Rates for Gradient Descent on the Edge of Stability in Overparametrised Least Squares

Authors: Lachlan Ewen MacDonald, Hancheng Min, Leandro Palma, Salma Tarmoun, Ziqing Xu, René Vidal
Published: 2025-10-20
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2510.17506v1

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large step size regime called the ``edge of stability", in which the objective decreases non-monotonically with an observed implicit bias towards flat minima. In this paper, we take a step toward quantifying this phenomenon by providing convergence rates for gradient descent with large learning rates in an overparametrised least squares setting. The key insight behind our analysis is that, as a consequence of overparametrisation, the set of global minimisers forms a Riemannian manifold $M$, which enables the decomposition of the GD dynamics into components parallel and orthogonal to $M$. The parallel component corresponds to Riemannian gradient descent on the objective sharpness, while the orthogonal component is a bifurcating dynamical system. This insight allows us to derive convergence rates in three regimes characterised by the learning rate size: (a) the subcritical regime, in which transient instability is overcome in finite time before linear convergence to a suboptimally flat global minimum; (b) the critical regime, in which instability persists for all time with a power-law convergence toward the optimally flat global minimum; and (c) the supercritical regime, in which instability persists for all time with linear convergence to an orbit of period two centred on the optimally flat global minimum.

---

### Lingua Custodi's participation at the WMT 2025 Terminology shared task

Authors: Jingshu Liu, Raheel Qader, Gaëtan Caillaut, Mariam Nakhlé
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17504v1

While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored. We systematically investigate methods for learning multilingual sentence embeddings by combining the best methods for learning monolingual and cross-lingual representations including: masked language modeling (MLM), translation language modeling (TLM), dual encoder translation ranking, and additive margin softmax. We show that introducing a pre-trained multilingual language model dramatically reduces the amount of parallel training data required to achieve good performance by 80%. Composing the best of these methods produces a model that achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, well above the 65.5 achieved by LASER, while still performing competitively on monolingual transfer learning benchmarks. Parallel data mined from CommonCrawl using our best model is shown to train competitive NMT models for en-zh and en-de. We publicly release our best multilingual sentence embedding model for 109+ languages at https://tfhub.dev/google/LaBSE.

---

### Stochastic Difference-of-Convex Optimization with Momentum

Authors: El Mahdi Chayti, Martin Jaggi
Published: 2025-10-20
Categories: cs.LG, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2510.17503v2

We study the online stochastic difference-of-convex (DC) program $\min_{x \in R^n} F(x) = G(x) - H(x) + r_1(x) - r_2(x)$, which covers sparse learning with nonconvex penalties, robust regression with smooth robust losses, and non-negative positive--unlabeled learning. We propose \emph{momentum-based DCA} (MDCA), which combines a damped DCA step with a momentum estimator for $\nabla H$ and uses a constant per-iteration batch size. With exact solutions of the convex subproblems, MDCA with Polyak momentum uses $\mathcal{O}( ε^{-4})$ stochastic gradients of $H$ to reach $ε$-stationarity, and momentum-based variance reduction (MVR) uses $\mathcal{O}(ε^{-3})$ under averaged smoothness, with a single $\mathcal O(ε^{-1})$ warm-up batch in place of the periodic large batches of DCA-PAGE, whose $ε$-dependence it matches. We also introduce a single-loop variant (S-MDCA) that replaces the subproblem solve by one stochastic prox-gradient step; for every fixed smoothing parameter $γ$ for which the separately smoothed surrogate $F_γ$ is bounded below, it reaches $ε$-stationarity of $F_γ$ in $\mathcal{O}(ε^{-4})$ iterations, which does not by itself imply stationarity of $F$. A variance--drift trade-off lemma describes how the momentum parameter trades estimator variance against iterate-drift bias in steady-state upper bounds. Guarantees are given for two criteria: the critical-distance measure, and a DCA fixed-point residual that requires no smoothness of $r_2$ and vanishes exactly at DC-critical points; both give the same $ε$-dependence. Experiments on two LIBSVM classification datasets illustrate the methods' behaviour.

---

### Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarization

Authors: Yuanli Wu, Long Zhang, Yue Du, Bin Li
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17501v3

We propose a rubric-guided, pseudo-labeled, and prompt-driven zero-shot video summarization framework that bridges large language models with structured semantic reasoning. A small subset of human annotations is converted into high-confidence pseudo labels and organized into dataset-adaptive rubrics defining clear evaluation dimensions such as thematic relevance, action detail, and narrative progression. During inference, boundary scenes, including the opening and closing segments, are scored independently based on their own descriptions, while intermediate scenes incorporate concise summaries of adjacent segments to assess narrative continuity and redundancy. This design enables the language model to balance local salience with global coherence without any parameter tuning. Across three benchmarks, the proposed method achieves stable and competitive results, with F1 scores of 57.58 on SumMe, 63.05 on TVSum, and 53.79 on QFVS, surpassing zero-shot baselines by +0.85, +0.84, and +0.37, respectively. These outcomes demonstrate that rubric-guided pseudo labeling combined with contextual prompting effectively stabilizes LLM-based scoring and establishes a general, interpretable, and training-free paradigm for both generic and query-focused video summarization.

---

### Deep Self-Evolving Reasoning

Authors: Zihan Liu, Shun Zheng, Xumeng Wen, Yang Wang, Jiang Bian, Mao Yang
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17498v1

Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their effectiveness hinges on strong, reliable verification and correction capabilities, which remain fragile in open-weight, smaller-scale models. This work demonstrates that even with weak verification and refinement capabilities on hard tasks, the reasoning limits of such models can be substantially extended through a probabilistic paradigm we call Deep Self-Evolving Reasoning (DSER). We conceptualize iterative reasoning as a Markov chain, where each step represents a stochastic transition in the solution space. The key insight is that convergence to a correct solution is guaranteed as long as the probability of improvement marginally exceeds that of degradation. By running multiple long-horizon, self-evolving processes in parallel, DSER amplifies these small positive tendencies, enabling the model to asymptotically approach correct answers. Empirically, we apply DSER to the DeepSeek-R1-0528-Qwen3-8B model. On the challenging AIME 2024-2025 benchmark, DSER solves 5 out of 9 previously unsolvable problems and boosts overall performance, enabling this compact model to surpass the single-turn accuracy of its 600B-parameter teacher through majority voting. Beyond its immediate utility for test-time scaling, the DSER framework serves to diagnose the fundamental limitations of current open-weight reasoners. By clearly delineating their shortcomings in self-verification, refinement, and stability, our findings establish a clear research agenda for developing next-generation models with powerful, intrinsic self-evolving capabilities.

---

### I-RAVEN-X: Benchmarking Generalization and Robustness of Analogical and Mathematical Reasoning in Large Language and Reasoning Models

Authors: Giacomo Camposampiero, Michael Hersche, Roger Wattenhofer, Abu Sebastian, Abbas Rahimi
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17496v2

We introduce I-RAVEN-X, a symbolic benchmark designed to evaluate generalization and robustness in analogical and mathematical reasoning for Large Language Models (LLMs) and Large Reasoning Models (LRMs). I-RAVEN-X extends I-RAVEN by increasing operand complexity, attribute range, and introducing perceptual uncertainty. Compared to LLMs, empirical results show that LRMs achieve improved productivity and systematicity on longer reasoning relations and wider attribute ranges, respectively. However, LRMs are still significantly challenged by reasoning under uncertainty and cannot effectively explore multiple probabilistic outcomes.

---

### Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents

Authors: Yihong Tang, Kehai Chen, Liang Yue, Jinxin Fan, Caishen Zhou, Xiaoguang Li, Yuyang Zhang, Mingming Zhao, Shixiong Kai, Kaiyang Guo, Xingshan Zeng, Wenjing Cun et al.
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17491v1

With the rise of large language models (LLMs), LLM agents capable of autonomous reasoning, planning, and executing complex tasks have become a frontier in artificial intelligence. However, how to translate the research on general agents into productivity that drives industry transformations remains a significant challenge. To address this, this paper systematically reviews the technologies, applications, and evaluation methods of industry agents based on LLMs. Using an industry agent capability maturity framework, it outlines the evolution of agents in industry applications, from "process execution systems" to "adaptive social systems." First, we examine the three key technological pillars that support the advancement of agent capabilities: Memory, Planning, and Tool Use. We discuss how these technologies evolve from supporting simple tasks in their early forms to enabling complex autonomous systems and collective intelligence in more advanced forms. Then, we provide an overview of the application of industry agents in real-world domains such as digital engineering, scientific discovery, embodied intelligence, collaborative business execution, and complex system simulation. Additionally, this paper reviews the evaluation benchmarks and methods for both fundamental and specialized capabilities, identifying the challenges existing evaluation systems face regarding authenticity, safety, and industry specificity. Finally, we focus on the practical challenges faced by industry agents, exploring their capability boundaries, developmental potential, and governance issues in various scenarios, while providing insights into future directions. By combining technological evolution with industry practices, this review aims to clarify the current state and offer a clear roadmap and theoretical foundation for understanding and building the next generation of industry agents.

---

### DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning

Authors: Yongxin He, Shan Zhang, Yixuan Cao, Lei Ma, Ping Luo
Published: 2025-10-20
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.17489v1

Detecting AI-involved text is essential for combating misinformation, plagiarism, and academic misconduct. However, AI text generation includes diverse collaborative processes (AI-written text edited by humans, human-written text edited by AI, and AI-generated text refined by other AI), where various or even new LLMs could be involved. Texts generated through these varied processes exhibit complex characteristics, presenting significant challenges for detection. Current methods model these processes rather crudely, primarily employing binary classification (purely human vs. AI-involved) or multi-classification (treating human-AI collaboration as a new class). We observe that representations of texts generated through different processes exhibit inherent clustering relationships. Therefore, we propose DETree, a novel approach that models the relationships among different processes as a Hierarchical Affinity Tree structure, and introduces a specialized loss function that aligns text representations with this tree. To facilitate this learning, we developed RealBench, a comprehensive benchmark dataset that automatically incorporates a wide spectrum of hybrid texts produced through various human-AI collaboration processes. Our method improves performance in hybrid text detection tasks and significantly enhances robustness and generalization in out-of-distribution scenarios, particularly in few-shot learning conditions, further demonstrating the promise of training-based approaches in OOD settings. Our code and dataset are available at https://github.com/heyongxin233/DETree.

---

### Local properties of neural networks through the lens of layer-wise Hessians

Authors: Maxim Bolshim, Alexander Kugaevskikh
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17486v2

We introduce a methodology for analyzing neural networks through the lens of layer-wise Hessian matrices. The local Hessian of each functional block (layer) is defined as the matrix of second derivatives of a scalar function with respect to the parameters of that layer. This concept provides a formal tool for characterizing the local geometry of the parameter space. We show that the spectral properties of local Hessians, such as the distribution of eigenvalues, reveal quantitative patterns associated with overfitting, underparameterization, and expressivity in neural network architectures. We conduct an extensive empirical study involving 111 experiments across 37 datasets. The results demonstrate consistent structural regularities in the evolution of local Hessians during training and highlight correlations between their spectra and generalization performance. These findings establish a foundation for using local geometric analysis to guide the diagnosis and design of deep neural networks. The proposed framework connects optimization geometry with functional behavior and offers practical insight for improving network architectures and training stability.

---

### Split-Fuse-Transport: Annotation-Free Saliency via Dual Clustering and Optimal Transport Alignment

Authors: Muhammad Umer Ramzan, Ali Zia, Abdelwahed Khamis, Noman Ali, Usman Ali, Wei Xiang
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17484v1

Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications. We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available. We revisit the prototype-based line of work and make two key observations. First, boundary pixels and interior pixels obey markedly different geometry; second, the global consistency enforced by optimal transport (OT) is underutilized if prototype quality is weak. To address this, we introduce POTNet, an adaptation of Prototypical Optimal Transport that replaces POT's single k-means step with an entropy-guided dual-clustering head: high-entropy pixels are organized by spectral clustering, low-entropy pixels by k-means, and the two prototype sets are subsequently aligned by OT. This split-fuse-transport design yields sharper, part-aware pseudo-masks in a single forward pass, without handcrafted priors. Those masks supervise a standard MaskFormer-style encoder-decoder, giving rise to AutoSOD, an end-to-end unsupervised SOD pipeline that eliminates SelfMask's offline voting yet improves both accuracy and training efficiency. Extensive experiments on five benchmarks show that AutoSOD outperforms unsupervised methods by up to 26% and weakly supervised methods by up to 36% in F-measure, further narrowing the gap to fully supervised models.

---

### ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts

Authors: Zheyue Tan, Zhiyuan Li, Tao Yuan, Dong Zhou, Weilin Liu, Yueqing Zhuang, Yadong Li, Guowei Niu, Cheng Qin, Zhuyu Yao, Congyi Liu, Haiyang Xu et al.
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17483v1

Mixture-of-Experts (MoE) architectures have emerged as a promising approach to scale Large Language Models (LLMs). MoE boosts the efficiency by activating a subset of experts per token. Recent works show that fine-grained experts substantially enriches the combinatorial flexibility of active experts and enhances model expressiveness. However, such a design is fundamentally limited by the layer-local routing mechanism: each layer is restricted to its own expert pool. This requires a careful trade-off between expert dimensionality and routing diversity given fixed parameter budgets. We describe ReXMoE, a novel MoE architecture that improves routing beyond the existing layer-local approaches by allowing routers to reuse experts across adjacent layers. ReXMoE decouples expert dimensionality from per-layer budgets, enabling richer expert combinations without sacrificing individual expert capacity or inflating overall parameters. To this end, we propose a new progressive scaling routing (PSR) strategy to gradually increase the candidate expert pool during training. As a result, ReXMoE improves both language modeling and downstream task performance. Extensive experiments on models ranging from 0.5B to 7B parameters across different architectures demonstrate that ReXMoE consistently improves performance under fixed architectural dimensions, confirming ReXMoE as new design paradigm for parameter-efficient and scalable MoE-based LLMs.

---

### SparseWorld: A Flexible, Adaptive, and Efficient 4D Occupancy World Model Powered by Sparse and Dynamic Queries

Authors: Chenxu Dang, Haiyan Liu, Jason Bao, Pei An, Xinyue Tang, PanAn, Jie Ma, Bingchuan Sun, Yan Wang
Published: 2025-10-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.17482v3

Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on static and fixed embeddings or grids, which inherently limit the flexibility of perception. Moreover, their ``in-place classification" over grids exhibits a potential misalignment with the dynamic and continuous nature of real scenarios. In this paper, we propose SparseWorld, a novel 4D occupancy world model that is flexible, adaptive, and efficient, powered by sparse and dynamic queries. We propose a Range-Adaptive Perception module, in which learnable queries are modulated by the ego vehicle states and enriched with temporal-spatial associations to enable extended-range perception. To effectively capture the dynamics of the scene, we design a State-Conditioned Forecasting module, which replaces classification-based forecasting with regression-guided formulation, precisely aligning the dynamic queries with the continuity of the 4D environment. In addition, We specifically devise a Temporal-Aware Self-Scheduling training strategy to enable smooth and efficient training. Extensive experiments demonstrate that SparseWorld achieves state-of-the-art performance across perception, forecasting, and planning tasks. Comprehensive visualizations and ablation studies further validate the advantages of SparseWorld in terms of flexibility, adaptability, and efficiency.

---

### Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization

Authors: Aurélien Bellet, Edwige Cyffers, Davide Frey, Romaric Gaudel, Dimitri Lerévérend, François Taïani
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17480v2

Decentralized Learning (DL) enables users to collaboratively train models without sharing raw data by iteratively averaging local updates with neighbors in a network graph. This setting is increasingly popular for its scalability and its ability to keep data local under user control. Strong privacy guarantees in DL are typically achieved through Differential Privacy (DP), with results showing that DL can even amplify privacy by disseminating noise across peer-to-peer communications. Yet in practice, the observed privacy-utility trade-off often appears worse than in centralized training, which may be due to limitations in current DP accounting methods for DL. In this paper, we show that recent advances in centralized DP accounting based on Matrix Factorization (MF) for analyzing temporal noise correlations can also be leveraged in DL. By generalizing existing MF results, we show how to cast both standard DL algorithms and common trust models into a unified formulation. This yields tighter privacy accounting for existing DP-DL algorithms and provides a principled way to develop new ones. To demonstrate the approach, we introduce MAFALDA-SGD, a gossip-based DL algorithm with user-level correlated noise that outperforms existing methods on synthetic and real-world graphs.

---

### Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS

Authors: Feng Zhou, Wenkai Guo, Pu Cao, Zhicheng Zhang, Jianqin Yin
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17479v1

Sparse-view 3D Gaussian Splatting (3DGS) often overfits to the training views, leading to artifacts like blurring in novel view rendering. Prior work addresses it either by enhancing the initialization (\emph{i.e.}, the point cloud from Structure-from-Motion (SfM)) or by adding training-time constraints (regularization) to the 3DGS optimization. Yet our controlled ablations reveal that initialization is the decisive factor: it determines the attainable performance band in sparse-view 3DGS, while training-time constraints yield only modest within-band improvements at extra cost. Given initialization's primacy, we focus our design there. Although SfM performs poorly under sparse views due to its reliance on feature matching, it still provides reliable seed points. Thus, building on SfM, our effort aims to supplement the regions it fails to cover as comprehensively as possible. Specifically, we design: (i) frequency-aware SfM that improves low-texture coverage via low-frequency view augmentation and relaxed multi-view correspondences; (ii) 3DGS self-initialization that lifts photometric supervision into additional points, compensating SfM-sparse regions with learned Gaussian centers; and (iii) point-cloud regularization that enforces multi-view consistency and uniform spatial coverage through simple geometric/visibility priors, yielding a clean and reliable point cloud. Our experiments on LLFF and Mip-NeRF360 demonstrate consistent gains in sparse-view settings, establishing our approach as a stronger initialization strategy. Code is available at https://github.com/zss171999645/ItG-GS.

---

### Towards geological inference with process-based and deep generative modeling, part 2: inversion of fluvial deposits and latent-space disentanglement

Authors: Guillaume Rongier, Luk Peeters
Published: 2025-10-20
Categories: cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.17478v1

High costs and uncertainties make subsurface decision-making challenging, as acquiring new data is rarely scalable. Embedding geological knowledge directly into predictive models offers a valuable alternative. A joint approach enables just that: process-based models that mimic geological processes can help train generative models that make predictions more efficiently. This study explores whether a generative adversarial network (GAN) - a type of deep-learning algorithm for generative modeling - trained to produce fluvial deposits can be inverted to match well and seismic data. Four inversion approaches applied to three test samples with 4, 8, and 20 wells struggled to match these well data, especially as the well number increased or as the test sample diverged from the training data. The key bottleneck lies in the GAN's latent representation: it is entangled, so samples with similar sedimentological features are not necessarily close in the latent space. Label conditioning or latent overparameterization can partially disentangle the latent space during training, although not yet sufficiently for a successful inversion. Fine-tuning the GAN to restructure the latent space locally reduces mismatches to acceptable levels for all test cases, with and without seismic data. But this approach depends on an initial, partially successful inversion step, which influences the quality and diversity of the final samples. Overall, GANs can already handle the tasks required for their integration into geomodeling workflows. We still need to further assess their robustness, and how to best leverage them in support of geological interpretation.

---

### Zoom In Disparities in Healthcare LLM Q&A

Authors: Ipek Baris Schlicht, Burcu Sayin, Zhixue Zhao, Frederik M. Labonté, Cesare Barbera, Marco Viviani, Paolo Rosso, Lucie Flek
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17476v2

Equitable access to reliable health information is vital when integrating AI into healthcare. Yet, information quality varies across languages, raising concerns about the reliability and consistency of multilingual Large Language Models (LLMs). We systematically examine cross-lingual disparities in pre-training source and factuality alignment in LLM answers for multilingual healthcare Q&A across English, German, Turkish, Chinese (Mandarin), and Italian. We (i) constructed Multilingual Wiki Health Care (MultiWikiHealthCare), a multilingual dataset from Wikipedia; (ii) analyzed cross-lingual healthcare coverage; (iii) assessed LLM response alignment with these references; and (iv) conducted a case study on factual alignment through the use of contextual information and Retrieval-Augmented Generation (RAG). Our findings reveal substantial cross-lingual disparities in both Wikipedia coverage and LLM factual alignment. Across LLMs, responses align more with English Wikipedia, even when the prompts are non-English. Providing contextual excerpts from non-English Wikipedia at inference time effectively shifts factual alignment toward culturally relevant knowledge. These results highlight practical pathways for building more equitable, multilingual AI systems for healthcare.

---

### DAMSDAN: Distribution-Aware Multi-Source Domain Adaptation Network for Cross-Domain EEG-based Emotion Recognition

Authors: Fo Hu, Can Wang, Qinxu Zheng, Xusheng Yang, Bin Zhou, Gang Li, Yu Sun, Wen-an Zhang
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17475v1

Significant inter-individual variability limits the generalization of EEG-based emotion recognition under cross-domain settings. We address two core challenges in multi-source adaptation: (1) dynamically modeling distributional heterogeneity across sources and quantifying their relevance to a target to reduce negative transfer; and (2) achieving fine-grained semantic consistency to strengthen class discrimination. We propose a distribution-aware multi-source domain adaptation network (DAMSDAN). DAMSDAN integrates prototype-based constraints with adversarial learning to drive the encoder toward discriminative, domain-invariant emotion representations. A domain-aware source weighting strategy based on maximum mean discrepancy (MMD) dynamically estimates inter-domain shifts and reweights source contributions. In addition, a prototype-guided conditional alignment module with dual pseudo-label interaction enhances pseudo-label reliability and enables category-level, fine-grained alignment, mitigating noise propagation and semantic drift. Experiments on SEED and SEED-IV show average accuracies of 94.86\% and 79.78\% for cross-subject, and 95.12\% and 83.15\% for cross-session protocols. On the large-scale FACED dataset, DAMSDAN achieves 82.88\% (cross-subject). Extensive ablations and interpretability analyses corroborate the effectiveness of the proposed framework for cross-domain EEG-based emotion recognition.

---

### Certified Self-Consistency: Statistical Guarantees and Test-Time Training for Reliable Reasoning in LLMs

Authors: Paula Cordero-Encinar, Andrew B. Duncan
Published: 2025-10-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.17472v2

Recent advances such as self-consistency and test-time reinforcement learning (TTRL) improve the reliability of large language models (LLMs) without additional supervision, yet their underlying mechanisms and statistical guarantees remain poorly understood. We present a unified framework for certifiable inference in LLMs, showing that majority voting provides a statistical certificate of self-consistency: under mild assumptions, the aggregated answer coincides with the mode of the model's terminal distribution with high probability. We derive finite-sample and anytime-valid concentration bounds that quantify this confidence, and introduce the Martingale Majority Certificate (MMC), a sequential stopping rule that adaptively determines when sufficient samples have been drawn. We further prove that label-free post-training methods such as TTRL implicitly sharpen the answer distribution by exponentially tilting it toward its mode, thereby reducing the number of samples required for certification. Building on this insight, we propose new post-training objectives that explicitly optimise this trade-off between sharpness and bias. Together, these results explain and connect two central test-time scaling strategies, self-consistency and TTRL, within a single statistical framework for label-free, certifiable reliability in reasoning LLMs.

---

### Layer Specialization Underlying Compositional Reasoning in Transformers

Authors: Jing Liu
Published: 2025-10-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.17469v1

Transformers exhibit compositional reasoning on sequences not observed during training, a capability often attributed to in-context learning (ICL) and skill composition. We investigate this phenomenon using the Random Hierarchy Model (RHM), a probabilistic context-free grammar that generates sequences through recursive rule application. Models are trained on subsets of sequences and evaluated across four generalization conditions: memorization, in-distribution generalization, out-of-distribution generalization with the same rules, and cross-layer transfer. Behaviorally, performance improves systematically with task complexity and the number of in-context examples, with out-of-distribution tasks requiring substantially more examples than in-distribution scenarios. Mechanistically, we identify a progressive emergence of layer specialization during training that correlates with generalization performance. Principal component analysis and attention pattern clustering reveal that transformers develop structured, hierarchically organized representations in specialized layers. These results demonstrate that transformers develop modular, interpretable mechanisms supporting compositional reasoning, linking internal algorithmic structure to observed behavioral capabilities.

---

### CrossStateECG: Multi-Scale Deep Convolutional Network with Attention for Rest-Exercise ECG Biometrics

Authors: Dan Zheng, Jing Feng, Juan Liu
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17467v1

Current research in Electrocardiogram (ECG) biometrics mainly emphasizes resting-state conditions, leaving the performance decline in rest-exercise scenarios largely unresolved. This paper introduces CrossStateECG, a robust ECG-based authentication model explicitly tailored for cross-state (rest-exercise) conditions. The proposed model creatively combines multi-scale deep convolutional feature extraction with attention mechanisms to ensure strong identification across different physiological states. Experimental results on the exercise-ECGID dataset validate the effectiveness of CrossStateECG, achieving an identification accuracy of 92.50% in the Rest-to-Exercise scenario (training on resting ECG and testing on post-exercise ECG) and 94.72% in the Exercise-to-Rest scenario (training on post-exercise ECG and testing on resting ECG). Furthermore, CrossStateECG demonstrates exceptional performance across both state combinations, reaching an accuracy of 99.94% in Rest-to-Rest scenarios and 97.85% in Mixed-to-Mixed scenarios. Additional validations on the ECG-ID and MIT-BIH datasets further confirmed the generalization abilities of CrossStateECG, underscoring its potential as a practical solution for post-exercise ECG-based authentication in dynamic real-world settings.

---

### Label Indeterminacy in AI & Law

Authors: Cor Steging, Tadeusz Zbiegień
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17463v1

Machine learning is increasingly used in the legal domain, where it typically operates retrospectively by treating past case outcomes as ground truth. However, legal outcomes are often shaped by human interventions that are not captured in most machine learning approaches. A final decision may result from a settlement, an appeal, or other procedural actions. This creates label indeterminacy: the outcome could have been different if the intervention had or had not taken place. We argue that legal machine learning applications need to account for label indeterminacy. Methods exist that can impute these indeterminate labels, but they are all grounded in unverifiable assumptions. In the context of classifying cases from the European Court of Human Rights, we show that the way that labels are constructed during training can significantly affect model behaviour. We therefore position label indeterminacy as a relevant concern in AI & Law and demonstrate how it can shape model behaviour.

---

### Evaluating Large Language Models on Urdu Idioms

Authors: Muhammad Farmal Khan, Mousumi Akter
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17460v2

Idioms remain a persistent challenge in natural language processing due to their figurative and culturally grounded meanings, which distinguish them from literal expressions. Although recent advances in large language models (LLMs) have improved idiom handling across several languages, limited attention has been given to low resource languages such as Urdu. In this work, we present a comprehensive benchmark for Urdu to English idiomatic translation, consisting of a manually verified dataset of 4,000 aligned idiom sentence pairs in both Perso Arabic (native Urdu script) and Romanized Urdu. We evaluate multiple tasks, including translation, paraphrasing, idiom span detection, and back-translation, using diverse prompting strategies such as cultural prompting, idiomatic prompting, and few-shot learning. Our findings show that frontier LLMs consistently outperform traditional neural machine translation systems across all evaluation settings, particularly in preserving figurative and metaphorical meaning. While models demonstrate relatively stable performance on native Urdu script, the absence of standardized orthography in Romanized Urdu introduces substantial challenges for consistency and idiom span detection. This work establishes a high quality benchmark for cross script idiomatic evaluation in Urdu and underscores the importance of prompt engineering in preserving figurative language meaning across languages.

---

### Estimating Orbital Parameters of Direct Imaging Exoplanet Using Neural Network

Authors: Bo Liang, Hanlin Song, Chang Liu, Tianyu Zhao, Yuxiang Xu, Zihao Xiao, Manjia Liang, Minghui Du, Wei-Liang Qian, Li-e Qiang, Peng Xu, Ziren Luo
Published: 2025-10-20
Categories: astro-ph.EP, astro-ph.GA, cs.LG
arXiv: https://arxiv.org/abs/2510.17459v3

In this work, we propose a flow-matching Markov chain Monte Carlo (FM-MCMC) algorithm for estimating the orbital parameters of exoplanetary systems, especially for those only one exoplanet is involved. Compared to traditional methods that rely on random sampling within the Bayesian framework, our approach first leverages flow matching posterior estimation (FMPE) to efficiently constrain the prior range of physical parameters, and then employs MCMC to accurately infer the posterior distribution. For example, in the orbital parameter inference of beta Pictoris b, our model achieved a substantial speed-up while maintaining comparable accuracy-running 77.8 times faster than Parallel Tempered MCMC (PTMCMC) and 365.4 times faster than nested sampling. Moreover, our FM-MCMC method also attained the highest average log-likelihood among all approaches, demonstrating its superior sampling efficiency and accuracy. This highlights the scalability and efficiency of our approach, making it well-suited for processing the massive datasets expected from future exoplanet surveys. Beyond astrophysics, our methodology establishes a versatile paradigm for synergizing deep generative models with traditional sampling, which can be adopted to tackle complex inference problems in other fields, such as cosmology, biomedical imaging, and particle physics.

---

### Explainable AI for microseismic event detection

Authors: Ayrat Abdullin, Denis Anikiev, Umair Bin Waheed
Published: 2025-10-20
Categories: cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2510.17458v2

Deep neural networks like PhaseNet show high accuracy in detecting microseismic events, but their black-box nature is a concern in critical applications. We apply Explainable Artificial Intelligence (XAI) techniques, such as Gradient-weighted Class Activation Mapping (Grad-CAM) and Shapley Additive Explanations (SHAP), to interpret the PhaseNet model's decisions and improve its reliability. Grad-CAM highlights that the network's attention aligns with P- and S-wave arrivals. SHAP values quantify feature contributions, confirming that vertical-component amplitudes drive P-phase picks while horizontal components dominate S-phase picks, consistent with geophysical principles. Leveraging these insights, we introduce a SHAP-gated inference scheme that combines the model's output with an explanation-based metric to reduce errors. On a test set of 9,000 waveforms, the SHAP-gated model achieved an F1-score of 0.98 (precision 0.99, recall 0.97), outperforming the baseline PhaseNet (F1-score 0.97) and demonstrating enhanced robustness to noise. These results show that XAI can not only interpret deep learning models but also directly enhance their performance, providing a template for building trust in automated seismic detectors. The implementation and scripts used in this study will be publicly available at https://github.com/ayratabd/xAI_PhaseNet.

---

### Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

Authors: Li Sun, Zhenhao Huang, Ming Zhang, Philip S. Yu
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17457v1

Message Passing Neural Networks (MPNNs) is the building block of graph foundation models, but fundamentally suffer from oversmoothing and oversquashing. There has recently been a surge of interest in fixing both issues. Existing efforts primarily adopt global approaches, which may be beneficial in some regions but detrimental in others, ultimately leading to the suboptimal expressiveness. In this paper, we begin by revisiting oversquashing through a global measure -- spectral gap $λ$ -- and prove that the increase of $λ$ leads to gradient vanishing with respect to the input features, thereby undermining the effectiveness of message passing. Motivated by such theoretical insights, we propose a \textbf{local} approach that adaptively adjusts message passing based on local structures. To achieve this, we connect local Riemannian geometry with MPNNs, and establish a novel nonhomogeneous boundary condition to address both oversquashing and oversmoothing. Building on the Robin condition, we design a GBN network with local bottleneck adjustment, coupled with theoretical guarantees. Extensive experiments on homophilic and heterophilic graphs show the expressiveness of GBN. Furthermore, GBN does not exhibit performance degradation even when the network depth exceeds $256$ layers.

---

### The Parameterized Complexity of Computing the VC-Dimension

Authors: Florent Foucaud, Harmender Gahlawat, Fionn Mc Inerney, Prafullkumar Tale
Published: 2025-10-20
Categories: cs.CC, cs.AI, cs.DM, cs.LG, math.CO
arXiv: https://arxiv.org/abs/2510.17451v2

The VC-dimension is a well-studied and fundamental complexity measure of a set system (or hypergraph) that is central to many areas of machine learning. We establish several new results on the complexity of computing the VC-dimension. In particular, given a hypergraph $\mathcal{H}=(\mathcal{V},\mathcal{E})$, we prove that the naive $2^{\mathcal{O}(|\mathcal{V}|)}$-time algorithm is asymptotically tight under the Exponential Time Hypothesis (ETH). We then prove that the problem admits a $1$-additive fixed-parameter approximation algorithm when parameterized by the maximum degree of $\mathcal{H}$ and a fixed-parameter algorithm when parameterized by its dimension, and that these are essentially the only such exploitable structural parameters. Lastly, we consider a generalization of the problem, formulated using graphs, which captures the VC-dimension of both set systems and graphs. We design a $2^{\mathcal{O}(\rm{tw}\cdot \log \rm{tw})}\cdot |V|$-time algorithm for any graph $G=(V,E)$ of treewidth $\rm{tw}$ (which, for a set system, applies to the treewidth of its incidence graph). This is in contrast with closely related problems that require a double-exponential dependency on the treewidth (assuming the ETH).

---

### Active Inference for an Intelligent Agent in Autonomous Reconnaissance Missions

Authors: Johan Schubert, Farzad Kamrani, Tove Gustavi
Published: 2025-10-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.17450v2

We develop an active inference route-planning method for the autonomous control of intelligent agents. The aim is to reconnoiter a geographical area to maintain a common operational picture. To achieve this, we construct an evidence map that reflects our current understanding of the situation, incorporating both positive and "negative" sensor observations of possible target objects collected over time, and diffusing the evidence across the map as time progresses. The generative model of active inference uses Dempster-Shafer theory and a Gaussian sensor model, which provides input to the agent. The generative process employs a Bayesian approach to update a posterior probability distribution. We calculate the variational free energy for all positions within the area by assessing the divergence between a pignistic probability distribution of the evidence map and a posterior probability distribution of a target object based on the observations, including the level of surprise associated with receiving new observations. Using the free energy, we direct the agents' movements in a simulation by taking an incremental step toward a position that minimizes the free energy. This approach addresses the challenge of exploration and exploitation, allowing agents to balance searching extensive areas of the geographical map while tracking identified target objects.

---

### Rethinking Nighttime Image Deraining via Learnable Color Space Transformation

Authors: Qiyuan Guan, Xiang Chen, Guiyue Jin, Jiyu Jin, Shumin Fan, Tianyu Song, Jinshan Pan
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17440v1

Compared to daytime image deraining, nighttime image deraining poses significant challenges due to inherent complexities of nighttime scenarios and the lack of high-quality datasets that accurately represent the coupling effect between rain and illumination. In this paper, we rethink the task of nighttime image deraining and contribute a new high-quality benchmark, HQ-NightRain, which offers higher harmony and realism compared to existing datasets. In addition, we develop an effective Color Space Transformation Network (CST-Net) for better removing complex rain from nighttime scenes. Specifically, we propose a learnable color space converter (CSC) to better facilitate rain removal in the Y channel, as nighttime rain is more pronounced in the Y channel compared to the RGB color space. To capture illumination information for guiding nighttime deraining, implicit illumination guidance is introduced enabling the learned features to improve the model's robustness in complex scenarios. Extensive experiments show the value of our dataset and the effectiveness of our method. The source code and datasets are available at https://github.com/guanqiyuan/CST-Net.

---

### From Spatial to Actions: Grounding Vision-Language-Action Model in Spatial Foundation Priors

Authors: Zhengshen Zhang, Hao Li, Yalun Dai, Zhengbang Zhu, Lei Zhou, Chenchen Liu, Dong Wang, Francis E. H. Tay, Sijin Chen, Ziwei Liu, Yuxiao Liu, Xinghang Li et al.
Published: 2025-10-20
Categories: cs.RO, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.17439v3

Existing vision-language-action (VLA) models act in 3D real-world but are typically built on 2D encoders, leaving a spatial reasoning gap that limits generalization and adaptability. Recent 3D integration techniques for VLAs either require specialized sensors and transfer poorly across modalities, or inject weak cues that lack geometry and degrade vision-language alignment. In this work, we introduce FALCON (From Spatial to Action), a novel paradigm that injects rich 3D spatial tokens into the action head. FALCON leverages spatial foundation models to deliver strong geometric priors from RGB alone, and includes an Embodied Spatial Model that can optionally fuse depth, or pose for higher fidelity when available, without retraining or architectural changes. To preserve language reasoning, spatial tokens are consumed by a Spatial-Enhanced Action Head rather than being concatenated into the vision-language backbone. These designs enable FALCON to address limitations in spatial representation, modality transferability, and alignment. In comprehensive evaluations across three simulation benchmarks and eleven real-world tasks, our proposed FALCON achieves state-of-the-art performance, consistently surpasses competitive baselines, and remains robust under clutter, spatial-prompt conditioning, and variations in object scale and height.

---

### Multilingual Clinical NER for Diseases and Medications Recognition in Cardiology Texts using BERT Embeddings

Authors: Manuela Daniela Danu, George Marica, Constantin Suciu, Lucian Mihai Itu, Oladimeji Farri
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17437v1

The rapidly increasing volume of electronic health record (EHR) data underscores a pressing need to unlock biomedical knowledge from unstructured clinical texts to support advancements in data-driven clinical systems, including patient diagnosis, disease progression monitoring, treatment effects assessment, prediction of future clinical events, etc. While contextualized language models have demonstrated impressive performance improvements for named entity recognition (NER) systems in English corpora, there remains a scarcity of research focused on clinical texts in low-resource languages. To bridge this gap, our study aims to develop multiple deep contextual embedding models to enhance clinical NER in the cardiology domain, as part of the BioASQ MultiCardioNER shared task. We explore the effectiveness of different monolingual and multilingual BERT-based models, trained on general domain text, for extracting disease and medication mentions from clinical case reports written in English, Spanish, and Italian. We achieved an F1-score of 77.88% on Spanish Diseases Recognition (SDR), 92.09% on Spanish Medications Recognition (SMR), 91.74% on English Medications Recognition (EMR), and 88.9% on Italian Medications Recognition (IMR). These results outperform the mean and median F1 scores in the test leaderboard across all subtasks, with the mean/median values being: 69.61%/75.66% for SDR, 81.22%/90.18% for SMR, 89.2%/88.96% for EMR, and 82.8%/87.76% for IMR.

---

### Leveraging AV1 motion vectors for Fast and Dense Feature Matching

Authors: Julien Zouein, Hossein Javidnia, François Pitié, Anil Kokaram
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17434v2

We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs comparably to sequential SIFT while using far less CPU, and yields denser matches with competitive pairwise geometry. As a small SfM demo on a 117-frame clip, MV matches register all images and reconstruct 0.46-0.62M points at 0.51-0.53,px reprojection error; BA time grows with match density. These results show compressed-domain correspondences are a practical, resource-efficient front end with clear paths to scaling in full pipelines.

---

### Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning

Authors: Yushi Yang, Shreyansh Padarha, Sarah Ball, Andrew Lee, Adam Mahdi
Published: 2025-10-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.17431v2

Agentic reinforcement learning (RL) trains large language models to use tools, but its impact on alignment is poorly understood. We study how agentic RL for search affects the alignment of instruction-tuned (IT) models. We find that RL-trained models inherit refusal reasoning by deflecting harmful requests into benign search queries, but this breaks down under a simple diagnostic trigger that elicits a search call before refusal can occur. Under this condition, RL models produce multi-step unsafe search actions and reasoning, reducing search query safety by up to 68.6% in Qwen and Llama models relative to their IT counterparts. The effect generalises across model families, scales, and RL algorithms. To understand why, we identify linear directions in the residual stream that control search query safety, and show that RL training progressively shifts search behaviour toward the harmful end of this direction. We thus propose representation-guided RL training, which adds a reward penalty based on projection toward the harmful search direction. Training on benign data alone, it restores IT-level alignment without reducing task accuracy and requires no additional training data. Together, our work provides the first framework for diagnosing, mechanistically analysing, and mitigating alignment degradation in agentic RL for search.

---

### Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merging

Authors: Tiancheng Hu, Benjamin Minixhofer, Nigel Collier
Published: 2025-10-20
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.17426v3

The "alignment tax" of post-training is typically framed as a drop in task accuracy. We show it also involves a severe loss of calibration, making models overconfident, less reliable, and model outputs less diverse. We show that this trade-off can be navigated effectively via a simple post-hoc intervention: interpolating between a model's weights before and after alignment. Crucially, this is not a strict trade-off. We find that the process consistently reveals Pareto-optimal interpolations - models that improve accuracy beyond both parents while substantially recovering the calibration lost during alignment. Our work demonstrates that simple model merging provides a computationally efficient method for mitigating the full scope of the alignment tax, yielding models that are more capable and more reliable.

---

### Quantifying Climate Policy Action and Its Links to Development Outcomes: A Cross-National Data-Driven Analysis

Authors: Aditi Dutta
Published: 2025-10-20
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2510.17425v2

Addressing climate change effectively requires more than cataloguing the number of policies in place; it calls for tools that can reveal their thematic priorities and their tangible impacts on development outcomes. Existing assessments often rely on qualitative descriptions or composite indices, which can mask crucial differences between key domains such as mitigation, adaptation, disaster risk management, and loss and damage. To bridge this gap, we develop a quantitative indicator of climate policy orientation by applying a multilingual transformer-based language model to official national policy documents, achieving a classification accuracy of 0.90 (F1-score). Linking these indicators with World Bank development data in panel regressions reveals that mitigation policies are associated with higher GDP and GNI; disaster risk management correlates with greater GNI and debt but reduced foreign direct investment; adaptation and loss and damage show limited measurable effects. This integrated NLP-econometric framework enables comparable, theme-specific analysis of climate governance, offering a scalable method to monitor progress, evaluate trade-offs, and align policy emphasis with development goals.

---

### DeepDetect: Learning All-in-One Dense Keypoints

Authors: Shaharyar Ahmed Khan Tareen, Filza Khan Tareen, Xiaojing Yuan
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17422v4

Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, ORB, BRISK, FAST, etc.) and learning-based methods (SuperPoint, R2D2, QuadNet, LIFT, etc.) have shown strong performance gains yet suffer from key limitations: sensitivity to photometric changes, low keypoint density and repeatability, limited adaptability to challenging scenes, and lack of semantic understanding, often failing to prioritize visually important regions. We present DeepDetect, an intelligent, all-in-one, dense detector that unifies the strengths of classical detectors using deep learning. Firstly, we create ground-truth masks by fusing outputs of 7 keypoint and 2 edge detectors, extracting diverse visual cues from corners and blobs to prominent edges and textures in the images. Afterwards, a lightweight and efficient model: ESPNet, is trained using fused masks as labels, enabling DeepDetect to focus semantically on images while producing highly dense keypoints, that are adaptable to diverse and visually degraded conditions. Evaluations on Oxford, HPatches, and Middlebury datasets demonstrate that DeepDetect surpasses other detectors achieving maximum values of 0.5143 (average keypoint density), 0.9582 (average repeatability), 338,118 (correct matches), and 842,045 (voxels in stereo 3D reconstruction).

---

### Diffusion Models as Dataset Distillation Priors

Authors: Duo Su, Huyu Wu, Huanran Chen, Yiming Shi, Yuzhu Wang, Xi Ye, Jun Zhu
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17421v2

Dataset distillation aims to synthesize compact yet informative datasets from large ones. A significant challenge in this field is achieving a trifecta of diversity, generalization, and representativeness in a single distilled dataset. Although recent generative dataset distillation methods adopt powerful diffusion models as their foundation models, the inherent representativeness prior in diffusion models is overlooked. Consequently, these approaches often necessitate the integration of external constraints to enhance data quality. To address this, we propose Diffusion As Priors (DAP), which formalizes representativeness by quantifying the similarity between synthetic and real data in feature space using a Mercer kernel. We then introduce this prior as guidance to steer the reverse diffusion process, enhancing the representativeness of distilled samples without any retraining. Extensive experiments on large-scale datasets, such as ImageNet-1K and its subsets, demonstrate that DAP outperforms state-of-the-art methods in generating high-fidelity datasets while achieving superior cross-architecture generalization. Our work not only establishes a theoretical connection between diffusion priors and the objectives of dataset distillation but also provides a practical, training-free framework for improving the quality of the distilled dataset.

---

### Diverse Planning with Simulators via Linear Temporal Logic

Authors: Mustafa F. Abdelwahed, Alice Toniolo, Joan Espasa, Ian P. Gent
Published: 2025-10-20
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2510.17418v1

Autonomous agents rely on automated planning algorithms to achieve their objectives. Simulation-based planning offers a significant advantage over declarative models in modelling complex environments. However, relying solely on a planner that produces a single plan may not be practical, as the generated plans may not always satisfy the agent's preferences. To address this limitation, we introduce $\texttt{FBI}_\texttt{LTL}$, a diverse planner explicitly designed for simulation-based planning problems. $\texttt{FBI}_\texttt{LTL}$ utilises Linear Temporal Logic (LTL) to define semantic diversity criteria, enabling agents to specify what constitutes meaningfully different plans. By integrating these LTL-based diversity models directly into the search process, $\texttt{FBI}_\texttt{LTL}$ ensures the generation of semantically diverse plans, addressing a critical limitation of existing diverse planning approaches that may produce syntactically different but semantically identical solutions. Extensive evaluations on various benchmarks consistently demonstrate that $\texttt{FBI}_\texttt{LTL}$ generates more diverse plans compared to a baseline approach. This work establishes the feasibility of semantically-guided diverse planning in simulation-based environments, paving the way for innovative approaches in realistic, non-symbolic domains where traditional model-based approaches fail.

---

### BenCao: An Instruction-Tuned Large Language Model for Traditional Chinese Medicine

Authors: Jiacheng Xie, Yang Yu, Yibo Chen, Hanyao Zhang, Lening Zhao, Jiaxuan He, Lei Jiang, Xiaoting Tang, Guanghui An, Dong Xu
Published: 2025-10-20
Categories: cs.CL, cs.AI, cs.MA, cs.MM, cs.SE
arXiv: https://arxiv.org/abs/2510.17415v1

Traditional Chinese Medicine (TCM), with a history spanning over two millennia, plays a role in global healthcare. However, applying large language models (LLMs) to TCM remains challenging due to its reliance on holistic reasoning, implicit logic, and multimodal diagnostic cues. Existing TCM-domain LLMs have made progress in text-based understanding but lack multimodal integration, interpretability, and clinical applicability. To address these limitations, we developed BenCao, a ChatGPT-based multimodal assistant for TCM, integrating structured knowledge bases, diagnostic data, and expert feedback refinement. BenCao was trained through natural language instruction tuning rather than parameter retraining, aligning with expert-level reasoning and ethical norms specific to TCM. The system incorporates a comprehensive knowledge base of over 1,000 classical and modern texts, a scenario-based instruction framework for diverse interactions, a chain-of-thought simulation mechanism for interpretable reasoning, and a feedback refinement process involving licensed TCM practitioners. BenCao connects to external APIs for tongue-image classification and multimodal database retrieval, enabling dynamic access to diagnostic resources. In evaluations across single-choice question benchmarks and multimodal classification tasks, BenCao achieved superior accuracy to general-domain and TCM-domain models, particularly in diagnostics, herb recognition, and constitution classification. The model was deployed as an interactive application on the OpenAI GPTs Store, accessed by nearly 1,000 users globally as of October 2025. This study demonstrates the feasibility of developing a TCM-domain LLM through natural language-based instruction tuning and multimodal integration, offering a practical framework for aligning generative AI with traditional medical reasoning and a scalable pathway for real-world deployment.

---

### Conditional Diffusion Modeling with Attention for Probabilistic Battery Capacity Prediction under Real-World Condition

Authors: Chunlin Jiang, Hequn Li, Zhongwei Deng, Jie Shao, Zhansheng Ning
Published: 2025-10-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.17414v2

Accurate prediction of lithium-ion battery capacity and its associated uncertainty is essential for reliable battery management but remains challenging due to the stochastic nature of aging. This paper presents a new method, termed the Conditional Diffusion U-Net with Attention (CDUA), which integrates feature engineering and deep learning to address this challenge. The proposed approach employs a diffusion-based generative model for time-series forecasting and incorporates attention mechanisms to enhance predictive performance. Battery capacity is first derived from real-world vehicle operation data. The most relevant features are then identified using the Pearson correlation coefficient and the XGBoost algorithm. These features are used to train the CDUA model, which comprises two components: (1) a contextual U-Net with self-attention to capture complex temporal dependencies, and (2) a noise predictor network that learns to estimate the added noise, enabling the reconstruction of accurate capacity values from noisy observations. Experimental validation on the real-world vehicle data demonstrates that the proposed CDUA model achieves a relative mean absolute error of 0.94% and a relative root mean square error of 1.14%, with a narrow 95% confidence interval of 3.74% in relative width. These results confirm that CDUA provides both accurate capacity estimation and reliable uncertainty quantification. Comparative experiments further verify its robustness and superior performance over existing mainstream approaches.

---

### Monitoring Horses in Stalls: From Object to Event Detection

Authors: Dmitrii Galimzianov, Viacheslav Vyshegorodtsev, Ivan Nezhivykh
Published: 2025-10-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.17409v1

Monitoring the behavior of stalled horses is essential for early detection of health and welfare issues but remains labor-intensive and time-consuming. In this study, we present a prototype vision-based monitoring system that automates the detection and tracking of horses and people inside stables using object detection and multi-object tracking techniques. The system leverages YOLOv11 and BoT-SORT for detection and tracking, while event states are inferred based on object trajectories and spatial relations within the stall. To support development, we constructed a custom dataset annotated with assistance from foundation models CLIP and GroundingDINO. The system distinguishes between five event types and accounts for the camera's blind spots. Qualitative evaluation demonstrated reliable performance for horse-related events, while highlighting limitations in detecting people due to data scarcity. This work provides a foundation for real-time behavioral monitoring in equine facilities, with implications for animal welfare and stable management.

---

### Multi-Window Temporal Analysis for Enhanced Arrhythmia Classification: Leveraging Long-Range Dependencies in Electrocardiogram Signals

Authors: Tiezhi Wang, Wilhelm Haverkamp, Nils Strodthoff
Published: 2025-10-20
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.17406v3

Objective. Arrhythmia classification from electrocardiograms (ECGs) suffers from high false positive rates and limited cross-dataset generalization, particularly for atrial fibrillation (AF) detection where specificity ranges from 0.72 to 0.98 using conventional 30-s analysis windows. While most deep learning approaches analyze isolated 30-s ECG windows, many arrhythmias, including AF and atrial flutter, exhibit diagnostic features that emerge over extended time scales. Approach. We introduce S4ECG, a deep learning architecture based on structured state-space models (S4), designed to capture long-range temporal dependencies by jointly analyzing multiple consecutive ECG windows spanning up to 20 min. We evaluate S4ECG on four publicly available databases for multi-class arrhythmia classification and perform systematic cross-dataset evaluations to assess out-of-distribution robustness. Results. Multi-window analysis consistently outperforms single-window approaches across all datasets, improving macro-averaged AUROC by 1.0-11.6 percentage points. For AF, specificity increases from 0.718-0.979 to 0.967-0.998 at a fixed sensitivity threshold, yielding a 3-10-fold reduction in false positive rates. Significance. Compared with convolutional neural network baselines, the S4 architecture shows superior performance, and multi-window training substantially reduces cross-dataset degradation. Optimal diagnostic windows are 10-20 min, beyond which performance plateaus or degrades. These findings demonstrate that structured incorporation of extended temporal context enhances both arrhythmia classification accuracy and cross-dataset robustness. The identified optimal temporal windows provide practical guidance for ECG monitoring system design and may reflect underlying physiological timescales of arrhythmogenic dynamics.

---

### AFRICAPTION: Establishing a New Paradigm for Image Captioning in African Languages

Authors: Mardiyyah Oduwole, Prince Mireku, Fatimo Adebanjo, Oluwatosin Olajide, Mahi Aminu Aliyu, Jekaterina Novikova
Published: 2025-10-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.17405v1

Multimodal AI research has overwhelmingly focused on high-resource languages, hindering the democratization of advancements in the field. To address this, we present AfriCaption, a comprehensive framework for multilingual image captioning in 20 African languages and our contributions are threefold: (i) a curated dataset built on Flickr8k, featuring semantically aligned captions generated via a context-aware selection and translation process; (ii) a dynamic, context-preserving pipeline that ensures ongoing quality through model ensembling and adaptive substitution; and (iii) the AfriCaption model, a 0.5B parameter vision-to-text architecture that integrates SigLIP and NLLB200 for caption generation across under-represented languages. This unified framework ensures ongoing data quality and establishes the first scalable image-captioning resource for under-represented African languages, laying the groundwork for truly inclusive multimodal AI.

---