# Research Papers — 2025-10 · bundle page 126 of 217

> Full-text markdown of papers #6251–6300 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/126
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/125.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/127.md)

### Attention Factors for Statistical Arbitrage

Authors: Elliot L. Epstein, Rose Wang, Jaewon Choi, Markus Pelger
Published: 2025-10-13
Categories: cs.LG, cs.AI, q-fin.CP
arXiv: https://arxiv.org/abs/2510.11616v1

Statistical arbitrage exploits temporal price differences between similar assets. We develop a framework to jointly identify similar assets through factors, identify mispricing and form a trading policy that maximizes risk-adjusted performance after trading costs. Our Attention Factors are conditional latent factors that are the most useful for arbitrage trading. They are learned from firm characteristic embeddings that allow for complex interactions. We identify time-series signals from the residual portfolios of our factors with a general sequence model. Estimating factors and the arbitrage trading strategy jointly is crucial to maximize profitability after trading costs. In a comprehensive empirical study we show that our Attention Factor model achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period. Our one-step solution yields an unprecedented Sharpe ratio of 2.3 net of transaction costs. We show that weak factors are important for arbitrage trading.

---

### LLM-Oriented Token-Adaptive Knowledge Distillation

Authors: Xurong Xie, Zhucun Xue, Jiafu Wu, Jian Li, Yabiao Wang, Xiaobin Hu, Yong Liu, Jiangning Zhang
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11615v1

Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student models. These methods typically treat all tokens indiscriminately and apply a single, fixed temperature, resulting in suboptimal knowledge transfer. To address these limitations, we propose LLM-Oriented Token-Adaptive Knowledge Distillation (AdaKD), a novel framework that adapts the distillation process to the real-time learning state of each token. AdaKD consists of two synergistic modules driven by a unified token difficulty metric. First, our Loss-Driven Adaptive Token Focusing (LATF) module dynamically adjusts the distillation focus by monitoring the student's learning stability, concentrating computational resources on the most valuable tokens at each training phase. Second, we introduce Inverse Difficulty Temperature Scaling (IDTS), a counterintuitive yet effective token-level temperature strategy. It employs low temperatures for difficult tokens for targeted error correction, and high temperatures for easy tokens to encourage students to learn from the teacher's complete and smooth output distribution, thereby enhancing generalization. As a plug-and-play framework, AdaKD can consistently improve the performance of various distillation methods on multiple model architectures and benchmarks.

---

### High-resolution Photo Enhancement in Real-time: A Laplacian Pyramid Network

Authors: Feng Zhang, Haoyou Deng, Zhiqiang Li, Lida Li, Bin Xu, Qingbo Lu, Zisheng Cao, Minchen Wei, Changxin Gao, Nong Sang, Xiang Bai
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11613v1

Photo enhancement plays a crucial role in augmenting the visual aesthetics of a photograph. In recent years, photo enhancement methods have either focused on enhancement performance, producing powerful models that cannot be deployed on edge devices, or prioritized computational efficiency, resulting in inadequate performance for real-world applications. To this end, this paper introduces a pyramid network called LLF-LUT++, which integrates global and local operators through closed-form Laplacian pyramid decomposition and reconstruction. This approach enables fast processing of high-resolution images while also achieving excellent performance. Specifically, we utilize an image-adaptive 3D LUT that capitalizes on the global tonal characteristics of downsampled images, while incorporating two distinct weight fusion strategies to achieve coarse global image enhancement. To implement this strategy, we designed a spatial-frequency transformer weight predictor that effectively extracts the desired distinct weights by leveraging frequency features. Additionally, we apply local Laplacian filters to adaptively refine edge details in high-frequency components. After meticulously redesigning the network structure and transformer model, LLF-LUT++ not only achieves a 2.64 dB improvement in PSNR on the HDR+ dataset, but also further reduces runtime, with 4K resolution images processed in just 13 ms on a single GPU. Extensive experimental results on two benchmark datasets further show that the proposed approach performs favorably compared to state-of-the-art methods. The source code will be made publicly available at https://github.com/fengzhang427/LLF-LUT.

---

### ParaCook: On Time-Efficient Planning for Multi-Agent Systems

Authors: Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11608v2

Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking tasks, with a simplified action space to isolate the core challenge of strategic parallel planning. Through a comprehensive evaluation of state-of-the-art LLMs, we find that current approaches achieve suboptimal plans, which struggle with parallel actions or coordination. Our analysis also reveals LLMs' potential on abstract tasks where they can focus on high-level parallel optimization. ParaCook provides a scalable evaluation framework with adjustable complexity, establishing a foundation for developing and assessing time efficiency-aware multi-agent planning. The code and data are available at https://github.com/zsq259/ParaCook.

---

### ExpVid: A Benchmark for Experiment Video Understanding & Reasoning

Authors: Yicheng Xu, Yue Wu, Jiashuo Yu, Ziang Yan, Tianxiang Jiang, Yinan He, Qingsong Zhao, Kai Chen, Yu Qiao, Limin Wang, Manabu Okumura, Yi Wang
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11606v1

Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video publications, ExpVid features a new three-level task hierarchy that mirrors the scientific process: (1) Fine-grained Perception of tools, materials, and actions; (2) Procedural Understanding of step order and completeness; and (3) Scientific Reasoning that connects the full experiment to its published conclusions. Our vision-centric annotation pipeline, combining automated generation with multi-disciplinary expert validation, ensures that tasks require visual grounding. We evaluate 19 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes. Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning. ExpVid not only provides a diagnostic tool but also charts a roadmap for developing MLLMs capable of becoming trustworthy partners in scientific experimentation.

---

### ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training

Authors: Leonard Bruns, Axel Barroso-Laguna, Tommaso Cavallari, Áron Monszpart, Sowmya Munukutla, Victor Adrian Prisacariu, Eric Brachmann
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11605v1

Scene coordinate regression (SCR) has established itself as a promising learning-based approach to visual relocalization. After mere minutes of scene-specific training, SCR models estimate camera poses of query images with high accuracy. Still, SCR methods fall short of the generalization capabilities of more classical feature-matching approaches. When imaging conditions of query images, such as lighting or viewpoint, are too different from the training views, SCR models fail. Failing to generalize is an inherent limitation of previous SCR frameworks, since their training objective is to encode the training views in the weights of the coordinate regressor itself. The regressor essentially overfits to the training views, by design. We propose to separate the coordinate regressor and the map representation into a generic transformer and a scene-specific map code. This separation allows us to pre-train the transformer on tens of thousands of scenes. More importantly, it allows us to train the transformer to generalize from mapping images to unseen query images during pre-training. We demonstrate on multiple challenging relocalization datasets that our method, ACE-G, leads to significantly increased robustness while keeping the computational footprint attractive.

---

### Explainability, risk modeling, and segmentation based customer churn analytics for personalized retention in e-commerce

Authors: Indrajith Ekanayake, Sanjula De Alwis
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11604v2

In online retail, customer acquisition typically incurs higher costs than customer retention, motivating firms to invest in churn analytics. However, many contemporary churn models operate as opaque black boxes, limiting insight into the determinants of attrition, the timing of retention opportunities, and the identification of high-risk customer segments. Accordingly, the emphasis should shift from prediction alone to the design of personalized retention strategies grounded in interpretable evidence. This study advances a three-component framework that integrates explainable AI to quantify feature contributions, survival analysis to model time-to-event churn risk, and RFM profiling to segment customers by transactional behaviour. In combination, these methods enable the attribution of churn drivers, estimation of intervention windows, and prioritization of segments for targeted actions, thereby supporting strategies that reduce attrition and strengthen customer loyalty.

---

### Deconstructing Attention: Investigating Design Principles for Effective Language Modeling

Authors: Huiyin Xue, Nafise Sadat Moosavi, Nikolaos Aletras
Published: 2025-10-13
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.11602v1

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions), sequence-dependent activations (where attention weights adapt to each input), a specific mathematical form (dot-product similarities plus softmax weighting), and coupling of queries and keys to evolving hidden states (grounding attention in the current layer). However, the necessity of each of these principles remains largely untested. In this work, we systematically deconstruct attention by designing controlled variants that selectively relax these principles, applied both uniformly across all layers and in hybrid architectures where only some layers retain standard attention. Our empirical analysis reveals that mechanisms for mixing tokens are indispensable, as their absence collapses models to near-random behavior, while the exact mathematical form and sequence dependency can be substantially relaxed, especially when preserved in just a subset of layers. Surprisingly, even variants that fail in isolation can achieve robust performance when interleaved with standard attention, highlighting a cooperative effect. These findings deepen our understanding of what truly underpins attention's effectiveness and open new avenues for simplifying language models without sacrificing performance.

---

### SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping

Authors: Marc Brinner, Sina Zarrieß
Published: 2025-10-13
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2510.11599v2

We propose SemCSE-Multi, a novel unsupervised framework for generating multifaceted embeddings of scientific abstracts, evaluated in the domains of invasion biology and medicine. These embeddings capture distinct, individually specifiable aspects in isolation, thus enabling fine-grained and controllable similarity assessments as well as adaptive, user-driven visualizations of scientific domains. Our approach relies on an unsupervised procedure that produces aspect-specific summarizing sentences and trains embedding models to map semantically related summaries to nearby positions in the embedding space. We then distill these aspect-specific embedding capabilities into a unified embedding model that directly predicts multiple aspect embeddings from a scientific abstract in a single, efficient forward pass. In addition, we introduce an embedding decoding pipeline that decodes embeddings back into natural language descriptions of their associated aspects. Notably, we show that this decoding remains effective even for unoccupied regions in low-dimensional visualizations, thus offering vastly improved interpretability in user-centric settings.

---

### MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models

Authors: Bo Cheng, Xu Wang, Jinda Liu, Yi Chang, Yuan Wu
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11598v1

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles to efficiently leverage inter-task knowledge in complex multi-task learning scenarios, often requiring substantial task-specific data to achieve optimal performance. To address this limitation, we introduce MeTA-LoRA, a two-stage optimization framework that significantly improves data efficiency in multi-task adaptation. In the first stage, task-specific LoRA adapters are learned using only a few samples from each involved dataset, enabling rapid adaptation without large-scale supervision. In the second stage, the shared LoRA adapter is updated by aggregating gradients from multiple tasks to promote knowledge transfer across tasks, further reducing data usage by leveraging common patterns. In both multi-task learning and multilingual learning scenarios, our method matches or surpasses the performance of traditional full-data LoRA fine-tuning approaches, while using significantly less task-specific data.

---

### Reproducibility: The New Frontier in AI Governance

Authors: Israel Mason-Williams, Gabryel Mason-Williams
Published: 2025-10-13
Categories: cs.AI, cs.GL
arXiv: https://arxiv.org/abs/2510.11595v1

AI policymakers are responsible for delivering effective governance mechanisms that can provide safe, aligned and trustworthy AI development. However, the information environment offered to policymakers is characterised by an unnecessarily low Signal-To-Noise Ratio, favouring regulatory capture and creating deep uncertainty and divides on which risks should be prioritised from a governance perspective. We posit that the current publication speeds in AI combined with the lack of strong scientific standards, via weak reproducibility protocols, effectively erodes the power of policymakers to enact meaningful policy and governance protocols. Our paper outlines how AI research could adopt stricter reproducibility guidelines to assist governance endeavours and improve consensus on the AI risk landscape. We evaluate the forthcoming reproducibility crisis within AI research through the lens of crises in other scientific domains; providing a commentary on how adopting preregistration, increased statistical power and negative result publication reproducibility protocols can enable effective AI governance. While we maintain that AI governance must be reactive due to AI's significant societal implications we argue that policymakers and governments must consider reproducibility protocols as a core tool in the governance arsenal and demand higher standards for AI research. Code to replicate data and figures: https://github.com/IFMW01/reproducibility-the-new-frontier-in-ai-governance

---

### Qubit-centric Transformer for Surface Code Decoding

Authors: Seong-Joon Park, Hee-Youl Kwak, Yongjune Kim
Published: 2025-10-13
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.11593v3

For reliable large-scale quantum computation, quantum error correction (QEC) is essential to protect logical information distributed across multiple physical qubits. Taking advantage of recent advances in deep learning, neural network-based decoders have emerged as a promising approach to improve the reliability of QEC. We propose the qubit-centric transformer (QCT), a novel and universal QEC decoder based on a transformer architecture with a qubit-centric attention mechanism. Our decoder transforms input syndromes from the stabilizer domain into qubit-centric tokens via a specialized embedding strategy. These qubit-centric tokens are processed through attention layers to effectively identify the underlying logical error. Furthermore, we introduce a graph-based masking method that incorporates the topological structure of quantum codes, enforcing attention toward relevant qubit interactions. Across various code distances for surface codes, QCT achieves state-of-the-art decoding performance, significantly outperforming existing neural decoders and the belief propagation (BP) with ordered statistics decoding (OSD) baseline. Notably, QCT achieves a high threshold of 18.1% under depolarizing noise, which closely approaches the theoretical bound of 18.9% and surpasses both the BP+OSD and the minimum-weight perfect matching (MWPM) thresholds. This qubit-centric approach provides a scalable and robust framework for surface code decoding, advancing the path toward fault-tolerant quantum computing.

---

### REGENT: Relevance-Guided Attention for Entity-Aware Multi-Vector Neural Re-Ranking

Authors: Shubham Chatterjee
Published: 2025-10-13
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.11592v1

Current neural re-rankers often struggle with complex information needs and long, content-rich documents. The fundamental issue is not computational--it is intelligent content selection: identifying what matters in lengthy, multi-faceted texts. While humans naturally anchor their understanding around key entities and concepts, neural models process text within rigid token windows, treating all interactions as equally important and missing critical semantic signals. We introduce REGENT, a neural re-ranking model that mimics human-like understanding by using entities as a "semantic skeleton" to guide attention. REGENT integrates relevance guidance directly into the attention mechanism, combining fine-grained lexical matching with high-level semantic reasoning. This relevance-guided attention enables the model to focus on conceptually important content while maintaining sensitivity to precise term matches. REGENT achieves new state-of-the-art performance in three challenging datasets, providing up to 108% improvement over BM25 and consistently outperforming strong baselines including ColBERT and RankVicuna. To our knowledge, this is the first work to successfully integrate entity semantics directly into neural attention, establishing a new paradigm for entity-aware information retrieval.

---

### Diffusion-DFL: Decision-focused Diffusion Models for Stochastic Optimization

Authors: Zihao Zhao, Christopher Yeh, Lingkai Kong, Kai Wang
Published: 2025-10-13
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2510.11590v1

Decision-focused learning (DFL) integrates predictive modeling and optimization by training predictors to optimize the downstream decision target rather than merely minimizing prediction error. To date, existing DFL methods typically rely on deterministic point predictions, which are often insufficient to capture the intrinsic stochasticity of real-world environments. To address this challenge, we propose the first diffusion-based DFL approach, which trains a diffusion model to represent the distribution of uncertain parameters and optimizes the decision by solving a stochastic optimization with samples drawn from the diffusion model. Our contributions are twofold. First, we formulate diffusion DFL using the reparameterization trick, enabling end-to-end training through diffusion. While effective, it is memory and compute-intensive due to the need to differentiate through the diffusion sampling process. Second, we propose a lightweight score function estimator that uses only several forward diffusion passes and avoids backpropagation through the sampling. This follows from our results that backpropagating through stochastic optimization can be approximated by a weighted score function formulation. We empirically show that our diffusion DFL approach consistently outperforms strong baselines in decision quality. The source code for all experiments is available at the project repository: https://github.com/GT-KOALA/Diffusion_DFL.

---

### QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking

Authors: Shubham Chatterjee, Jeff Dalton
Published: 2025-10-13
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2510.11589v1

Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches by integrating knowledge graph semantics into a multi-vector model. QDER's key innovation lies in its modeling of query-document relationships: rather than computing similarity scores on aggregated embeddings, we maintain individual token and entity representations throughout the ranking process, performing aggregation only at the final scoring stage - an approach we call "late aggregation." We first transform these fine-grained representations through learned attention patterns, then apply carefully chosen mathematical operations for precise matches. Experiments across five standard benchmarks show that QDER achieves significant performance gains, with improvements of 36% in nDCG@20 over the strongest baseline on TREC Robust 2004 and similar improvements on other datasets. QDER particularly excels on difficult queries, achieving an nDCG@20 of 0.70 where traditional approaches fail completely (nDCG@20 = 0.0), setting a foundation for future work in entity-aware retrieval.

---

### Analyzing and Internalizing Complex Policy Documents for LLM Agents

Authors: Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xing Fan, Xiang Li, Chenlei Guo, Ruhi Sarikaya, Heng Ji
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11588v1

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internalization harder. We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels, enabling systematic evaluation of agents' ability to handle complexity and offering a unified framework for assessing policy internalization. Our analysis shows that complex policy specifications governing workflows pose major reasoning challenges. Supporting internalization with gold user agent interaction trajectories containing chain-of-thought (CoT) annotations via supervised fine-tuning (SFT) is data-intensive and degrades sharply as policy complexity increases. To mitigate data and reasoning burdens, we propose Category-Aware Policy Continued Pretraining (CAP-CPT). Our automated pipeline parses policy documents to extract key specifications, grouping them into factual, behavioral, and conditional categories, and isolating complex conditions that drive workflow complexity. This guides targeted data synthesis and enables agents to internalize policy information through an autoregressive pretraining loss. Experiments show CAP-CPT improves SFT baselines in all settings, with up to 41% and 22% gains on Qwen-3-32B, achieving 97.3% prompt length reduction on CC-Gen and further enhancing tau-Bench with minimal SFT data.

---

### Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models

Authors: Georg Ahnert, Anna-Carolina Haensch, Barbara Plank, Markus Strohmaier
Published: 2025-10-13
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2510.11586v2

Many in-silico simulations of human survey responses with large language models (LLMs) focus on generating closed-ended survey responses, whereas LLMs are typically trained to generate open-ended text instead. Previous research has used a diverse range of methods for generating closed-ended survey responses with LLMs, and a standard practice remains to be identified. In this paper, we systematically investigate the impact that various Survey Response Generation Methods have on predicted survey responses. We present the results of 32 mio. simulated survey responses across 8 Survey Response Generation Methods, 4 political attitude surveys, and 10 open-weight language models. We find significant differences between the Survey Response Generation Methods in both individual-level and subpopulation-level alignment. Our results show that Restricted Generation Methods perform best overall, and that reasoning output does not consistently improve alignment. Our work underlines the significant impact that Survey Response Generation Methods have on simulated survey responses, and we develop practical recommendations on the application of Survey Response Generation Methods.

---

### LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings

Authors: Ting Li, Yang Yang, Yipeng Yu, Liang Yao, Guoqing Chao, Ruifeng Xu
Published: 2025-10-13
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2510.11584v1

Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reasoning. In this paper, we propose LLMAtKGE, a novel LLM-based framework that selects attack targets and generates human-readable explanations. To provide the LLM with sufficient factual context under limited input constraints, we design a structured prompting scheme that explicitly formulates the attack as multiple-choice questions while incorporating KG factual evidence. To address the context-window limitation and hesitation issues, we introduce semantics-based and centrality-based filters, which compress the candidate set while preserving high recall of attack-relevant information. Furthermore, to efficiently integrate both semantic and structural information into the filter, we precompute high-order adjacency and fine-tune the LLM with a triple classification task to enhance filtering performance. Experiments on two widely used knowledge graph datasets demonstrate that our attack outperforms the strongest black-box baselines and provides explanations via reasoning, and showing competitive performance compared with white-box methods. Comprehensive ablation and case studies further validate its capability to generate explanations.

---

### MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis

Authors: Hongyu Zhu, Lin Chen, Xin Jin, Mingsheng Shang
Published: 2025-10-13
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.11579v3

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotation costs, severely limiting real-world deployment in social media analytics and human-computer systems. Existing Mixup-based augmentation techniques, when naively applied to MSA, often produce semantically inconsistent samples and amplified label noise by ignoring emotional semantics across modalities. To address these challenges, we propose MS-Mix, an adaptive emotion-sensitive augmentation framework that automatically optimizes data quality in multimodal settings. Its key components are: (1) Sentiment-aware sample selection strategy that filters incompatible pairs via latent-space semantic similarity to prevent contradictory emotion mixing. (2) Sentiment intensity guided module with multi-head self-attention for computing modality-specific mixing ratios conditioned on emotional salience dynamically. (3) Sentiment alignment loss based on Kullback-Leibler divergence to align predicted sentiment distributions across modalities with ground-truth labels, improving discrimination and consistency. Extensive experiments on two public datasets with six state-of-the-art backbones confirm that MS-Mix consistently outperforms prior methods, significantly improving robustness and practical applicability for MSA. The source code is available at an anonymous link: https://anonymous.4open.science/r/MS-Mix-review-0C72.

---

### Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping

Authors: Walid Elbarz, Mohamed Bourriz, Hicham Hajji, Hamd Ait Abdelali, François Bourzeix
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11576v2

Foundation models are transforming Earth observation, but their potential for hyperspectral crop mapping remains underexplored. This study benchmarks three foundation models for cereal crop mapping using hyperspectral imagery: HyperSigma, DOFA, and Vision Transformers pre-trained on the SpectralEarth dataset (a large multitemporal hyperspectral archive). Models were fine-tuned on manually labeled data from a training region and evaluated on an independent test region. Performance was measured with overall accuracy (OA), average accuracy (AA), and F1-score. HyperSigma achieved an OA of 34.5% (+/- 1.8%), DOFA reached 62.6% (+/- 3.5%), and the SpectralEarth model achieved an OA of 93.5% (+/- 0.8%). A compact SpectralEarth variant trained from scratch achieved 91%, highlighting the importance of model architecture for strong generalization across geographic regions and sensor platforms. These results provide a systematic evaluation of foundation models for operational hyperspectral crop mapping and outline directions for future model development.

---

### Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails

Authors: Shuo Chen, Zhen Han, Haokun Chen, Bailan He, Shengyun Si, Jingpei Wu, Philip Torr, Volker Tresp, Jindong Gu
Published: 2025-10-13
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2510.11570v3

Open-weight Large Reasoning Models (LRMs) are approaching the capabilities of their frontier counterparts but pose significant safety concerns, as they are difficult to patch or monitor post-release. To prevent misuse, reasoning-based safety guardrails, where models explicitly reason on safety justifications before answering, have become a promising primary defense, achieving near-perfect refusal rates on harmful queries. We show that this strong defense is alarmingly brittle and can be subverted by embarrassingly simple attacks to elicit extremely forbidden questions, such as `How to kill a man without being caught?' Specifically, we identify one systematic vulnerability from the reasoning-then-answer mechanism: the stage-transition logic that governs when safety reasoning begins and ends can be trivially manipulated. Based on this finding, we develop four simple yet effective red-teaming methods that systematically subvert different stages of the guardrails, either by bypassing reasoning entirely or exploiting it to produce targeted harmful content. These methods achieve attack success rates up to 90\% across five benchmarks on multiple LRM families. Our findings reveal that reasoning-based guardrails are necessary but not sufficient and must be paired with robust triggering mechanisms and stronger base-model alignment. Code is in https://chenxshuo.github.io/bag-of-tricks/.

---

### A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation

Authors: Damjan Kalšan, Denis Zavadski, Tim Küchler, Haebom Lee, Stefan Roth, Carsten Rother
Published: 2025-10-13
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2510.11567v2

Synthetic datasets are widely used for training urban scene recognition models, but even highly realistic renderings show a noticeable gap to real imagery. This gap is particularly pronounced when adapting to a specific target domain, such as Cityscapes, where differences in architecture, vegetation, object appearance, and camera characteristics limit downstream performance. Closing this gap with more detailed 3D modelling would require expensive asset and scene design, defeating the purpose of low-cost labelled data. To address this, we present a new framework that adapts an off-the-shelf diffusion model to a target domain using only imperfect pseudo-labels. Once trained, it generates high-fidelity, target-aligned images from semantic maps of any synthetic dataset, including low-effort sources created in hours rather than months. The method filters suboptimal generations, rectifies image-label misalignments, and standardises semantics across datasets, transforming weak synthetic data into competitive real-domain training sets. Experiments on five synthetic datasets and two real target datasets show segmentation gains of up to +8.0%pt. mIoU over state-of-the-art translation methods, making rapidly constructed synthetic datasets as effective as high-effort, time-intensive synthetic datasets requiring extensive manual design. This work highlights a valuable collaborative paradigm where fast semantic prototyping, combined with generative models, enables scalable, high-quality training data creation for urban scene understanding.

---

### SCOOP'D: Learning Mixed-Liquid-Solid Scooping via Sim2Real Generative Policy

Authors: Kuanning Wang, Yongchong Gu, Yuqian Fu, Zeyu Shangguan, Sicheng He, Xiangyang Xue, Yanwei Fu, Daniel Seita
Published: 2025-10-13
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2510.11566v1

Scooping items with tools such as spoons and ladles is common in daily life, ranging from assistive feeding to retrieving items from environmental disaster sites. However, developing a general and autonomous robotic scooping policy is challenging since it requires reasoning about complex tool-object interactions. Furthermore, scooping often involves manipulating deformable objects, such as granular media or liquids, which is challenging due to their infinite-dimensional configuration spaces and complex dynamics. We propose a method, SCOOP'D, which uses simulation from OmniGibson (built on NVIDIA Omniverse) to collect scooping demonstrations using algorithmic procedures that rely on privileged state information. Then, we use generative policies via diffusion to imitate demonstrations from observational input. We directly apply the learned policy in diverse real-world scenarios, testing its performance on various item quantities, item characteristics, and container types. In zero-shot deployment, our method demonstrates promising results across 465 trials in diverse scenarios, including objects of different difficulty levels that we categorize as "Level 1" and "Level 2." SCOOP'D outperforms all baselines and ablations, suggesting that this is a promising approach to acquiring robotic scooping skills. Project page is at https://scoopdiff.github.io/.

---

### SNAP: Towards Segmenting Anything in Any Point Cloud

Authors: Aniket Gupta, Hanhui Wang, Charles Saunders, Aruni RoyChowdhury, Hanumant Singh, Huaizu Jiang
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11565v2

Interactive 3D point cloud segmentation enables efficient annotation of complex 3D scenes through user-guided prompts. However, current approaches are typically restricted in scope to a single domain (indoor or outdoor), and to a single form of user interaction (either spatial clicks or textual prompts). Moreover, training on multiple datasets often leads to negative transfer, resulting in domain-specific tools that lack generalizability. To address these limitations, we present SNAP (Segment aNything in Any Point cloud), a unified model for interactive 3D segmentation that supports both point-based and text-based prompts across diverse domains. Our approach achieves cross-domain generalizability by training on 7 datasets spanning indoor, outdoor, and aerial environments, while employing domain-adaptive normalization to prevent negative transfer. For text-prompted segmentation, we automatically generate mask proposals without human intervention and match them against CLIP embeddings of textual queries, enabling both panoptic and open-vocabulary segmentation. Extensive experiments demonstrate that SNAP consistently delivers high-quality segmentation results. We achieve state-of-the-art performance on 8 out of 9 zero-shot benchmarks for spatial-prompted segmentation and demonstrate competitive results on all 5 text-prompted benchmarks. These results show that a unified model can match or exceed specialized domain-specific approaches, providing a practical tool for scalable 3D annotation. Project page is at, https://neu-vi.github.io/SNAP/

---

### Culturally-Aware Conversations: A Framework & Benchmark for LLMs

Authors: Shreya Havaldar, Sunny Rai, Young-Min Cho, Lyle Ungar
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11563v1

Existing benchmarks that measure cultural adaptation in LLMs are misaligned with the actual challenges these models face when interacting with users from diverse cultural backgrounds. In this work, we introduce the first framework and benchmark designed to evaluate LLMs in realistic, multicultural conversational settings. Grounded in sociocultural theory, our framework formalizes how linguistic style - a key element of cultural communication - is shaped by situational, relational, and cultural context. We construct a benchmark dataset based on this framework, annotated by culturally diverse raters, and propose a new set of desiderata for cross-cultural evaluation in NLP: conversational framing, stylistic sensitivity, and subjective correctness. We evaluate today's top LLMs on our benchmark and show that these models struggle with cultural adaptation in a conversational setting.

---

### Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python

Authors: Caglar Demir, Alkid Baci, N'Dah Jean Kouagou, Leonie Nora Sieger, Stefan Heindorf, Simon Bin, Lukas Blübaum, Alexander Bigerl, Axel-Cyrille Ngonga Ngomo
Published: 2025-10-13
Categories: cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2510.11561v1

In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class expression learners including EvoLearner and DRILL. A learned OWL class expression can be used to classify instances in the knowledge graph. Furthermore, Ontolearn integrates a verbalization module based on an LLM to translate complex OWL class expressions into natural language sentences. By mapping OWL class expressions into respective SPARQL queries, Ontolearn can be easily used to operate over a remote triplestore. The source code of Ontolearn is available at https://github.com/dice-group/Ontolearn.

---

### Characterizing Web Search in The Age of Generative AI

Authors: Elisabeth Kirsten, Jost Grosse Perdekamp, Qinyuan Wu, Mihir Upadhyay, Krishna P. Gummadi, Muhammad Bilal Zafar
Published: 2025-10-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.11560v2

The advent of LLMs has given rise to generative search, a new search paradigm in which LLMs retrieve information from the web related to a query and synthesize it into a single, coherent response. This paradigm differs fundamentally from traditional web search, where results are returned as a ranked list of independent web pages. In this paper, we ask: Along what dimensions does generative search differ from traditional search? We conduct a systematic comparison between Google organic search and five generative search systems from three providers: Google, OpenAI, and Perplexity. Our analysis reveals substantial variation among engines in their reliance on internal v.s. external knowledge, source diversity, and stability. While generative systems often achieve topical coverage comparable to traditional search, they do so using markedly different retrieval footprints and synthesis strategies. We further show that the outputs of generative search can vary across time and executions, raising new challenges for robustness. Our findings demonstrate that generative search introduces new dimensions that are not captured by existing evaluation paradigms, motivating the development of evaluations that explicitly account for retrieval behavior, synthesis, and stability in generative search systems.

---

### Zero Data Retention in LLM-based Enterprise AI Assistants: A Comparative Study of Market Leading Agentic AI Products

Authors: Komal Gupta, Aditya Shrivastava
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11558v1

Governance of data, compliance, and business privacy matters, particularly for healthcare and finance businesses. Since the recent emergence of AI enterprise AI assistants enhancing business productivity, safeguarding private data and compliance is now a priority. With the implementation of AI assistants across the enterprise, the zero data retention can be achieved by implementing zero data retention policies by Large Language Model businesses like Open AI and Anthropic and Meta. In this work, we explore zero data retention policies for the Enterprise apps of large language models (LLMs). Our key contribution is defining the architectural, compliance, and usability trade-offs of such systems in parallel. In this research work, we examine the development of commercial AI assistants with two industry leaders and market titans in this arena - Salesforce and Microsoft. Both of these companies used distinct technical architecture to support zero data retention policies. Salesforce AgentForce and Microsoft Copilot are among the leading AI assistants providing much-needed push to business productivity in customer care. The purpose of this paper is to analyze the technical architecture and deployment of zero data retention policy by consuming applications as well as big language models service providers like Open Ai, Anthropic, and Meta.

---

### Invisible Languages of the LLM Universe

Authors: Saurabh Khanna, Xinxu Li
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11557v2

Large Language Models are trained on massive multilingual corpora, yet this abundance masks a profound crisis: of the world's 7,613 living languages, approximately 2,000 languages with millions of speakers remain effectively invisible in digital ecosystems. We propose a critical framework connecting empirical measurements of language vitality (real world demographic strength) and digitality (online presence) with postcolonial theory and epistemic injustice to explain why linguistic inequality in AI systems is not incidental but structural. Analyzing data across all documented human languages, we identify four categories: Strongholds (33%, high vitality and digitality), Digital Echoes (6%, high digitality despite declining vitality), Fading Voices (36%, low on both dimensions), and critically, Invisible Giants (27%, high vitality but near-zero digitality) - languages spoken by millions yet absent from the LLM universe. We demonstrate that these patterns reflect continuities from colonial-era linguistic hierarchies to contemporary AI development, constituting digital epistemic injustice. Our analysis reveals that English dominance in AI is not a technical necessity but an artifact of power structures that systematically exclude marginalized linguistic knowledge. We conclude with implications for decolonizing language technology and democratizing access to AI benefits.

---

### How many samples to label for an application given a foundation model? Chest X-ray classification study

Authors: Nikolay Nechaev, Evgeniia Przhezdzetskaia, Viktor Gombolevskiy, Dmitry Umerenkov, Dmitry Dylov
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11553v2

Chest X-ray classification is vital yet resource-intensive, typically demanding extensive annotated data for accurate diagnosis. Foundation models mitigate this reliance, but how many labeled samples are required remains unclear. We systematically evaluate the use of power-law fits to predict the training size necessary for specific ROC-AUC thresholds. Testing multiple pathologies and foundation models, we find XrayCLIP and XraySigLIP achieve strong performance with significantly fewer labeled examples than a ResNet-50 baseline. Importantly, learning curve slopes from just 50 labeled cases accurately forecast final performance plateaus. Our results enable practitioners to minimize annotation costs by labeling only the essential samples for targeted performance.

---

### ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?

Authors: Liu Yang, Huiyu Duan, Ran Tao, Juntao Cheng, Sijing Wu, Yunhao Li, Jing Liu, Xiongkuo Min, Guangtao Zhai
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11549v2

Omnidirectional images (ODIs) provide full 360x180 view which are widely adopted in VR, AR and embodied intelligence applications. While multi-modal large language models (MLLMs) have demonstrated remarkable performance on conventional 2D image and video understanding benchmarks, their ability to comprehend the immersive environments captured by ODIs remains largely unexplored. To address this gap, we first present ODI-Bench, a novel comprehensive benchmark specifically designed for omnidirectional image understanding. ODI-Bench contains 2,000 high-quality omnidirectional images and over 4,000 manually annotated question-answering (QA) pairs across 10 fine-grained tasks, covering both general-level and spatial-level ODI understanding. Extensive experiments are conducted to benchmark 20 representative MLLMs, including proprietary and open-source models, under both close-ended and open-ended settings. Experimental results reveal that current MLLMs still struggle to capture the immersive context provided by ODIs. To this end, we further introduce Omni-CoT, a training-free method which significantly enhances MLLMs' comprehension ability in the omnidirectional environment through chain-of-thought reasoning across both textual information and visual cues. Both the benchmark and the code will be released at https://github.com/ylylyl-sjtu/ODI-Bench.

---

### Efficient Group Lasso Regularized Rank Regression with Simulation-Based Tuning

Authors: Meixia Lin, Mengjiao Shi, Yunhai Xiao, Qian Zhang
Published: 2025-10-13
Categories: stat.ML, cs.LG, math.OC, math.ST
arXiv: https://arxiv.org/abs/2510.11546v3

High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods. To improve robustness, we adopt a non-smooth Wilcoxon score based rank objective and incorporate the group sparsity regularization. By extending the tuning-free property originally developed for the rank Lasso, we introduce a simulation-based tuning rule and further establish a finite-sample error bound for the resulting estimator. To solve the associated optimization problem, we develop a proximal augmented Lagrangian method, for which we provide a novel convergence analysis by proving the metric subregularity of the underlying non-polyhedral KKT mapping, while enabling efficient semismooth Newton updates for the subproblems. Extensive numerical experiments demonstrate the robustness and effectiveness of our proposed estimator against several leading alternatives, and showcase the efficiency and scalability of our algorithm compared to the state-of-the-art baseline in both simulated and real-data settings.

---

### Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Authors: Jiayu Ding, Lei Cui, Li Dong, Nanning Zheng, Furu Wei
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11545v1

Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex tasks. While revealing these reasoning traces helps users better follow, verify, and learn from the model's problem-solving process, it also makes them highly vulnerable to unauthorized distillation. To mitigate this risk, proprietary model providers often adopt aggressive protection strategies, such as replacing detailed reasoning with brief summaries, which deprive users of valuable intermediate information. To address this trade-off, we propose PART, an information-preserving antidistillation reformulation of reasoning traces. Motivated by the difference between how humans understand reasoning traces and how LLMs exploit them for supervised fine-tuning, we design a simple but effective two-step reformulation: removing self-talk behaviors and reordering sub-conclusions. A small auxiliary model is trained to perform this reformulation, incurring minimal computational overhead. Extensive experiments demonstrate that PART consistently disrupts distillation across student models of different sizes and types on various reasoning benchmarks. For instance, when training on reformulated traces, even the performance of a large 32B student model decreases from 54.17 to 46.88 on AIME 2024, corresponding to a 13.5% degradation.

---

### Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

Authors: Yuchen Yan, Peiyan Zhang, Zhihua Liu, Hao Wang, Yatao Bian, Weiming Li, Xiaoshuai Hao
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11541v2

Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval of multiple information targets. To address these limitations, we propose a novel graph representation learning framework for multi-hop question retrieval. We first introduce a Multi-information Level Knowledge Graph (Multi-L KG) to model various information levels for a more comprehensive understanding of multi-hop questions. Based on this, we design a Question-Adaptive Graph Neural Network (Quest-GNN) for representation learning on the Multi-L KG. Quest-GNN employs intra/inter-level message passing mechanisms, and in each message passing the information aggregation is guided by the question, which not only facilitates multi-granular information aggregation but also significantly reduces the impact of noise. To enhance its ability to learn robust representations, we further propose two synthesized data generation strategies for pre-training the Quest-GNN. Extensive experimental results demonstrate the effectiveness of our framework in multi-hop scenarios, especially in high-hop questions the improvement can reach 33.8\%. The code is available at: https://github.com/Jerry2398/QSGNN.

---

### Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers

Authors: Chaofan Gan, Zicheng Zhao, Yuanpeng Tu, Xi Chen, Ziran Qin, Tieyuan Chen, Mehrtash Harandi, Weiyao Lin
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11538v2

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feature maps, yet their function remains poorly understood. In this work, we systematically investigate these activations to elucidate their role in visual generation. We found that these massive activations occur across all spatial tokens, and their distribution is modulated by the input timestep embeddings. Importantly, our investigations further demonstrate that these massive activations play a key role in local detail synthesis, while having minimal impact on the overall semantic content of output. Building on these insights, we propose \textbf{D}etail \textbf{G}uidance (\textbf{DG}), a MAs-driven, training-free self-guidance strategy to explicitly enhance local detail fidelity for DiTs. Specifically, DG constructs a degraded ``detail-deficient'' model by disrupting MAs and leverages it to guide the original network toward higher-quality detail synthesis. Our DG can seamlessly integrate with Classifier-Free Guidance (CFG), enabling further refinements of fine-grained details. Extensive experiments demonstrate that our DG consistently improves fine-grained detail quality across various pre-trained DiTs (\eg, SD3, SD3.5, and Flux).

---

### An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification

Authors: Ba-Quang Nguyen
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11537v1

We propose a novel neural architecture named TextGraphFuseGAT, which integrates a pretrained transformer encoder (PhoBERT) with Graph Attention Networks for token-level classification tasks. The proposed model constructs a fully connected graph over the token embeddings produced by PhoBERT, enabling the GAT layer to capture rich inter-token dependencies beyond those modeled by sequential context alone. To further enhance contextualization, a Transformer-style self-attention layer is applied on top of the graph-enhanced embeddings. The final token representations are passed through a classification head to perform sequence labeling. We evaluate our approach on three Vietnamese benchmark datasets: PhoNER-COVID19 for named entity recognition in the COVID-19 domain, PhoDisfluency for speech disfluency detection, and VietMed-NER for medical-domain NER. VietMed-NER is the first Vietnamese medical spoken NER dataset, featuring 18 entity types collected from real-world medical speech transcripts and annotated with the BIO tagging scheme. Its specialized vocabulary and domain-specific expressions make it a challenging benchmark for token-level classification models. Experimental results show that our method consistently outperforms strong baselines, including transformer-only and hybrid neural models such as BiLSTM + CNN + CRF, confirming the effectiveness of combining pretrained semantic features with graph-based relational modeling for improved token classification across multiple domains.

---

### CodeWatcher: IDE Telemetry Data Extraction Tool for Understanding Coding Interactions with LLMs

Authors: Manaal Basha, Aimeê M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodríguez-Pérez
Published: 2025-10-13
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.11536v1

Understanding how developers interact with code generation tools (CGTs) requires detailed, real-time data on programming behavior which is often difficult to collect without disrupting workflow. We present \textit{CodeWatcher}, a lightweight, unobtrusive client-server system designed to capture fine-grained interaction events from within the Visual Studio Code (VS Code) editor. \textit{CodeWatcher} logs semantically meaningful events such as insertions made by CGTs, deletions, copy-paste actions, and focus shifts, enabling continuous monitoring of developer activity without modifying user workflows. The system comprises a VS Code plugin, a Python-based RESTful API, and a MongoDB backend, all containerized for scalability and ease of deployment. By structuring and timestamping each event, \textit{CodeWatcher} enables post-hoc reconstruction of coding sessions and facilitates rich behavioral analyses, including how and when CGTs are used during development. This infrastructure is crucial for supporting research on responsible AI, developer productivity, and the human-centered evaluation of CGTs. Please find the demo, diagrams, and tool here: https://osf.io/j2kru/overview.

---

### A Flexible Multi-Agent Deep Reinforcement Learning Framework for Dynamic Routing and Scheduling of Latency-Critical Services

Authors: Vincenzo Norman Vitale, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca
Published: 2025-10-13
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2510.11535v1

Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is increasingly essential for a range of interactive applications, such as industrial automation, self-driving vehicles, and augmented reality. However, most existing network control solutions target only average delay performance, falling short of providing strict End-to-End (E2E) peak latency guarantees. This paper addresses the challenge of reliably delivering packets within application-imposed deadlines by leveraging recent advancements in Multi-Agent Deep Reinforcement Learning (MA-DRL). After introducing the Delay-Constrained Maximum-Throughput (DCMT) dynamic network control problem, and highlighting the limitations of current solutions, we present a novel MA-DRL network control framework that leverages a centralized routing and distributed scheduling architecture. The proposed framework leverages critical networking domain knowledge for the design of effective MA-DRL strategies based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) technique, where centralized routing and distributed scheduling agents dynamically assign paths and schedule packet transmissions according to packet lifetimes, thereby maximizing on-time packet delivery. The generality of the proposed framework allows integrating both data-driven \blue{Deep Reinforcement Learning (DRL)} agents and traditional rule-based policies in order to strike the right balance between performance and learning complexity. Our results confirm the superiority of the proposed framework with respect to traditional stochastic optimization-based approaches and provide key insights into the role and interplay between data-driven DRL agents and new rule-based policies for both efficient and high-performance control of latency-critical services.

---

### Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models

Authors: Yusheng Song, Lirong Qiu, Xi Zhang, Zhihao Tang
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11529v2

The detection of sophisticated hallucinations in Large Language Models (LLMs) is hampered by a ``Detection Dilemma'': methods probing internal states (Internal State Probing) excel at identifying factual inconsistencies but fail on logical fallacies, while those verifying externalized reasoning (Chain-of-Thought Verification) show the opposite behavior. This schism creates a task-dependent blind spot: Chain-of-Thought Verification fails on fact-intensive tasks like open-domain QA where reasoning is ungrounded, while Internal State Probing is ineffective on logic-intensive tasks like mathematical reasoning where models are confidently wrong. We resolve this with a unified framework that bridges this critical gap. However, unification is hindered by two fundamental challenges: the Signal Scarcity Barrier, as coarse symbolic reasoning chains lack signals directly comparable to fine-grained internal states, and the Representational Alignment Barrier, a deep-seated mismatch between their underlying semantic spaces. To overcome these, we introduce a multi-path reasoning mechanism to obtain more comparable, fine-grained signals, and a segment-aware temporalized cross-attention module to adaptively fuse these now-aligned representations, pinpointing subtle dissonances. Extensive experiments on three diverse benchmarks and two leading LLMs demonstrate that our framework consistently and significantly outperforms strong baselines. Our code is available: https://github.com/peach918/HalluDet.

---

### mmWalk: Towards Multi-modal Multi-view Walking Assistance

Authors: Kedi Ying, Ruiping Liu, Chongyan Chen, Mingzhe Tao, Hao Shi, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11520v2

Walking assistance in extreme or complex environments remains a significant challenge for people with blindness or low vision (BLV), largely due to the lack of a holistic scene understanding. Motivated by the real-world needs of the BLV community, we build mmWalk, a simulated multi-modal dataset that integrates multi-view sensor and accessibility-oriented features for outdoor safe navigation. Our dataset comprises 120 manually controlled, scenario-categorized walking trajectories with 62k synchronized frames. It contains over 559k panoramic images across RGB, depth, and semantic modalities. Furthermore, to emphasize real-world relevance, each trajectory involves outdoor corner cases and accessibility-specific landmarks for BLV users. Additionally, we generate mmWalkVQA, a VQA benchmark with over 69k visual question-answer triplets across 9 categories tailored for safe and informed walking assistance. We evaluate state-of-the-art Vision-Language Models (VLMs) using zero- and few-shot settings and found they struggle with our risk assessment and navigational tasks. We validate our mmWalk-finetuned model on real-world datasets and show the effectiveness of our dataset for advancing multi-modal walking assistance.

---

### Cracking CodeWhisperer: Analyzing Developers' Interactions and Patterns During Programming Tasks

Authors: Jeena Javahar, Tanya Budhrani, Manaal Basha, Cleidson R. B. de Souza, Ivan Beschastnikh, Gema Rodriguez-Perez
Published: 2025-10-13
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2510.11516v1

The use of AI code-generation tools is becoming increasingly common, making it important to understand how software developers are adopting these tools. In this study, we investigate how developers engage with Amazon's CodeWhisperer, an LLM-based code-generation tool. We conducted two user studies with two groups of 10 participants each, interacting with CodeWhisperer - the first to understand which interactions were critical to capture and the second to collect low-level interaction data using a custom telemetry plugin. Our mixed-methods analysis identified four behavioral patterns: 1) incremental code refinement, 2) explicit instruction using natural language comments, 3) baseline structuring with model suggestions, and 4) integrative use with external sources. We provide a comprehensive analysis of these patterns .

---

### LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference

Authors: Jianhao Yuan, Fabio Pizzati, Francesco Pinto, Lars Kunze, Ivan Laptev, Paul Newman, Philip Torr, Daniele De Martini
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11512v3

Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in disentangling physics correctness from visual appearance in generation. To the end, we introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models by distinguishing physically valid and impossible videos using the denoising objective as an ELBO-based likelihood surrogate on a curated dataset of valid-invalid pairs. By testing on our constructed benchmark of twelve scenarios spanning over four physics domains, we show that our evaluation metric, Plausibility Preference Error (PPE), demonstrates strong alignment with human preference, outperforming state-of-the-art evaluator baselines. We then systematically benchmark intuitive physics understanding in current video diffusion models. Our study further analyses how model design and inference settings affect intuitive physics understanding and highlights domain-specific capacity variations across physical laws. Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.

---

### Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

Authors: Ruiping Liu, Junwei Zheng, Yufan Chen, Zirui Wang, Kunyu Peng, Kailun Yang, Jiaming Zhang, Marc Pollefeys, Rainer Stiefelhagen
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11509v1

Physical environments and circumstances are fundamentally dynamic, yet current 3D datasets and evaluation benchmarks tend to concentrate on either dynamic scenarios or dynamic situations in isolation, resulting in incomplete comprehension. To overcome these constraints, we introduce Situat3DChange, an extensive dataset supporting three situation-aware change understanding tasks following the perception-action model: 121K question-answer pairs, 36K change descriptions for perception tasks, and 17K rearrangement instructions for the action task. To construct this large-scale dataset, Situat3DChange leverages 11K human observations of environmental changes to establish shared mental models and shared situational awareness for human-AI collaboration. These observations, enriched with egocentric and allocentric perspectives as well as categorical and coordinate spatial relations, are integrated using an LLM to support understanding of situated changes. To address the challenge of comparing pairs of point clouds from the same scene with minor changes, we propose SCReasoner, an efficient 3D MLLM approach that enables effective point cloud comparison with minimal parameter overhead and no additional tokens required for the language decoder. Comprehensive evaluation on Situat3DChange tasks highlights both the progress and limitations of MLLMs in dynamic scene and situation understanding. Additional experiments on data scaling and cross-domain transfer demonstrate the task-agnostic effectiveness of using Situat3DChange as a training dataset for MLLMs.

---

### Towards Fast and Scalable Normal Integration using Continuous Components

Authors: Francesco Milano, Jen Jen Chung, Lionel Ott, Roland Siegwart
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11508v2

Surface normal integration is a fundamental problem in computer vision, dealing with the objective of reconstructing a surface from its corresponding normal map. Existing approaches require an iterative global optimization to jointly estimate the depth of each pixel, which scales poorly to larger normal maps. In this paper, we address this problem by recasting normal integration as the estimation of relative scales of continuous components. By constraining pixels belonging to the same component to jointly vary their scale, we drastically reduce the number of optimization variables. Our framework includes a heuristic to accurately estimate continuous components from the start, a strategy to rebalance optimization terms, and a technique to iteratively merge components to further reduce the size of the problem. Our method achieves state-of-the-art results on the standard normal integration benchmark in as little as a few seconds and achieves one-order-of-magnitude speedup over pixel-level approaches on large-resolution normal maps.

---

### Automatic Music Sample Identification with Multi-Track Contrastive Learning

Authors: Alain Riou, Joan Serrà, Yuki Mitsufuji
Published: 2025-10-13
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2510.11507v2

Sampling, the technique of reusing pieces of existing audio tracks to create new music content, is a very common practice in modern music production. In this paper, we tackle the challenging task of automatic sample identification, that is, detecting such sampled content and retrieving the material from which it originates. To do so, we adopt a self-supervised learning approach that leverages a multi-track dataset to create positive pairs of artificial mixes, and design a novel contrastive learning objective. We show that such method significantly outperforms previous state-of-the-art baselines, that is robust to various genres, and that scales well when increasing the number of noise songs in the reference database. In addition, we extensively analyze the contribution of the different components of our training pipeline and highlight, in particular, the need for high-quality separated stems for this task.

---

### Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest

Authors: Aleksei Rozanov, Samikshya Subedi, Vasudha Sharma, Bryan C. Runck
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11505v1

Evapotranspiration (ET) plays a critical role in the land-atmosphere interactions, yet its accurate quantification across various spatiotemporal scales remains a challenge. In situ measurement approaches, like eddy covariance (EC) or weather station-based ET estimation, allow for measuring ET at a single location. Agricultural uses of ET require estimates for each field over broad areas, making it infeasible to deploy sensing systems at each location. This study integrates tree-based and knowledge-guided machine learning (ML) techniques with multispectral remote sensing data, griddled meteorology and EC data to upscale ET across the Midwest United States. We compare four tree-based models - Random Forest, CatBoost, XGBoost, LightGBM - and a simple feed-forward artificial neural network in combination with features engineered using knowledge-guided ML principles. Models were trained and tested on EC towers located in the Midwest of the United States using k-fold cross validation with k=5 and site-year, biome stratified train-test split to avoid data leakage. Results show that LightGBM with knowledge-guided features outperformed other methods with an R2=0.86, MSE=14.99 W m^-2 and MAE = 8.82 W m^-2 according to grouped k-fold validation (k=5). Feature importance analysis shows that knowledge-guided features were most important for predicting evapotranspiration. Using the best performing model, we provide a data product at 500 m spatial and one-day temporal resolution for gridded ET for the period of 2019-2024. Intercomparison between the new gridded product and state-level weather station-based ET estimates show best-in-class correspondence.

---

### People use fast and flat simulation to reason about new games

Authors: Katherine M. Collins, Cedegao E. Zhang, Lionel Wong, Mauricio Barba da Costa, Graham Todd, Adrian Weller, Samuel J. Cheyette, Thomas L. Griffiths, Joshua B. Tenenbaum
Published: 2025-10-13
Categories: q-bio.NC, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2510.11503v2

Games have long been a microcosm for studying planning and reasoning in both natural and artificial intelligence (AI), often focusing on expert-level or even super-human play. But real life also pushes human intelligence along a different frontier, requiring people to flexibly navigate decision-making problems that they have never thought about before. Here, we use novice gameplay to study how people reason about new problem settings. Through a series of large-scale behavioral studies with over 1000 participants and 121 two-player strategic board games (almost all novel to our participants), we show that people are systematic and adaptively rational in how they play a game for the first time, or evaluate a game (e.g., how fair or how fun it is likely to be) before they have played it even once. We explain these capacities via a computational cognitive model that we call the 'Intuitive Gamer', a model based on mechanisms of fast and flat (depth-limited) goal-directed probabilistic simulation. Our work offers new insights into how people rapidly evaluate, act, and make suggestions when encountering novel problems, and could inform the design of more flexible and human-like AI systems that can determine not just how to solve new tasks, but whether a task is worth thinking about at all.

---

### Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors

Authors: Alexis Ross, Jacob Andreas
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11502v1

Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that can reason about and simulate student errors are useful for providing real-time feedback in the classroom or offline practice for educators-in-training. This paper presents a new method, MISTAKE, that (1) constructs high-quality synthetic examples of reasoning errors by leveraging cycle consistency between incorrect answers and latent misconceptions; and (2) uses the generated data to learn models for student simulation, misconception classification, and answer generation. We evaluate MISTAKE on three educational tasks and find that it results in (1) higher accuracy when simulating incorrect student answers based on specific misconceptions, (2) increased performance inferring latent misconceptions from observed incorrect answers, and (3) higher alignment with expert-written distractor answers when generating incorrect answers (e.g., for multiple-choice tests).

---

### Context-Aware Model-Based Reinforcement Learning for Autonomous Racing

Authors: Emran Yasser Moustafa, Ivana Dusparic
Published: 2025-10-13
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2510.11501v1

Autonomous vehicles have shown promising potential to be a groundbreaking technology for improving the safety of road users. For these vehicles, as well as many other safety-critical robotic technologies, to be deployed in real-world applications, we require algorithms that can generalize well to unseen scenarios and data. Model-based reinforcement learning algorithms (MBRL) have demonstrated state-of-the-art performance and data efficiency across a diverse set of domains. However, these algorithms have also shown susceptibility to changes in the environment and its transition dynamics. In this work, we explore the performance and generalization capabilities of MBRL algorithms for autonomous driving, specifically in the simulated autonomous racing environment, Roboracer (formerly F1Tenth). We frame the head-to-head racing task as a learning problem using contextual Markov decision processes and parameterize the driving behavior of the adversaries using the context of the episode, thereby also parameterizing the transition and reward dynamics. We benchmark the behavior of MBRL algorithms in this environment and propose a novel context-aware extension of the existing literature, cMask. We demonstrate that context-aware MBRL algorithms generalize better to out-of-distribution adversary behaviors relative to context-free approaches. We also demonstrate that cMask displays strong generalization capabilities, as well as further performance improvement relative to other context-aware MBRL approaches when racing against adversaries with in-distribution behaviors.

---

### Offline Reinforcement Learning with Generative Trajectory Policies

Authors: Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11499v2

Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitations of individual methods, we argue, lies in a unifying perspective that views modern generative models, including diffusion, flow matching, and consistency models, as specific instances of learning a continuous-time generative trajectory governed by an Ordinary Differential Equation (ODE). This principled foundation provides a clearer design space for generative policies in RL and allows us to propose Generative Trajectory Policies (GTPs), a new and more general policy paradigm that learns the entire solution map of the underlying ODE. To make this paradigm practical for offline RL, we further introduce two key theoretically principled adaptations. Empirical results demonstrate that GTP achieves state-of-the-art performance on D4RL benchmarks - it significantly outperforms prior generative policies, achieving perfect scores on several notoriously hard AntMaze tasks.

---