# Research Papers — 2025-10 · bundle page 112 of 217

> Full-text markdown of papers #5551–5600 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/112
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/111.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/113.md)

### Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models

Authors: Agnese Lombardi, Alessandro Lenci
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13395v1

Language is fundamental to human cooperation, facilitating not only the exchange of information but also the coordination of actions through shared interpretations of situational contexts. This study explores whether the Generative Agent-Based Model (GABM) Concordia can effectively model Theory of Mind (ToM) within simulated real-world environments. Specifically, we assess whether this framework successfully simulates ToM abilities and whether GPT-4 can perform tasks by making genuine inferences from social context, rather than relying on linguistic memorization. Our findings reveal a critical limitation: GPT-4 frequently fails to select actions based on belief attribution, suggesting that apparent ToM-like abilities observed in previous studies may stem from shallow statistical associations rather than true reasoning. Additionally, the model struggles to generate coherent causal effects from agent actions, exposing difficulties in processing complex social interactions. These results challenge current statements about emergent ToM-like capabilities in LLMs and highlight the need for more rigorous, action-based evaluation frameworks.

---

### Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models

Authors: Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, Xiaowei Huang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13394v4

Spatial reasoning ability is crucial for Vision Language Models (VLMs) to support real-world applications in diverse domains including robotics, augmented reality, and autonomous navigation. Unfortunately, existing benchmarks are inadequate in assessing spatial reasoning ability, especially the \emph{intrinsic-dynamic} spatial reasoning which is a fundamental aspect of human spatial cognition. In this paper, we propose a unified benchmark, \textbf{Spatial-DISE}, based on a cognitively grounded taxonomy that categorizes tasks into four fundamental quadrants: \textbf{I}ntrinsic-\textbf{S}tatic, Intrinsic-\textbf{D}ynamic, \textbf{E}xtrinsic-Static, and Extrinsic-Dynamic spatial reasoning. Moreover, to address the issue of data scarcity, we develop a scalable and automated pipeline to generate diverse and verifiable spatial reasoning questions, resulting in a new \textbf{Spatial-DISE} dataset that includes Spatial-DISE Bench (559 evaluation VQA pairs) and Spatial-DISE-12K (12K+ training VQA pairs). Our comprehensive evaluation across 28 state-of-the-art VLMs reveals that, current VLMs have a large and consistent gap to human competence, especially on multi-step multi-view spatial reasoning. Spatial-DISE offers a robust framework, valuable dataset, and clear direction for future research toward human-like spatial intelligence. Benchmark, dataset, and code will be publicly released.

---

### Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization

Authors: Yunxiao Zhao, Zhiqiang Wang, Xingtong Yu, Xiaoli Li, Jiye Liang, Ru Li
Published: 2025-10-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.13393v1

Rationalization, a data-centric framework, aims to build self-explanatory models to explain the prediction outcome by generating a subset of human-intelligible pieces of the input data. It involves a cooperative game model where a generator generates the most human-intelligible parts of the input (i.e., rationales), followed by a predictor that makes predictions based on these generated rationales. Conventional rationalization methods typically impose constraints via regularization terms to calibrate or penalize undesired generation. However, these methods are suffering from a problem called mode collapse, in which the predictor produces correct predictions yet the generator consistently outputs rationales with collapsed patterns. Moreover, existing studies are typically designed separately for specific collapsed patterns, lacking a unified consideration. In this paper, we systematically revisit cooperative rationalization from a novel game-theoretic perspective and identify the fundamental cause of this problem: the generator no longer tends to explore new strategies to uncover informative rationales, ultimately leading the system to converge to a suboptimal game equilibrium (correct predictions v.s collapsed rationales). To solve this problem, we then propose a novel approach, Game-theoretic Policy Optimization oriented RATionalization (PORAT), which progressively introduces policy interventions to address the game equilibrium in the cooperative game process, thereby guiding the model toward a more optimal solution state. We theoretically analyse the cause of such a suboptimal equilibrium and prove the feasibility of the proposed method. Furthermore, we validate our method on nine widely used real-world datasets and two synthetic settings, where PORAT achieves up to 8.1% performance improvements over existing state-of-the-art methods.

---

### Going with the Flow: Approximating Banzhaf Values via Graph Neural Networks

Authors: Benjamin Kempinski, Tal Kachman
Published: 2025-10-15
Categories: cs.LG, cs.GT
arXiv: https://arxiv.org/abs/2510.13391v2

Computing the Banzhaf value in network flow games is fundamental for quantifying agent influence in multi-agent systems, with applications ranging from cybersecurity to infrastructure planning. However, exact computation is intractable for systems with more than $\sim20$ agents due to exponential complexity $\mathcal{O}(2^m)$. While Monte Carlo sampling methods provide statistical estimates, they suffer from high sample complexity and cannot transfer knowledge across different network configurations, making them impractical for large-scale or dynamic systems. We present a novel learning-based approach using Graph Neural Networks (GNNs) to approximate Banzhaf values in cardinal network flow games. By framing the problem as a graph-level prediction task, our method learns generalisable patterns of agent influence directly from network topology and control structure. We conduct a comprehensive empirical study comparing three state-of-the-art GNN architectures-Graph Attention Networks (GAT), Graph Isomorphism Networks with Edge features (GINE), and EdgeConv-on a large-scale synthetic dataset of 200,000 graphs per configuration, varying in size (20-100 nodes), agent count (5-20), and edge probability (0.5-1.0). Our results demonstrate that trained GNN models achieve high-fidelity Banzhaf value approximation with order-of-magnitude speedups compared to exact and sampling-based methods. Most significantly, we show strong zero-shot generalisation: models trained on graphs of a specific size and topology accurately predict Banzhaf values for entirely new networks with different structural properties, without requiring retraining. This work establishes GNNs as a practical tool for scalable cooperative game-theoretic analysis of complex networked systems.

---

### Generalizing WiFi Gesture Recognition via Large-Model-Aware Semantic Distillation and Alignment

Authors: Feng-Qi Cui, Yu-Tong Guo, Tianyue Zheng, Jinyang Huang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13390v1

WiFi-based gesture recognition has emerged as a promising RF sensing paradigm for enabling non-contact and privacy-preserving human-computer interaction in AIoT environments. However, existing methods often suffer from limited generalization and semantic expressiveness due to the domain-sensitive nature of Channel State Information and the lack of high-level gesture abstraction. To address these challenges, we propose a novel generalization framework, termed Large-Model-Aware Semantic Distillation and Alignment (GLSDA), which leverages the semantic prior of pre-trained large foundation models to enhance gesture representation learning in both in-domain and cross-domain scenarios. Specifically, we first design a dual-path CSI encoding pipeline that captures geometric and dynamic gesture patterns via CSI-Ratio phase sequences and Doppler spectrograms. These representations are then fed into a Multiscale Semantic Encoder, which learns robust temporal embeddings and aligns them with gesture semantics through cross-modal attention mechanisms. To further enhance category discrimination, we introduce a Semantic-Aware Soft Supervision scheme that encodes inter-class correlations and reduces label ambiguity, especially for semantically similar gestures. Finally, we develop a Robust Dual-Distillation strategy to compress the aligned model into a lightweight student network, jointly distilling intermediate features and semantic-informed soft labels from the teacher model. Extensive experiments on the Widar3.0 benchmark show that GLSDA consistently outperforms state-of-the-art methods in both in-domain and cross-domain gesture recognition tasks, while significantly reducing model size and inference latency. Our method offers a scalable and deployable solution for generalized RF-based gesture interfaces in real-world AIoT applications.

---

### Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment

Authors: Buwei He, Yang Liu, Zhaowei Zhang, Zixia Jia, Yang Yu, Huijia Wu, Zhaofeng He, Zilong Zheng, Yipeng Kang
Published: 2025-10-15
Categories: cs.CL, cs.GT
arXiv: https://arxiv.org/abs/2510.13387v3

Large language models (LLMs) still struggle with strategic persuasion, largely because existing approaches either neglect information asymmetry or rely on unrealistic pre-commitment assumptions. We introduce a type-induced commitment-communication mechanism that grounds Bayesian Persuasion (BP) in natural language dialogue without pre-commitment: the persuader narrates their potential types (e.g., honest vs. dishonest) to dynamically construct an information schema, enabling the persuadee to perform Bayesian belief updates within the conversation itself. We implement two variants: Semi-Formal-Natural-Language (SFNL) and Fully-Natural-Language (FNL), evaluating them against strong baselines across multiple LLMs and human judges. BP strategies consistently outperform baselines: SFNL excels in logical credibility, while FNL shows superior robustness and emotional resonance. We verify that gains stem from genuine Bayesian reasoning rather than superficial formatting, and we further show that supervised fine-tuning enables small models to match the persuasive performance of much larger ones.

---

### Probabilistic Prediction Markets with Intermittent Contributions

Authors: Michael Vitali, Pierre Pinson
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13385v3

Although both data availability and the demand for accurate forecasts are increasing, collaboration between stakeholders is often constrained by data ownership and competitive interests. In contrast to recent proposals within cooperative game-theoretical frameworks, we place ourselves in a more general framework, based on prediction markets. There, independent agents trade forecasts of uncertain future events in exchange for rewards. We introduce and analyse a prediction market that (i) accounts for the historical performance of the agents, (ii) adapts to time-varying conditions, while (iii) permitting agents to enter and exit the market at will. The proposed design employs robust regression models to learn the optimal forecasts' combination whilst handling missing submissions. Moreover, we introduce a pay-off allocation mechanism that considers both in-sample and out-of-sample performance while satisfying several desirable economic properties. Case-studies using simulated and real-world data allow demonstrating the effectiveness and adaptability of the proposed market design.

---

### Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering

Authors: Siddharth Tourani, Jayaram Reddy, Akash Kumbar, Satyajit Tourani, Nishant Goyal, Madhava Krishna, N. Dinesh Reddy, Muhammad Haris Khan
Published: 2025-10-15
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.13381v1

Dynamic scene rendering and reconstruction play a crucial role in computer vision and augmented reality. Recent methods based on 3D Gaussian Splatting (3DGS), have enabled accurate modeling of dynamic urban scenes, but for urban scenes they require both camera and LiDAR data, ground-truth 3D segmentations and motion data in the form of tracklets or pre-defined object templates such as SMPL. In this work, we explore whether a combination of 2D object agnostic priors in the form of depth and point tracking coupled with a signed distance function (SDF) representation for dynamic objects can be used to relax some of these requirements. We present a novel approach that integrates Signed Distance Functions (SDFs) with 3D Gaussian Splatting (3DGS) to create a more robust object representation by harnessing the strengths of both methods. Our unified optimization framework enhances the geometric accuracy of 3D Gaussian splatting and improves deformation modeling within the SDF, resulting in a more adaptable and precise representation. We demonstrate that our method achieves state-of-the-art performance in rendering metrics even without LiDAR data on urban scenes. When incorporating LiDAR, our approach improved further in reconstructing and generating novel views across diverse object categories, without ground-truth 3D motion annotation. Additionally, our method enables various scene editing tasks, including scene decomposition, and scene composition.

---

### DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning

Authors: Tianyuan Yuan, Yicheng Liu, Chenhao Lu, Zhuoguang Chen, Tao Jiang, Hang Zhao
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13375v1

Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requiring precise spatial reasoning due to limited spatial reasoning inherited from Vision-Language Models (VLMs). Existing VLAs rely on extensive action-data pretraining to ground VLMs in 3D space, which reduces training efficiency and is still insufficient for accurate spatial understanding. In this work, we present DepthVLA, a simple yet effective VLA architecture that explicitly incorporates spatial awareness through a pretrained depth prediction module. DepthVLA adopts a mixture-of-transformers design that unifies a VLM, a depth transformer, and an action expert with fully shared attentions, forming an end-to-end model with enhanced spatial reasoning. Extensive evaluations in both real-world and simulated environments show that DepthVLA outperforms state-of-the-art approaches, achieving 78.5% vs. 65.0% progress in real-world tasks, 94.9% vs. 93.6% in the LIBERO simulator, and 74.8% vs. 58.8% in the Simpler simulator. Our code will be made publicly available.

---

### MADREC: A Multi-Aspect Driven LLM Agent for Explainable and Adaptive Recommendation

Authors: Jiin Park, Misuk Kim
Published: 2025-10-15
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.13371v1

Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM Agent MADRec, an autonomous LLM-based recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews and performs direct recommendation, sequential recommendation, and explanation generation. MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs. When the ground-truth item is missing from the output, the Self-Feedback mechanism dynamically adjusts the inference criteria. Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability, with human evaluation further confirming the persuasiveness of the generated explanations.

---

### Contrastive Learning-Based Dependency Modeling for Anomaly Detection in Cloud Services

Authors: Yue Xing, Yingnan Deng, Heyao Liu, Ming Wang, Yun Zi, Xiaoxuan Sun
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13368v1

This paper addresses the challenges of complex dependencies and diverse anomaly patterns in cloud service environments by proposing a dependency modeling and anomaly detection method that integrates contrastive learning. The method abstracts service interactions into a dependency graph, extracts temporal and structural features through embedding functions, and employs a graph convolution mechanism to aggregate neighborhood information for context-aware service representations. A contrastive learning framework is then introduced, constructing positive and negative sample pairs to enhance the separability of normal and abnormal patterns in the representation space. Furthermore, a temporal consistency constraint is designed to maintain representation stability across time steps and reduce the impact of short-term fluctuations and noise. The overall optimization combines contrastive loss and temporal consistency loss to ensure stable and reliable detection across multi-dimensional features. Experiments on public datasets systematically evaluate the method from hyperparameter, environmental, and data sensitivity perspectives. Results show that the proposed approach significantly outperforms existing methods on key metrics such as Precision, Recall, F1-Score, and AUC, while maintaining robustness under conditions of sparse labeling, monitoring noise, and traffic fluctuations. This study verifies the effectiveness of integrating dependency modeling with contrastive learning, provides a complete technical solution for cloud service anomaly detection, and demonstrates strong adaptability and stability in complex environments.

---

### A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control

Authors: Nikita Kachaev, Daniil Zelezetsky, Egor Cherepanov, Alexey K. Kovelev, Aleksandr I. Panov
Published: 2025-10-15
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2510.13367v1

Despite their effectiveness and popularity in offline or model-based reinforcement learning (RL), transformers remain underexplored in online model-free RL due to their sensitivity to training setups and model design decisions such as how to structure the policy and value networks, share components, or handle temporal information. In this paper, we show that transformers can be strong baselines for continuous control in online model-free RL. We investigate key design questions: how to condition inputs, share components between actor and critic, and slice sequential data for training. Our experiments reveal stable architectural and training strategies enabling competitive performance across fully and partially observable tasks, and in both vector- and image-based settings. These findings offer practical guidance for applying transformers in online RL.

---

### Document Intelligence in the Era of Large Language Models: A Survey

Authors: Weishi Wang, Hengchang Hu, Zhijie Zhang, Zhaochen Li, Hongxin Shao, Daniel Dahlmeier
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13366v1

Document AI (DAI) has emerged as a vital application area, and is significantly transformed by the advent of large language models (LLMs). While earlier approaches relied on encoder-decoder architectures, decoder-only LLMs have revolutionized DAI, bringing remarkable advancements in understanding and generation. This survey provides a comprehensive overview of DAI's evolution, highlighting current research attempts and future prospects of LLMs in this field. We explore key advancements and challenges in multimodal, multilingual, and retrieval-augmented DAI, while also suggesting future research directions, including agent-based approaches and document-specific foundation models. This paper aims to provide a structured analysis of the state-of-the-art in DAI and its implications for both academic and practical applications.

---

### Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity

Authors: MingZe Tang, Jubal Chandy Jacob
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13364v1

Recent Vision-Language Models (VLMs) enable zero-shot classification by aligning images and text in a shared space, a promising approach for data-scarce conditions. However, the influence of prompt design on recognizing visually similar categories, such as human postures, is not well understood. This study investigates how prompt specificity affects the zero-shot classification of sitting, standing, and walking/running on a small, 285-image COCO-derived dataset. A suite of modern VLMs, including OpenCLIP, MetaCLIP 2, and SigLip, were evaluated using a three-tiered prompt design that systematically increases linguistic detail. Our findings reveal a compelling, counter-intuitive trend: for the highest-performing models (MetaCLIP 2 and OpenCLIP), the simplest, most basic prompts consistently achieve the best results. Adding descriptive detail significantly degrades performance for instance, MetaCLIP 2's multi-class accuracy drops from 68.8\% to 55.1\% a phenomenon we term "prompt overfitting". Conversely, the lower-performing SigLip model shows improved classification on ambiguous classes when given more descriptive, body-cue-based prompts.

---

### D-SMART: Enhancing LLM Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree

Authors: Xiang Lei, Qin Li, Min Zhang, Min Zhang
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13363v1

Large Language Models (LLMs) often exhibit factual inconsistencies and logical decay in extended, multi-turn dialogues, a challenge stemming from their reliance on static, pre-trained knowledge and an inability to reason adaptively over the dialogue history. Prevailing mitigation strategies, such as Retrieval-Augmented Generation (RAG) and agentic working memories, improve information recall but still engage with fundamentally static knowledge sources and follow pre-defined single reasoning path. This hinders their ability to preserve factual and logical consistency of their responses in multi-turn dialogues while the context evolves over time. To address this issue, we propose D-SMART, a model-agnostic framework designed to maintain multi-turn dialogue consistency by enabling LLMs to build and reason over a dynamic, structured representation of the conversational context. This is achieved via two synergistic components: (1) a Dynamic Structured Memory (DSM), which incrementally constructs and maintains an authoritative, OWL-compliant knowledge graph of the conversation; and (2) a Reasoning Tree (RT), which executes inferences as an explicit and traceable multi-step search over the graph. As the popular-used quality score (judged by GPT-4) can overlook logical flaws, we introduce new NLI-based metrics to better measure multi-turn dialogue consistency. Comprehensive experiments on the MT-Bench-101 benchmark show that D-SMART significantly outperforms state-of-the-art baselines, elevating the dialogue consistency score by over 48\% for both proprietary and open-source models, and notably improves the quality score of the latter by up to 10.1\%.

---

### Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training

Authors: Yisen Wang, Yichuan Mo, Hongjun Wang, Junyi Li, Zhouchen Lin
Published: 2025-10-15
Categories: cs.LG, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2510.13361v1

Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. While AT has been extensively studied, its practical applications expose two major limitations: natural accuracy tends to degrade significantly compared with standard training, and robustness does not transfer well across attacks crafted under different norm constraints. Unlike prior works that attempt to address only one issue within a single network, we propose to partition the overall generalization goal into multiple sub-tasks, each assigned to a dedicated base learner. By specializing in its designated objective, each base learner quickly becomes an expert in its field. In the later stages of training, we interpolate their parameters to form a knowledgeable global learner, while periodically redistributing the global parameters back to the base learners to prevent their optimization trajectories from drifting too far from the shared target. We term this framework Generalist and introduce three variants tailored to different application scenarios. Both theoretical analysis and extensive experiments demonstrate that Generalist achieves lower generalization error and significantly alleviates the trade-off problems compared with baseline methods. Our results suggest that Generalist provides a promising step toward developing fully robust classifiers in the future.

---

### Improving Visual Recommendation on E-commerce Platforms Using Vision-Language Models

Authors: Yuki Yada, Sho Akiyama, Ryo Watanabe, Yuta Ueno, Yusuke Shido, Andre Rusli
Published: 2025-10-15
Categories: cs.IR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2510.13359v1

On large-scale e-commerce platforms with tens of millions of active monthly users, recommending visually similar products is essential for enabling users to efficiently discover items that align with their preferences. This study presents the application of a vision-language model (VLM) -- which has demonstrated strong performance in image recognition and image-text retrieval tasks -- to product recommendations on Mercari, a major consumer-to-consumer marketplace used by more than 20 million monthly users in Japan. Specifically, we fine-tuned SigLIP, a VLM employing a sigmoid-based contrastive loss, using one million product image-title pairs from Mercari collected over a three-month period, and developed an image encoder for generating item embeddings used in the recommendation system. Our evaluation comprised an offline analysis of historical interaction logs and an online A/B test in a production environment. In offline analysis, the model achieved a 9.1% improvement in nDCG@5 compared with the baseline. In the online A/B test, the click-through rate improved by 50% whereas the conversion rate improved by 14% compared with the existing model. These results demonstrate the effectiveness of VLM-based encoders for e-commerce product recommendations and provide practical insights into the development of visual similarity-based recommendation systems.

---

### Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control

Authors: Shingo Ayabe, Hiroshi Kera, Kazuhiko Kawamoto
Published: 2025-10-15
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.13358v2

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study introduces an offline-to-online framework that trains policies on clean data and then performs adversarial fine-tuning, where perturbations are injected into executed actions to induce compensatory behavior and improve resilience. A performance-aware curriculum further adjusts the perturbation probability during training via an exponential-moving-average signal, balancing robustness and stability throughout the learning process. Experiments on continuous-control locomotion tasks demonstrate that the proposed method consistently improves robustness over offline-only baselines and converges faster than training from scratch. Matching the fine-tuning and evaluation conditions yields the strongest robustness to action-space perturbations, while the adaptive curriculum strategy mitigates the degradation of nominal performance observed with the linear curriculum strategy. Overall, the results show that adversarial fine-tuning enables adaptive and robust control under uncertain environments, bridging the gap between offline efficiency and online adaptability.

---

### Personal Attribute Leakage in Federated Speech Models

Authors: Hamdan Al-Ali, Ali Reza Ghavamipour, Tommaso Caselli, Fatih Turkmen, Zeerak Talat, Hanan Aldarmaki
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13357v1

Federated learning is a common method for privacy-preserving training of machine learning models. In this paper, we analyze the vulnerability of ASR models to attribute inference attacks in the federated setting. We test a non-parametric white-box attack method under a passive threat model on three ASR models: Wav2Vec2, HuBERT, and Whisper. The attack operates solely on weight differentials without access to raw speech from target speakers. We demonstrate attack feasibility on sensitive demographic and clinical attributes: gender, age, accent, emotion, and dysarthria. Our findings indicate that attributes that are underrepresented or absent in the pre-training data are more vulnerable to such inference attacks. In particular, information about accents can be reliably inferred from all models. Our findings expose previously undocumented vulnerabilities in federated ASR models and offer insights towards improved security.

---

### Kernel Representation and Similarity Measure for Incomplete Data

Authors: Yang Cao, Sikun Yang, Kai He, Wenjun Ma, Ming Liu, Yujiu Yang, Jian Weng
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13352v1

Measuring similarity between incomplete data is a fundamental challenge in web mining, recommendation systems, and user behavior analysis. Traditional approaches either discard incomplete data or perform imputation as a preprocessing step, leading to information loss and biased similarity estimates. This paper presents the proximity kernel, a new similarity measure that directly computes similarity between incomplete data in kernel feature space without explicit imputation in the original space. The proposed method introduces data-dependent binning combined with proximity assignment to project data into a high-dimensional sparse representation that adapts to local density variations. For missing value handling, we propose a cascading fallback strategy to estimate missing feature distributions. We conduct clustering tasks on the proposed kernel representation across 12 real world incomplete datasets, demonstrating superior performance compared to existing methods while maintaining linear time complexity. All the code are available at https://anonymous.4open.science/r/proximity-kernel-2289.

---

### Protect: Towards Robust Guardrailing Stack for Trustworthy Enterprise LLM Systems

Authors: Karthik Avinash, Nikhil Pareek, Rishav Hada
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13351v1

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions often struggle with real-time oversight, multi-modal data handling, and explainability -- limitations that hinder their adoption in regulated environments. Existing guardrails largely operate in isolation, focused on text alone making them inadequate for multi-modal, production-scale environments. We introduce Protect, natively multi-modal guardrailing model designed to operate seamlessly across text, image, and audio inputs, designed for enterprise-grade deployment. Protect integrates fine-tuned, category-specific adapters trained via Low-Rank Adaptation (LoRA) on an extensive, multi-modal dataset covering four safety dimensions: toxicity, sexism, data privacy, and prompt injection. Our teacher-assisted annotation pipeline leverages reasoning and explanation traces to generate high-fidelity, context-aware labels across modalities. Experimental results demonstrate state-of-the-art performance across all safety dimensions, surpassing existing open and proprietary models such as WildGuard, LlamaGuard-4, and GPT-4.1. Protect establishes a strong foundation for trustworthy, auditable, and production-ready safety systems capable of operating across text, image, and audio modalities.

---

### No-Reference Rendered Video Quality Assessment: Dataset and Metrics

Authors: Sipeng Yang, Jiayu Ji, Qingchuan Zhu, Zhiyao Yang, Xiaogang Jin
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13349v1

Quality assessment of videos is crucial for many computer graphics applications, including video games, virtual reality, and augmented reality, where visual performance has a significant impact on user experience. When test videos cannot be perfectly aligned with references or when references are unavailable, the significance of no-reference video quality assessment (NR-VQA) methods is undeniable. However, existing NR-VQA datasets and metrics are primarily focused on camera-captured videos; applying them directly to rendered videos would result in biased predictions, as rendered videos are more prone to temporal artifacts. To address this, we present a large rendering-oriented video dataset with subjective quality annotations, as well as a designed NR-VQA metric specific to rendered videos. The proposed dataset includes a wide range of 3D scenes and rendering settings, with quality scores annotated for various display types to better reflect real-world application scenarios. Building on this dataset, we calibrate our NR-VQA metric to assess rendered video quality by looking at both image quality and temporal stability. We compare our metric to existing NR-VQA metrics, demonstrating its superior performance on rendered videos. Finally, we demonstrate that our metric can be used to benchmark supersampling methods and assess frame generation strategies in real-time rendering.

---

### UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE

Authors: Zhenyu Liu, Yunxin Li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Jinchao Li, Qi Wang, Haolan Chen, Fanbo Meng, Mingjun Zhao et al.
Published: 2025-10-15
Categories: cs.SD, cs.CL
arXiv: https://arxiv.org/abs/2510.13344v1

Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation. However, the auditory domain remains a significant challenge, with music and speech often developed in isolation, hindering progress towards universal audio synthesis. This separation stems from inherent task conflicts and severe data imbalances, which impede the development of a truly unified audio generation model. To address this challenge, we propose UniMoE-Audio, a unified speech and music generation model within a novel Dynamic-Capacity Mixture-of-Experts (MoE) framework. Architecturally, UniMoE-Audio introduces a Top-P routing strategy for dynamic expert number allocation, and a hybrid expert design comprising routed experts for domain-specific knowledge, shared experts for domain-agnostic features, and null experts for adaptive computation skipping. To tackle data imbalance, we introduce a three-stage training curriculum: 1) Independent Specialist Training leverages original datasets to instill domain-specific knowledge into each "proto-expert" without interference; 2) MoE Integration and Warmup incorporates these specialists into the UniMoE-Audio architecture, warming up the gate module and shared expert using a subset of balanced dataset; and 3) Synergistic Joint Training trains the entire model end-to-end on the fully balanced dataset, fostering enhanced cross-domain synergy. Extensive experiments show that UniMoE-Audio not only achieves state-of-the-art performance on major speech and music generation benchmarks, but also demonstrates superior synergistic learning, mitigating the performance degradation typically seen in naive joint training. Our findings highlight the substantial potential of specialized MoE architecture and curated training strategies in advancing the field of universal audio generation. Homepage: https://mukioxun.github.io/Uni-MoE-site/home.html

---

### AOAD-MAT: Transformer-based multi-agent deep reinforcement learning model considering agents' order of action decisions

Authors: Shota Takayama, Katsuhide Fujita
Published: 2025-10-15
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2510.13343v1

Multi-agent reinforcement learning focuses on training the behaviors of multiple learning agents that coexist in a shared environment. Recently, MARL models, such as the Multi-Agent Transformer (MAT) and ACtion dEpendent deep Q-learning (ACE), have significantly improved performance by leveraging sequential decision-making processes. Although these models can enhance performance, they do not explicitly consider the importance of the order in which agents make decisions. In this paper, we propose an Agent Order of Action Decisions-MAT (AOAD-MAT), a novel MAT model that considers the order in which agents make decisions. The proposed model explicitly incorporates the sequence of action decisions into the learning process, allowing the model to learn and predict the optimal order of agent actions. The AOAD-MAT model leverages a Transformer-based actor-critic architecture that dynamically adjusts the sequence of agent actions. To achieve this, we introduce a novel MARL architecture that cooperates with a subtask focused on predicting the next agent to act, integrated into a Proximal Policy Optimization based loss function to synergistically maximize the advantage of the sequential decision-making. The proposed method was validated through extensive experiments on the StarCraft Multi-Agent Challenge and Multi-Agent MuJoCo benchmarks. The experimental results show that the proposed AOAD-MAT model outperforms existing MAT and other baseline models, demonstrating the effectiveness of adjusting the AOAD order in MARL.

---

### Proverbs or Pythian Oracles? Sentiments and Emotions in Greek Sayings

Authors: Katerina Korre, John Pavlopoulos
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13341v3

Proverbs are among the most fascinating language phenomena that transcend cultural and linguistic boundaries. Yet, much of the global landscape of proverbs remains underexplored, as many cultures preserve their traditional wisdom within their own communities due to the oral tradition of the phenomenon. Taking advantage of the current advances in Natural Language Processing (NLP), we focus on Greek proverbs, analyzing their sentiment and emotion. Departing from an annotated dataset of Greek proverbs, (1) we propose a multi-label annotation framework and dataset that captures the emotional variability of the proverbs, (2) we up-scale to local varieties, (3) we sketch a map of Greece that provides an overview of the distribution of emotions. Our findings show that the interpretation of proverbs is multidimensional, a property manifested through both multi-labeling and instance-level polarity. LLMs can capture and reproduce this complexity, and can therefore help us better understand the proverbial landscape of a place, as in the case of Greece, where surprise and anger compete and coexist within proverbs.

---

### Taming the Fragility of KV Cache Eviction in LLM Inference

Authors: Yuan Feng, Haoyu Guo, JunLin Lv, S. Kevin Zhou, Xike Xie
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13334v1

Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key-Value cache. To mitigate this, recent methods employ a scoring-aggregation framework to evict unimportant cache entries, based on the stability assumption-that a fixed subset of entries remains consistently important during generation. However, prior work has largely focused on refining importance indicators for scoring, while defaulting to mean aggregation due to a faithful trust in the stability assumption. In this work, we argue that this underlying assumption is inherently fragile, making mean aggregation highly vulnerable in extreme cases. To counter this, we propose a simple yet elegant defensive aggregation strategy: a two-step, linear-time approach that controls worst-case risk, thereby defending against extreme cases with negligible computational overhead. Embodying this strategy, we propose a novel cache eviction method, DefensiveKV and its extension, Layer-DefensiveKV, which incorporates layer-wise budget allocation. Across seven task domains (18 datasets), our methods reduce generation quality loss by 2.3x and 4.3x respectively, versus the strongest baseline under a 20% cache size. These results set new performance benchmarks and pioneer a promising direction for optimizing cache eviction against underlying fragility through worst-case risk management. Our code is available at https://github.com/FFY0/DefensiveKV.

---

### Group-Wise Optimization for Self-Extensible Codebooks in Vector Quantized Models

Authors: Hong-Kai Zheng, Piji Li
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13331v2

Vector Quantized Variational Autoencoders (VQ-VAEs) leverage self-supervised learning through reconstruction tasks to represent continuous vectors using the closest vectors in a codebook. However, issues such as codebook collapse persist in the VQ model. To address these issues, existing approaches employ implicit static codebooks or jointly optimize the entire codebook, but these methods constrain the codebook's learning capability, leading to reduced reconstruction quality. In this paper, we propose Group-VQ, which performs group-wise optimization on the codebook. Each group is optimized independently, with joint optimization performed within groups. This approach improves the trade-off between codebook utilization and reconstruction performance. Additionally, we introduce a training-free codebook resampling method, allowing post-training adjustment of the codebook size. In image reconstruction experiments under various settings, Group-VQ demonstrates improved performance on reconstruction metrics. And the post-training codebook sampling method achieves the desired flexibility in adjusting the codebook size.

---

### Embedding-Based Context-Aware Reranker

Authors: Ye Yuan, Mohammad Amin Shabani, Siqi Liu
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13329v2

Retrieval-Augmented Generation (RAG) systems rely on retrieving relevant evidence from a corpus to support downstream generation. The common practice of splitting a long document into multiple shorter passages enables finer-grained and targeted information retrieval. However, it also introduces challenges when a correct retrieval would require inference across passages, such as resolving coreference, disambiguating entities, and aggregating evidence scattered across multiple sources. Many state-of-the-art (SOTA) reranking methods, despite utilizing powerful large pretrained language models with potentially high inference costs, still neglect the aforementioned challenges. Therefore, we propose Embedding-Based Context-Aware Reranker (EBCAR), a lightweight reranking framework operating directly on embeddings of retrieved passages with enhanced cross-passage understandings through the structural information of the passages and a hybrid attention mechanism, which captures both high-level interactions across documents and low-level relationships within each document. We evaluate EBCAR against SOTA rerankers on the ConTEB benchmark, demonstrating its effectiveness for information retrieval requiring cross-passage inference and its advantages in both accuracy and efficiency.

---

### Thompson Sampling via Fine-Tuning of LLMs

Authors: Nicolas Menet, Aleksandar Terzić, Michael Hersche, Andreas Krause, Abbas Rahimi
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13328v4

Bayesian optimization in large unstructured discrete spaces is often hindered by the computational cost of maximizing acquisition functions due to the absence of gradients. We propose a scalable alternative based on Thompson sampling that eliminates the need for acquisition function maximization by directly parameterizing the probability that a candidate yields the maximum reward. Our approach, Thompson Sampling via Fine-Tuning (ToSFiT) leverages the prior knowledge embedded in prompt-conditioned large language models, and incrementally adapts them toward the posterior. Theoretically, we derive a novel regret bound for a variational formulation of Thompson Sampling that matches the strong guarantees of its standard counterpart. Our analysis reveals the critical role of careful adaptation to the posterior probability of maximality -- a principle that underpins our ToSFiT algorithm. Empirically, we validate our method on three diverse tasks: FAQ response refinement, thermally stable protein search, and quantum circuit design. Within a collection of methods covering in-context Bayesian optimization, reinforcement learning, and evolutionary search, ToSFiT exhibits both state-of-the-art sample efficiency and computational efficiency.

---

### When In Doubt, Abstain: The Impact of Abstention on Strategic Classification

Authors: Lina Alkarmi, Ziyuan Huang, Mingyan Liu
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13327v3

Algorithmic decision making is increasingly prevalent, but often vulnerable to strategic manipulation by agents seeking a favorable outcome. Prior research has shown that classifier abstention (allowing a classifier to decline making a decision due to insufficient confidence) can significantly increase classifier accuracy. This paper studies abstention within a strategic classification context, exploring how its introduction impacts strategic agents' responses and how principals should optimally leverage it. We model this interaction as a Stackelberg game where a principal, acting as the classifier, first announces its decision policy, and then strategic agents, acting as followers, manipulate their features to receive a desired outcome. Here, we focus on binary classifiers where agents manipulate observable features rather than their true features, and show that optimal abstention ensures that the principal's utility (or loss) is no worse than in a non-abstention setting, even in the presence of strategic agents. We also show that beyond improving accuracy, abstention can also serve as a deterrent to manipulation, making it costlier for agents, especially those less qualified, to manipulate to achieve a positive outcome when manipulation costs are significant enough to affect agent behavior. These results highlight abstention as a valuable tool for reducing the negative effects of strategic behavior in algorithmic decision making systems.

---

### DEF-YOLO: Leveraging YOLO for Concealed Weapon Detection in Thermal Imagin

Authors: Divya Bhardwaj, Arnav Ramamoorthy, Poonam Goyal
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13326v1

Concealed weapon detection aims at detecting weapons hidden beneath a person's clothing or luggage. Various imaging modalities like Millimeter Wave, Microwave, Terahertz, Infrared, etc., are exploited for the concealed weapon detection task. These imaging modalities have their own limitations, such as poor resolution in microwave imaging, privacy concerns in millimeter wave imaging, etc. To provide a real-time, 24 x 7 surveillance, low-cost, and privacy-preserved solution, we opted for thermal imaging in spite of the lack of availability of a benchmark dataset. We propose a novel approach and a dataset for concealed weapon detection in thermal imagery. Our YOLO-based architecture, DEF-YOLO, is built with key enhancements in YOLOv8 tailored to the unique challenges of concealed weapon detection in thermal vision. We adopt deformable convolutions at the SPPF layer to exploit multi-scale features; backbone and neck layers to extract low, mid, and high-level features, enabling DEF-YOLO to adaptively focus on localization around the objects in thermal homogeneous regions, without sacrificing much of the speed and throughput. In addition to these simple yet effective key architectural changes, we introduce a new, large-scale Thermal Imaging Concealed Weapon dataset, TICW, featuring a diverse set of concealed weapons and capturing a wide range of scenarios. To the best of our knowledge, this is the first large-scale contributed dataset for this task. We also incorporate focal loss to address the significant class imbalance inherent in the concealed weapon detection task. The efficacy of the proposed work establishes a new benchmark through extensive experimentation for concealed weapon detection in thermal imagery.

---

### Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning

Authors: Baogang Song, Dongdong Zhao, Jianwen Xiang, Qiben Xu, Zizhuo Yu
Published: 2025-10-15
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.13322v1

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detected through static analysis. In this work, we introduce the first paradigm of revocable backdoor attacks, where the backdoor can be proactively and thoroughly removed after the attack objective is achieved. We formulate the trigger optimization in revocable backdoor attacks as a bilevel optimization problem: by simulating both backdoor injection and unlearning processes, the trigger generator is optimized to achieve a high attack success rate (ASR) while ensuring that the backdoor can be easily erased through unlearning. To mitigate the optimization conflict between injection and removal objectives, we employ a deterministic partition of poisoning and unlearning samples to reduce sampling-induced variance, and further apply the Projected Conflicting Gradient (PCGrad) technique to resolve the remaining gradient conflicts. Experiments on CIFAR-10 and ImageNet demonstrate that our method maintains ASR comparable to state-of-the-art backdoor attacks, while enabling effective removal of backdoor behavior after unlearning. This work opens a new direction for backdoor attack research and presents new challenges for the security of machine learning systems.

---

### RockNet: Distributed Learning on Ultra-Low-Power Devices

Authors: Alexander Gräfe, Fabian Mager, Marco Zimmerling, Sebastian Trimpe
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13320v2

As Machine Learning (ML) becomes integral to Cyber-Physical Systems (CPS), there is growing interest in shifting training from traditional cloud-based to on-device processing (TinyML), for example, due to privacy and latency concerns. However, CPS often comprise ultra-low-power microcontrollers, whose limited compute resources make training challenging. This paper presents RockNet, a new TinyML method tailored for ultra-low-power hardware that achieves state-of-the-art accuracy in timeseries classification, such as fault or malware detection, without requiring offline pretraining. By leveraging that CPS consist of multiple devices, we design a distributed learning method that integrates ML and wireless communication. RockNet leverages all devices for distributed training of specialized compute efficient classifiers that need minimal communication overhead for parallelization. Combined with tailored and efficient wireless multi-hop communication protocols, our approach overcomes the communication bottleneck that often occurs in distributed learning. Hardware experiments on a testbed with 20 ultra-low-power devices demonstrate RockNet's effectiveness. It successfully learns timeseries classification tasks from scratch, surpassing the accuracy of the latest approach for neural network microcontroller training by up to 2x. RockNet's distributed ML architecture reduces memory, latency and energy consumption per device by up to 90 % when scaling from one central device to 20 devices. Our results show that a tight integration of distributed ML, distributed computing, and communication enables, for the first time, training on ultra-low-power hardware with state-of-the-art accuracy.

---

### Removing Cost Volumes from Optical Flow Estimators

Authors: Simon Kiefhaber, Stefan Roth, Simone Schaub-Meyer
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13317v1

Cost volumes are used in every modern optical flow estimator, but due to their computational and space complexity, they are often a limiting factor regarding both processing speed and the resolution of input frames. Motivated by our empirical observation that cost volumes lose their importance once all other network parts of, e.g., a RAFT-based pipeline have been sufficiently trained, we introduce a training strategy that allows removing the cost volume from optical flow estimators throughout training. This leads to significantly improved inference speed and reduced memory requirements. Using our training strategy, we create three different models covering different compute budgets. Our most accurate model reaches state-of-the-art accuracy while being $1.2\times$ faster and having a $6\times$ lower memory footprint than comparable models; our fastest model is capable of processing Full HD frames at $20\,\mathrm{FPS}$ using only $500\,\mathrm{MB}$ of GPU memory.

---

### Visual Interestingness Decoded: How GPT-4o Mirrors Human Interests

Authors: Fitim Abdullahu, Helmut Grabner
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13316v1

Our daily life is highly influenced by what we consume and see. Attracting and holding one's attention -- the definition of (visual) interestingness -- is essential. The rise of Large Multimodal Models (LMMs) trained on large-scale visual and textual data has demonstrated impressive capabilities. We explore these models' potential to understand to what extent the concepts of visual interestingness are captured and examine the alignment between human assessments and GPT-4o's, a leading LMM, predictions through comparative analysis. Our studies reveal partial alignment between humans and GPT-4o. It already captures the concept as best compared to state-of-the-art methods. Hence, this allows for the effective labeling of image pairs according to their (commonly) interestingness, which are used as training data to distill the knowledge into a learning-to-rank model. The insights pave the way for a deeper understanding of human interest.

---

### Self-Aug: Query and Entropy Adaptive Decoding for Large Vision-Language Models

Authors: Eun Woo Im, Muhammad Kashif Ali, Vivek Gupta
Published: 2025-10-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.13315v2

Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal capabilities, but they inherit the tendency to hallucinate from their underlying language models. While visual contrastive decoding has been proposed to mitigate this issue, existing methods often apply generic visual augmentations that disregard the specific context provided by the text query, limiting their effectiveness. This study introduces a novel training-free decoding strategy that addresses these limitations, featuring two key contributions. First, a self-augmentation prompting strategy that leverages the intrinsic knowledge of the model to dynamically align semantics between the query and the visual augmentation. Second, an adaptive thresholding algorithm that adaptively adjusts next token candidate size based on the output sparsity, utilizing full information from the logit distribution. Extensive experiments across four LVLMs and seven benchmarks demonstrate that the proposed decoding significantly enhances factual consistency compared to state-of-the-art decoding methods. This work highlights the importance of integrating query-dependent augmentation and entropy-aware decoding for improving effective generation of LVLMs.

---

### ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering

Authors: Simon Lupart, Mohammad Aliannejadi, Evangelos Kanoulas
Published: 2025-10-15
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2510.13312v2

We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an important role in CQA, where user intent evolves across dialogue turns, and utterances are often underspecified, requiring contextual interpretation, query reformulation, and dynamic coordination between retrieval and generation. Unlike static `rewrite, retrieve, and generate' pipelines, ChatR1 interleaves search and reasoning across turns, enabling exploratory and adaptive behaviors learned through RL. To address the challenge of sparse and delayed rewards in RL, we propose an intent-aware reward that provides turn-level feedback by aligning retrieval and reasoning with evolving user goals. ChatR1 demonstrates strong performance on both 3B and 7B model backbones, outperforming competitive models on five CQA datasets, measured by different metrics (F1, BERTScore, and LLM-as-judge). We include a diverse set of CQA datasets to cover topic shifts, evolving intents, mixed-initiative dialogues, and multi-document grounding, testing ChatR1's performance from various aspects. Ablation studies confirm the effectiveness of the intent-aware reward. Our analyses further reveal diverse reasoning trajectories and effective use of the search tool. ChatR1 also generalizes robustly across domains, demonstrating that RL-based reasoning enables more flexible and context-aware behavior than static CQA pipelines.

---

### Isolation-based Spherical Ensemble Representations for Tabular Anomaly Detection

Authors: Yang Cao, Sikun Yang, Hao Tian, Kai He, Lianyong Qi, Ming Liu, Yujiu Yang, Hong-Kun Zhang
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13311v2

Unsupervised tabular anomaly detection is a critical task with applications spanning offensive language detection, network security, and quality control. Despite extensive research, existing unsupervised anomaly detection methods still face fundamental challenges including conflicting distributional assumptions, computational inefficiency, and difficulty handling different anomaly types. To address these problems, we propose ISER (Isolation-based Spherical Ensemble Representations) that extends existing isolation-based methods by using hypersphere radii as a monotonic transformation of local density characteristics while maintaining linear time and constant space complexity w.r.t. the dataset size. ISER constructs ensemble representations where hypersphere radii encode local sparsity through a monotonic transformation of density: smaller radii correspond to dense regions while larger radii correspond to sparse regions. We introduce a novel similarity-based scoring method that measures pattern consistency by comparing ensemble representations against a theoretical anomaly reference pattern. Additionally, we enhance the performance of Isolation Forest by using ISER and adapting the scoring function to address axis-parallel bias and local anomaly detection limitations. Comprehensive experiments on 20 real-world datasets demonstrate ISER's competitive performance over 12 SOTA methods.

---

### InstantSfM: Towards GPU-Native SfM for the Deep Learning Era

Authors: Jiankun Zhong, Zitong Zhan, Quankai Gao, Ziyu Chen, Haozhe Lou, Jiageng Mao, Ulrich Neumann, Chen Wang, Yue Wang
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13310v3

Structure-from-Motion (SfM) is a fundamental technique for recovering camera poses and scene structure from multi-view imagery, serving as a critical upstream component for applications ranging from 3D reconstruction to modern neural scene representations such as 3D Gaussian Splatting. However, most mature SfM systems remain CPU-centric and built upon traditional optimization toolchains, creating a growing mismatch with modern GPU-based, learning-driven pipelines and limiting scalability in large-scale scenes. While recent advances in GPU-accelerated bundle adjustment (BA) have demonstrated the potential of parallel sparse optimization, extending these techniques to build a complete global SfM system remains challenging due to unresolved issues in metric scale recovery and numerical robustness. In this paper, we implement a fully GPU-based and PyTorch-compatible global SfM system, named InstantSfM, to integrate seamlessly with modern learning pipelines. InstantSfM embeds metric depth priors directly into both global positioning and BA through a depth-constrained Jacobian structure, thereby resolving scale ambiguity within the optimization framework. To ensure numerical stability, we employ explicit filtering of under-constrained variables for the Jacobian matrix in an optimized GPU-friendly manner. Extensive experiments on diverse datasets demonstrate that InstantSfM achieves state-of-the-art efficiency while maintaining reconstruction accuracy comparable to both established classical pipelines and recent learning-based methods, showing up to ${\sim40\times}$ speedup over COLMAP on large-scale scenes.

---

### Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Authors: Yang Li, Aming Wu, Zihao Zhang, Yahong Han
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13307v2

In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is to setup the exact correlations between the point representations and their base class labels, as well as the representation correlations between the points from base and novel classes. A coarse or statistical correlation learning may lead to the confusion in novel class inference. lf we impose a causal relationship as a strong correlated constraint upon the learning process, the essential point cloud representations that accurately correspond to the classes should be uncovered. To this end, we introduce a structural causal model (SCM) to re-formalize the 3D-NCD problem and propose a new method, i.e., Joint Learning of Causal Representation and Reasoning. Specifically, we first analyze hidden confounders in the base class representations and the causal relationships between the base and novel classes through SCM. We devise a causal representation prototype that eliminates confounders to capture the causal representations of base classes. A graph structure is then used to model the causal relationships between the base classes' causal representation prototypes and the novel class prototypes, enabling causal reasoning from base to novel classes. Extensive experiments and visualization results on 3D and 2D NCD semantic segmentation demonstrate the superiorities of our method.

---

### Automated document processing system for government agencies using DBNET++ and BART models

Authors: Aya Kaysan Bahjat
Published: 2025-10-15
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2510.13303v1

An automatic document classification system is presented that detects textual content in images and classifies documents into four predefined categories (Invoice, Report, Letter, and Form). The system supports both offline images (e.g., files on flash drives, HDDs, microSD) and real-time capture via connected cameras, and is designed to mitigate practical challenges such as variable illumination, arbitrary orientation, curved or partially occluded text, low resolution, and distant text. The pipeline comprises four stages: image capture and preprocessing, text detection (1) using a DBNet++ (Differentiable Binarization Network Plus) detector, and text classification (2) using a BART (Bidirectional and Auto-Regressive Transformers) classifier, all integrated within a user interface implemented in Python with PyQt5. The achieved results by the system for text detection in images were good at about 92.88% through 10 hours on Total-Text dataset that involve high resolution images simulate a various and very difficult challenges. The results indicate the proposed approach is effective for practical, mixed-source document categorization in unconstrained imaging scenarios.

---

### One-shot Style Transfer LLM log-probabilities for Authorship Attribution and Verification

Authors: Pablo Miralles-González, Javier Huertas-Tato, Alejandro Martín, David Camacho
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13302v4

Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, identity linking, and plagiarism detection. Despite the relevance of language modeling to these tasks, the pre-training of modern large language models (LLMs) has been underutilized in authorship attribution and verification. We introduce an unsupervised framework that uses the log-probabilities of an LLM to measure style transferability between two texts. This framework takes advantage of the extensive Causal Language Modeling (CLM) pre-training, one-shot capabilities and scale of LLMs, avoiding explicit supervision. Our methods substantially outperform prompting-based unsupervised baselines in authorship verification at similar model sizes, and is competitive with or improves contrastive baselines in most settings with sufficient model scale. We further observe strong performance across non-English languages. The effectiveness of the proposed framework improves consistently with increasing model scale. In the case of authorship verification, we propose an additional mechanism that increases test-time computation to improve accuracy; enabling flexible trade-offs between computational cost and task performance.

---

### Km-scale dynamical downscaling through conformalized latent diffusion models

Authors: Alessandro Brusaferri, Andrea Ballarino
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13301v1

Dynamical downscaling is crucial for deriving high-resolution meteorological fields from coarse-scale simulations, enabling detailed analysis for critical applications such as weather forecasting and renewable energy modeling. Generative Diffusion models (DMs) have recently emerged as powerful data-driven tools for this task, offering reconstruction fidelity and more scalable sampling supporting uncertainty quantification. However, DMs lack finite-sample guarantees against overconfident predictions, resulting in miscalibrated grid-point-level uncertainty estimates hindering their reliability in operational contexts. In this work, we tackle this issue by augmenting the downscaling pipeline with a conformal prediction framework. Specifically, the DM's samples are post-processed to derive conditional quantile estimates, incorporated into a conformalized quantile regression procedure targeting locally adaptive prediction intervals with finite-sample marginal validity. The proposed approach is evaluated on ERA5 reanalysis data over Italy, downscaled to a 2-km grid. Results demonstrate grid-point-level uncertainty estimates with markedly improved coverage and stable probabilistic scores relative to the DM baseline, highlighting the potential of conformalized generative models for more trustworthy probabilistic downscaling to high-resolution meteorological fields.

---

### Federated Conditional Conformal Prediction via Generative Models

Authors: Rui Xu, Xingyuan Chen, Wenxing Huang, Minxuan Huang, Yun Xie, Weiyan Chen, Sihong Xie
Published: 2025-10-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.13297v2

Conformal Prediction (CP) provides distribution-free uncertainty quantification by constructing prediction sets that guarantee coverage of the true labels. This reliability makes CP valuable for high-stakes federated learning scenarios such as multi-center healthcare. However, standard CP assumes i.i.d. data, which is violated in federated settings where client distributions differ substantially. Existing federated CP methods address this by maintaining marginal coverage on each client, but such guarantees often fail to reflect input-conditional uncertainty. In this work, we propose Federated Conditional Conformal Prediction (Fed-CCP) via generative models, which aims for conditional coverage that adapts to local data heterogeneity. Fed-CCP leverages generative models, such as normalizing flows or diffusion models, to approximate conditional data distributions without requiring the sharing of raw data. This enables each client to locally calibrate conformal scores that reflect its unique uncertainty, while preserving global consistency through federated aggregation. Experiments on real datasets demonstrate that Fed-CCP achieves more adaptive prediction sets.

---

### Cross-modal Consistency Guidance for Robust Emotion Control in Auto-Regressive TTS Models

Authors: Yizhou Peng, Yukun Ma, Chong Zhang, Yi-Wen Chao, Chongjia Ni, Bin Ma, Eng Siong Chng
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13293v4

While Text-to-Speech (TTS) systems enable emotional control via natural-language instructions, expressiveness, naturalness, and speech quality degrade when the target emotion conflicts with the textual semantics. We propose a Cross-modal Consistency Guided Classifier-Free Guidance (CCG-CFG) method with dynamic scales based on the degree of inconsistency between the text emotion and the explicit speech emotion, replacing the dropout condition with the text emotion. We also distill the CCG-CFG guidance signal using a hard-sample mining strategy, improving the TTS model's emotional alignment capability. Evaluations on five emotional corpora and two TTS benchmarks show that our approaches applied to CosyVoice2 achieve up to a 12% absolute improvement in emotion-recognition accuracy and a 10% relative improvement in subjective scores, outperforming baselines including HierSpeech++, Qwen3-TTS, and original CosyVoice2, while preserving intelligibility, naturalness, and high speech quality.

---

### Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems

Authors: Xuxin Cheng, Ke Zeng, Zhiquan Cao, Linyi Dai, Wenxuan Gao, Fei Han, Ai Jian, Feng Hong, Wenxing Hu, Zihe Huang, Dejian Kong, Jia Leng et al.
Published: 2025-10-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.13291v2

Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality data for cold-start training is difficult, hindering self-evolution and raising labor costs. (2) Multi-turn dialogue performance remains suboptimal due to inadequate intent understanding, rule compliance, and solution extraction. (3) Frequent evolution of business rules affects system operability and transferability, constraining low-cost expansion and adaptability. (4) Reliance on a single LLM is insufficient in complex scenarios, where the absence of multi-agent frameworks and effective collaboration undermines process completeness and service quality. (5) The open-domain nature of multi-turn dialogues, lacking unified golden answers, hampers quantitative evaluation and continuous optimization. To address these challenges, we introduce WOWService, an intelligent interaction system tailored for industrial applications. With the integration of LLMs and multi-agent architectures, WOWService enables autonomous task management and collaborative problem-solving. Specifically, WOWService focuses on core modules including data construction, general capability enhancement, business scenario adaptation, multi-agent coordination, and automated evaluation. Currently, WOWService is deployed on the Meituan App, achieving significant gains in key metrics, e.g., User Satisfaction Metric 1 (USM 1) -27.53% and User Satisfaction Metric 2 (USM 2) +25.51%, demonstrating its effectiveness in capturing user needs and advancing personalized service.

---

### To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models

Authors: Anna Hedström, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
Published: 2025-10-15
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.13290v1

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually tuned steering strengths, often resulting in under or oversteering, MERA addresses these limitations by (i) optimising the intervention direction, and (ii) calibrating when, and how much to steer, thereby provably improving performance or abstaining when no confident correction is possible. Experiments across diverse datasets, and LM families demonstrate safe, effective, non-degrading error correction, and that MERA outperforms existing baselines. Moreover, MERA can be applied on top of existing steering techniques to further enhance their performance, establishing it as a general-purpose, and efficient approach to mechanistic activation steering.

---

### In-Distribution Steering: Balancing Control and Coherence in Language Model Generation

Authors: Arthur Vogels, Benjamin Wong, Yann Choho, Annabelle Blangero, Milan Bhan
Published: 2025-10-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.13285v1

Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either insufficient control or unadapted intervention that degrades text plausibility and coherence. We introduce In-Distribution Steering (IDS), a novel method that adapts steering strength based on the input data distribution in representation space. IDS dynamically adjusts interventions according to how far a given input lies within the distribution, enabling adaptive intervention and generation stability during text generation. Experiments demonstrate that IDS achieves strong accuracy on classification tasks while producing coherent text without collapse, making IDS particularly well suited for real-world applications.

---

### Universal Image Restoration Pre-training via Masked Degradation Classification

Authors: JiaKui Hu, Zhengjian Yao, Lujia Jin, Yinghao Chen, Yanye Lu
Published: 2025-10-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.13282v1

This study introduces a Masked Degradation Classification Pre-Training method (MaskDCPT), designed to facilitate the classification of degradation types in input images, leading to comprehensive image restoration pre-training. Unlike conventional pre-training methods, MaskDCPT uses the degradation type of the image as an extremely weak supervision, while simultaneously leveraging the image reconstruction to enhance performance and robustness. MaskDCPT includes an encoder and two decoders: the encoder extracts features from the masked low-quality input image. The classification decoder uses these features to identify the degradation type, whereas the reconstruction decoder aims to reconstruct a corresponding high-quality image. This design allows the pre-training to benefit from both masked image modeling and contrastive learning, resulting in a generalized representation suited for restoration tasks. Benefit from the straightforward yet potent MaskDCPT, the pre-trained encoder can be used to address universal image restoration and achieve outstanding performance. Implementing MaskDCPT significantly improves performance for both convolution neural networks (CNNs) and Transformers, with a minimum increase in PSNR of 3.77 dB in the 5D all-in-one restoration task and a 34.8% reduction in PIQE compared to baseline in real-world degradation scenarios. It also emergences strong generalization to previously unseen degradation types and levels. In addition, we curate and release the UIR-2.5M dataset, which includes 2.5 million paired restoration samples across 19 degradation types and over 200 degradation levels, incorporating both synthetic and real-world data. The dataset, source code, and models are available at https://github.com/MILab-PKU/MaskDCPT.

---

### Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses

Authors: Sungnyun Kim, Kangwook Jang, Sungwoo Cho, Joon Son Chung, Hoirin Kim, Se-Young Yun
Published: 2025-10-15
Categories: eess.AS, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2510.13281v1

This paper introduces a new paradigm for generative error correction (GER) framework in audio-visual speech recognition (AVSR) that reasons over modality-specific evidences directly in the language space. Our framework, DualHyp, empowers a large language model (LLM) to compose independent N-best hypotheses from separate automatic speech recognition (ASR) and visual speech recognition (VSR) models. To maximize the effectiveness of DualHyp, we further introduce RelPrompt, a noise-aware guidance mechanism that provides modality-grounded prompts to the LLM. RelPrompt offers the temporal reliability of each modality stream, guiding the model to dynamically switch its focus between ASR and VSR hypotheses for an accurate correction. Under various corruption scenarios, our framework attains up to 57.7% error rate gain on the LRS2 benchmark over standard ASR baseline, contrary to single-stream GER approaches that achieve only 10% gain. To facilitate research within our DualHyp framework, we release the code and the dataset comprising ASR and VSR hypotheses at https://github.com/sungnyun/dualhyp.

---