# Research Papers — 2025-11 · bundle page 121 of 197 > Full-text markdown of papers #6001–6050 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/121 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/120.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/122.md) ### FactGuard: Event-Centric and Commonsense-Guided Fake News Detection Authors: Jing He, Han Zhang, Yuanhui Xiao, Wei Guo, Shaowen Yao, Renyang Liu Published: 2025-11-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.10281v1 Fake news detection methods based on writing style have achieved remarkable progress. However, as adversaries increasingly imitate the style of authentic news, the effectiveness of such approaches is gradually diminishing. Recent research has explored incorporating large language models (LLMs) to enhance fake news detection. Yet, despite their transformative potential, LLMs remain an untapped goldmine for fake news detection, with their real-world adoption hampered by shallow functionality exploration, ambiguous usability, and prohibitive inference costs. In this paper, we propose a novel fake news detection framework, dubbed FactGuard, that leverages LLMs to extract event-centric content, thereby reducing the impact of writing style on detection performance. Furthermore, our approach introduces a dynamic usability mechanism that identifies contradictions and ambiguous cases in factual reasoning, adaptively incorporating LLM advice to improve decision reliability. To ensure efficiency and practical deployment, we employ knowledge distillation to derive FactGuard-D, enabling the framework to operate effectively in cold-start and resource-constrained scenarios. Comprehensive experiments on two benchmark datasets demonstrate that our approach consistently outperforms existing methods in both robustness and accuracy, effectively addressing the challenges of style sensitivity and LLM usability in fake news detection. --- ### PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning Authors: Yanbei Jiang, Chao Lei, Yihao Ding, Krista Ehinger, Jey Han Lau Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10279v1 Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited: Supervised Fine-Tuning (SFT) relies on costly step-level annotations, while Reinforcement Learning with Verifiable Rewards (RLVR) methods like GRPO provide only sparse, outcome-level feedback, hindering stable optimization. We introduce PROPA (Process-level Reasoning Optimization with interleaved Policy Alignment), a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations. To overcome the cold-start problem, PROPA interleaves GRPO updates with SFT, enabling the model to learn from both successful and failed reasoning trajectories. A Process Reward Model (PRM) is further trained to guide inference-time search, aligning the test-time search with the training signal. Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines. It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art, establishing a strong reasoning and generalization capability for visual reasoning tasks. The code isavailable at: https://github.com/YanbeiJiang/PROPA. --- ### Fixed-Persona SLMs with Modular Memory: Scalable NPC Dialogue on Consumer Hardware Authors: Martin Braas, Lukas Esterle Published: 2025-11-13 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.10277v1 Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, yet their applicability to dialogue systems in computer games remains limited. This limitation arises from their substantial hardware requirements, latency constraints, and the necessity to maintain clearly defined knowledge boundaries within a game setting. In this paper, we propose a modular NPC dialogue system that leverages Small Language Models (SLMs), fine-tuned to encode specific NPC personas and integrated with runtime-swappable memory modules. These memory modules preserve character-specific conversational context and world knowledge, enabling expressive interactions and long-term memory without retraining or model reloading during gameplay. We comprehensively evaluate our system using three open-source SLMs: DistilGPT-2, TinyLlama-1.1B-Chat, and Mistral-7B-Instruct, trained on synthetic persona-aligned data and benchmarked on consumer-grade hardware. While our approach is motivated by applications in gaming, its modular design and persona-driven memory architecture hold significant potential for broader adoption in domains requiring expressive, scalable, and memory-rich conversational agents, such as virtual assistants, customer support bots, or interactive educational systems. --- ### RoboBenchMart: Benchmarking Robots in Retail Environment Authors: Konstantin Soshin, Alexander Krapukhin, Andrei Spiridonov, Gregorii Bukhtuev, Andrey Kuznetsov, Vlad Shakhuro, Denis Shepelev Published: 2025-11-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.10276v2 Most existing robotic manipulation benchmarks focus on tabletop or household scenarios. While these setups have driven impressive progress, it remains unclear whether generalist VLAs that excel there can truly generalize to domains with different geometry, semantics, and workflows. We introduce RoboBenchMart, an open-source simulated benchmark targeting retail dark-store environments, where a mobile manipulator must perform complex manipulation tasks with diverse grocery items. This setting presents significant challenges, including dense object clutter and varied spatial configurations, with items positioned at different heights, depths, and in close proximity. By targeting on the retail domain, our benchmark addresses a setting with strong potential for near-term automation impact. Using generated trajectories, we model a standard, realistic fine-tuning setup for current generalist VLAs and evaluate several state-of-the-art models. We find that they still struggle even on common retail tasks, indicating that these models are not yet truly general across domains. To support further research, we release the RoboBenchMart suite, which includes a procedural store layout generator, a trajectory generation pipeline, evaluation tools, and fine-tuned baseline models. --- ### Bidirectional Bounded-Suboptimal Heuristic Search with Consistent Heuristics Authors: Shahaf S. Shperberg, Natalie Morad, Lior Siag, Ariel Felner, Dor Atzmon Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10272v1 Recent advancements in bidirectional heuristic search have yielded significant theoretical insights and novel algorithms. While most previous work has concentrated on optimal search methods, this paper focuses on bounded-suboptimal bidirectional search, where a bound on the suboptimality of the solution cost is specified. We build upon the state-of-the-art optimal bidirectional search algorithm, BAE*, designed for consistent heuristics, and introduce several variants of BAE* specifically tailored for the bounded-suboptimal context. Through experimental evaluation, we compare the performance of these new variants against other bounded-suboptimal bidirectional algorithms as well as the standard weighted A* algorithm. Our results demonstrate that each algorithm excels under distinct conditions, highlighting the strengths and weaknesses of each approach. --- ### Quality Assurance of LLM-generated Code: Addressing Non-Functional Quality Characteristics Authors: Xin Sun, Daniel Ståhl, Kristian Sandahl, Christoph Kessler Published: 2025-11-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.10271v2 In recent years, large language models have been widely integrated into software engineering workflows, supporting tasks like code generation. While prior evaluations focus on functional correctness, there is still a limited understanding of the non-functional quality characteristics of generated code. Guided by the ISO/IEC 25010 quality model, this study adopts a multi-methods approach comprising three complementary elements: a literature review of 109 papers, two industry workshops with practitioners from multiple organizations, and an empirical analysis of patching real-world software issues using three LLMs. Motivated by insights from both the literature and practitioners, the empirical study examined the quality of generated patches regarding security, maintainability, and performance efficiency, which were identified as critical code-level quality attributes. Our results indicate that existing research primarily emphasizes security, performance efficiency, and maintainability, while other quality attributes are understudied. In contrast, practitioners prioritize maintainability and readability, warning that generated code may accelerate the accumulation of technical debt. The empirical evaluation demonstrates the instability of optimizing NFQCs through prompts in practical software engineering settings. Overall, our findings expose a misalignment between academic focus, industry priorities, and observed model behavior, highlighting the need to integrate quality assurance mechanisms into LLM code generation pipelines to ensure that future generated code not only passes tests but truly passes with quality. --- ### Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention Authors: Zhe Xu, Zhicai Wang, Junkang Wu, Jinda Lu, Xiang Wang Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10268v1 Large Vision-Language Models (LVLMs) often suffer from object hallucination, making erroneous judgments about the presence of objects in images. We propose this primar- ily stems from spurious correlations arising when models strongly associate highly co-occurring objects during train- ing, leading to hallucinated objects influenced by visual con- text. Current benchmarks mainly focus on hallucination de- tection but lack a formal characterization and quantitative evaluation of spurious correlations in LVLMs. To address this, we introduce causal analysis into the object recognition scenario of LVLMs, establishing a Structural Causal Model (SCM). Utilizing the language of causality, we formally de- fine spurious correlations arising from co-occurrence bias. To quantify the influence induced by these spurious correla- tions, we develop Causal-HalBench, a benchmark specifically constructed with counterfactual samples and integrated with comprehensive causal metrics designed to assess model ro- bustness against spurious correlations. Concurrently, we pro- pose an extensible pipeline for the construction of these coun- terfactual samples, leveraging the capabilities of proprietary LVLMs and Text-to-Image (T2I) models for their genera- tion. Our evaluations on mainstream LVLMs using Causal- HalBench demonstrate these models exhibit susceptibility to spurious correlations, albeit to varying extents. --- ### Temporal Properties of Conditional Independence in Dynamic Bayesian Networks Authors: Rajab Aghamov, Christel Baier, Joel Ouaknine, Jakob Piribauer, Mihir Vahanwala, Isa Vialard Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10266v1 Dynamic Bayesian networks (DBNs) are compact graphical representations used to model probabilistic systems where interdependent random variables and their distributions evolve over time. In this paper, we study the verification of the evolution of conditional-independence (CI) propositions against temporal logic specifications. To this end, we consider two specification formalisms over CI propositions: linear temporal logic (LTL), and non-deterministic Büchi automata (NBAs). This problem has two variants. Stochastic CI properties take the given concrete probability distributions into account, while structural CI properties are viewed purely in terms of the graphical structure of the DBN. We show that deciding if a stochastic CI proposition eventually holds is at least as hard as the Skolem problem for linear recurrence sequences, a long-standing open problem in number theory. On the other hand, we show that verifying the evolution of structural CI propositions against LTL and NBA specifications is in PSPACE, and is NP- and coNP-hard. We also identify natural restrictions on the graphical structure of DBNs that make the verification of structural CI properties tractable. --- ### Beyond Single-Step Updates: Reinforcement Learning of Heuristics with Limited-Horizon Search Authors: Gal Hadar, Forest Agostinelli, Shahaf S. Shperberg Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10264v1 Many sequential decision-making problems can be formulated as shortest-path problems, where the objective is to reach a goal state from a given starting state. Heuristic search is a standard approach for solving such problems, relying on a heuristic function to estimate the cost to the goal from any given state. Recent approaches leverage reinforcement learning to learn heuristics by applying deep approximate value iteration. These methods typically rely on single-step Bellman updates, where the heuristic of a state is updated based on its best neighbor and the corresponding edge cost. This work proposes a generalized approach that enhances both state sampling and heuristic updates by performing limited-horizon searches and updating each state's heuristic based on the shortest path to the search frontier, incorporating both edge costs and the heuristic values of frontier states. --- ### MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models Authors: He Zhang, Wenqian Cui, Haoning Xu, Xiaohui Li, Lei Zhu, Haoli Bai, Shaohua Ma, Irwin King Published: 2025-11-13 Categories: cs.CL, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2511.10262v3 Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions, neglecting the complexities of multi-round communication. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference. Also, existing benchmarks often focus solely on evaluating conversational features, neglecting other critical aspects. To address these gaps, we introduce MTR-DuplexBench, a novel benchmark designed for a comprehensive multi-round evaluation of FD-SLMs. MTR-DuplexBench not only segments continuous full-duplex dialogues into discrete turns for turn-by-turn assessment but also incorporates various evaluation aspects, including conversational features, dialogue quality, instruction following, and safety. Experimental results reveal that current FD-SLMs face difficulties in maintaining consistent performance across multiple rounds and evaluation dimensions, highlighting the necessity and effectiveness of our benchmark. Code and data are available at: https://github.com/ZhangHe0918/MTR-DuplexBench --- ### H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification Authors: Yongji Zhang, Siqi Li, Kuiyang Huang, Yue Gao, Yu Jiang Published: 2025-11-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10260v2 Fine-Grained Visual Classification (FGVC) remains a challenging task due to subtle inter-class differences and large intra-class variations. Existing approaches typically rely on feature-selection mechanisms or region-proposal strategies to localize discriminative regions for semantic analysis. However, these methods often fail to capture discriminative cues comprehensively while introducing substantial category-agnostic redundancy. To address these limitations, we propose H3Former, a novel token-to-region framework that leverages high-order semantic relations to aggregate local fine-grained representations with structured region-level modeling. Specifically, we propose the Semantic-Aware Aggregation Module (SAAM), which exploits multi-scale contextual cues to dynamically construct a weighted hypergraph among tokens. By applying hypergraph convolution, SAAM captures high-order semantic dependencies and progressively aggregates token features into compact region-level representations. Furthermore, we introduce the Hyperbolic Hierarchical Contrastive Loss (HHCL), which enforces hierarchical semantic constraints in a non-Euclidean embedding space. The HHCL enhances inter-class separability and intra-class consistency while preserving the intrinsic hierarchical relationships among fine-grained categories. Comprehensive experiments conducted on four standard FGVC benchmarks validate the superiority of our H3Former framework. --- ### Workload Schedulers -- Genesis, Algorithms and Differences Authors: Leszek Sliwko, Vladimir Getov Published: 2025-11-13 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2511.10258v1 This paper presents a novel approach to categorization of modern workload schedulers. We provide descriptions of three classes of schedulers: Operating Systems Process Schedulers, Cluster Systems Jobs Schedulers and Big Data Schedulers. We describe their evolution from early adoptions to modern implementations, considering both the use and features of algorithms. In summary, we discuss differences between all presented classes of schedulers and discuss their chronological development. In conclusion we highlight similarities in the focus of scheduling strategies design, applicable to both local and distributed systems. --- ### Unitho: A Unified Multi-Task Framework for Computational Lithography Authors: Qian Jin, Yumeng Liu, Yuqi Jiang, Qi Sun, Cheng Zhuo Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10255v2 Reliable, generalizable data foundations are critical for enabling large-scale models in computational lithography. However, essential tasks-mask generation, rule violation detection, and layout optimization-are often handled in isolation, hindered by scarce datasets and limited modeling approaches. To address these challenges, we introduce Unitho, a unified multi-task large vision model built upon the Transformer architecture. Trained on a large-scale industrial lithography simulation dataset with hundreds of thousands of cases, Unitho supports end-to-end mask generation, lithography simulation, and rule violation detection. By enabling agile and high-fidelity lithography simulation, Unitho further facilitates the construction of robust data foundations for intelligent EDA. Experimental results validate its effectiveness and generalizability, with performance substantially surpassing academic baselines. --- ### Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis Authors: Jiulong Wu, Yucheng Shen, Lingyong Yan, Haixin Sun, Deguo Xia, Jizhou Huang, Min Cao Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10254v2 Facial Emotion Analysis (FEA) extends traditional facial emotion recognition by incorporating explainable, fine-grained reasoning. The task integrates three subtasks: emotion recognition, facial Action Unit (AU) recognition, and AU-based emotion reasoning to model affective states jointly. While recent approaches leverage Vision-Language Models (VLMs) and achieve promising results, they face two critical limitations: (1) hallucinated reasoning, where VLMs generate plausible but inaccurate explanations due to insufficient emotion-specific knowledge; and (2) misalignment between emotion reasoning and recognition, caused by fragmented connections between observed facial features and final labels. We propose Facial-R1, a three-stage alignment framework that effectively addresses both challenges with minimal supervision. First, we employ instruction fine-tuning to establish basic emotional reasoning capability. Second, we introduce reinforcement training guided by emotion and AU labels as reward signals, which explicitly aligns the generated reasoning process with the predicted emotion. Third, we design a data synthesis pipeline that iteratively leverages the prior stages to expand the training dataset, enabling scalable self-improvement of the model. Built upon this framework, we introduce FEA-20K, a benchmark dataset comprising 17,737 training and 1,688 test samples with fine-grained emotion analysis annotations. Extensive experiments across eight standard benchmarks demonstrate that Facial-R1 achieves state-of-the-art performance in FEA, with strong generalization and robust interpretability. --- ### Heuristic Transformer: Belief Augmented In-Context Reinforcement Learning Authors: Oliver Dippel, Alexei Lisitsa, Bei Peng Published: 2025-11-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.10251v1 Transformers have demonstrated exceptional in-context learning (ICL) capabilities, enabling applications across natural language processing, computer vision, and sequential decision-making. In reinforcement learning, ICL reframes learning as a supervised problem, facilitating task adaptation without parameter updates. Building on prior work leveraging transformers for sequential decision-making, we propose Heuristic Transformer (HT), an in-context reinforcement learning (ICRL) approach that augments the in-context dataset with a belief distribution over rewards to achieve better decision-making. Using a variational auto-encoder (VAE), a low-dimensional stochastic variable is learned to represent the posterior distribution over rewards, which is incorporated alongside an in-context dataset and query states as prompt to the transformer policy. We assess the performance of HT across the Darkroom, Miniworld, and MuJoCo environments, showing that it consistently surpasses comparable baselines in terms of both effectiveness and generalization. Our method presents a promising direction to bridge the gap between belief-based augmentations and transformer-based decision-making. --- ### FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment Authors: Yongji Zhang, Siqi Li, Yue Gao, Yu Jiang Published: 2025-11-13 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.10250v1 Action Quality Assessment (AQA) aims to evaluate and score sports actions, which has attracted widespread interest in recent years. Existing AQA methods primarily predict scores based on features extracted from the entire video, resulting in limited interpretability and reliability. Meanwhile, existing AQA datasets also lack fine-grained annotations for action scores, especially for deduction items and sub-score annotations. In this paper, we construct the first AQA dataset containing fine-grained sub-score and deduction annotations for aerial skiing, which will be released as a new benchmark. For the technical challenges, we propose a novel AQA method, named JudgeMind, which significantly enhances performance and reliability by simulating the judgment and scoring mindset of professional referees. Our method segments the input action video into different stages and scores each stage to enhance accuracy. Then, we propose a stage-aware feature enhancement and fusion module to boost the perception of stage-specific key regions and enhance the robustness to visual changes caused by frequent camera viewpoints switching. In addition, we propose a knowledge-based grade-aware decoder to incorporate possible deduction items as prior knowledge to predict more accurate and reliable scores. Experimental results demonstrate that our method achieves state-of-the-art performance. --- ### Robustness and Imperceptibility Analysis of Hybrid Spatial-Frequency Domain Image Watermarking Authors: Rizal Khoirul Anam Published: 2025-11-13 Categories: cs.MM, cs.AI, eess.IV arXiv: https://arxiv.org/abs/2511.10245v1 The proliferation of digital media necessitates robust methods for copyright protection and content authentication. This paper presents a comprehensive comparative study of digital image watermarking techniques implemented using the spatial domain (Least Significant Bit - LSB), the frequency domain (Discrete Fourier Transform - DFT), and a novel hybrid (LSB+DFT) approach. The core objective is to evaluate the trade-offs between imperceptibility (measured by Peak Signal-to-Noise Ratio - PSNR) and robustness (measured by Normalized Correlation - NC and Bit Error Rate - BER). We implemented these three techniques within a unified MATLAB-based experimental framework. The watermarked images were subjected to a battery of common image processing attacks, including JPEG compression, Gaussian noise, and salt-and-pepper noise, at varying intensities. Experimental results generated from standard image datasets (USC-SIPI) demonstrate that while LSB provides superior imperceptibility, it is extremely fragile. The DFT method offers significant robustness at the cost of visual quality. The proposed hybrid LSB+DFT technique, which leverages redundant embedding and a fallback extraction mechanism, is shown to provide the optimal balance, maintaining high visual fidelity while exhibiting superior resilience to all tested attacks. --- ### PepTriX: A Framework for Explainable Peptide Analysis through Protein Language Models Authors: Vincent Schilling, Akshat Dubey, Georges Hattab Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10244v1 Peptide classification tasks, such as predicting toxicity and HIV inhibition, are fundamental to bioinformatics and drug discovery. Traditional approaches rely heavily on handcrafted encodings of one-dimensional (1D) peptide sequences, which can limit generalizability across tasks and datasets. Recently, protein language models (PLMs), such as ESM-2 and ESMFold, have demonstrated strong predictive performance. However, they face two critical challenges. First, fine-tuning is computationally costly. Second, their complex latent representations hinder interpretability for domain experts. Additionally, many frameworks have been developed for specific types of peptide classification, lacking generalization. These limitations restrict the ability to connect model predictions to biologically relevant motifs and structural properties. To address these limitations, we present PepTriX, a novel framework that integrates one dimensional (1D) sequence embeddings and three-dimensional (3D) structural features via a graph attention network enhanced with contrastive training and cross-modal co-attention. PepTriX automatically adapts to diverse datasets, producing task-specific peptide vectors while retaining biological plausibility. After evaluation by domain experts, we found that PepTriX performs remarkably well across multiple peptide classification tasks and provides interpretable insights into the structural and biophysical motifs that drive predictions. Thus, PepTriX offers both predictive robustness and interpretable validation, bridging the gap between performance-driven peptide-level models (PLMs) and domain-level understanding in peptide research. --- ### TubeRMC: Tube-conditioned Reconstruction with Mutual Constraints for Weakly-supervised Spatio-Temporal Video Grounding Authors: Jinxuan Li, Yi Zhang, Jian-Fang Hu, Chaolei Tan, Tianming Liang, Beihao Xia Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10241v2 Spatio-Temporal Video Grounding (STVG) aims to localize a spatio-temporal tube that corresponds to a given language query in an untrimmed video. This is a challenging task since it involves complex vision-language understanding and spatiotemporal reasoning. Recent works have explored weakly-supervised setting in STVG to eliminate reliance on fine-grained annotations like bounding boxes or temporal stamps. However, they typically follow a simple late-fusion manner, which generates tubes independent of the text description, often resulting in failed target identification and inconsistent target tracking. To address this limitation, we propose a Tube-conditioned Reconstruction with Mutual Constraints (\textbf{TubeRMC}) framework that generates text-conditioned candidate tubes with pre-trained visual grounding models and further refine them via tube-conditioned reconstruction with spatio-temporal constraints. Specifically, we design three reconstruction strategies from temporal, spatial, and spatio-temporal perspectives to comprehensively capture rich tube-text correspondences. Each strategy is equipped with a Tube-conditioned Reconstructor, utilizing spatio-temporal tubes as condition to reconstruct the key clues in the query. We further introduce mutual constraints between spatial and temporal proposals to enhance their quality for reconstruction. TubeRMC outperforms existing methods on two public benchmarks VidSTG and HCSTVG. Further visualization shows that TubeRMC effectively mitigates both target identification errors and inconsistent tracking. --- ### ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs Authors: Minbae Park, Hyemin Yang, Jeonghyun Kim, Kunsoo Park, Hyunjoon Kim Published: 2025-11-13 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.10240v2 Large Language Models (LLMs) demonstrate strong reasoning capabilities but struggle with hallucinations and limited transparency. Recently, KG-enhanced LLMs that integrate knowledge graphs (KGs) have been shown to improve reasoning performance, particularly for complex, knowledge-intensive tasks. However, these methods still face significant challenges, including inaccurate retrieval and reasoning failures, often exacerbated by long input contexts that obscure relevant information or by context constructions that struggle to capture the richer logical directions required by different question types. Furthermore, many of these approaches rely on LLMs to directly retrieve evidence from KGs, and to self-assess the sufficiency of this evidence, which often results in premature or incorrect reasoning. To address the retrieval and reasoning failures, we propose ProgRAG, a multi-hop knowledge graph question answering (KGQA) framework that decomposes complex questions into sub-questions, and progressively extends partial reasoning paths by answering each sub-question. At each step, external retrievers gather candidate evidence, which is then refined through uncertainty-aware pruning by the LLM. Finally, the context for LLM reasoning is optimized by organizing and rearranging the partial reasoning paths obtained from the sub-question answers. Experiments on three well-known datasets demonstrate that ProgRAG outperforms existing baselines in multi-hop KGQA, offering improved reliability and reasoning quality. --- ### Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners Authors: Daniel Herbst, Lea Karbevska, Divyanshu Kumar, Akanksha Ahuja, Fatemeh Gholamzadeh Nasrabadi, Fabrizio Frasca Published: 2025-11-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.10234v3 While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operating on sequential graph serializations, LLMs can produce different outputs under node reindexing, edge reordering, or formatting changes, raising robustness concerns. We systematically analyze these effects, studying how fine-tuning impacts encoding sensitivity as well generalization on unseen tasks. We propose a principled decomposition of graph serializations into node labeling, edge encoding, and syntax, and evaluate LLM robustness to variations of each of these factors on a comprehensive benchmarking suite. We also contribute a novel set of spectral tasks to further assess generalization abilities of fine-tuned reasoners. Results show that larger (non-fine-tuned) models are more robust. Fine-tuning reduces sensitivity to node relabeling but may increase it to variations in structure and format, while it does not consistently improve performance on unseen tasks. --- ### Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation Authors: Jianghan Zhu, Yaoxin Wu, Zhuoyi Lin, Zhengyuan Zhang, Haiyan Yin, Zhiguang Cao, Senthilnath Jayavelu, Xiaoli Li Published: 2025-11-13 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2511.10233v2 Recent advances in Neural Combinatorial Optimization (NCO) methods have significantly improved the capability of neural solvers to handle synthetic routing instances. Nonetheless, existing neural solvers typically struggle to generalize effectively from synthetic, uniformly-distributed training data to real-world VRP scenarios, including widely recognized benchmark instances from TSPLib and CVRPLib. To bridge this generalization gap, we present Evolutionary Realistic Instance Synthesis (EvoReal), which leverages an evolutionary module guided by large language models (LLMs) to generate synthetic instances characterized by diverse and realistic structural patterns. Specifically, the evolutionary module produces synthetic instances whose structural attributes statistically mimics those observed in authentic real-world instances. Subsequently, pre-trained NCO models are progressively refined, firstly aligning them with these structurally enriched synthetic distributions and then further adapting them through direct fine-tuning on actual benchmark instances. Extensive experimental evaluations demonstrate that EvoReal markedly improves the generalization capabilities of state-of-the-art neural solvers, yielding a notable reduced performance gap compared to the optimal solutions on the TSPLib (1.05%) and CVRPLib (2.71%) benchmarks across a broad spectrum of problem scales. --- ### VocalNet-M2: Advancing Low-Latency Spoken Language Modeling via Integrated Multi-Codebook Tokenization and Multi-Token Prediction Authors: Yuhao Wang, Ziyang Cheng, Heyang Liu, Ronghua Wu, Qunshan Gu, Yanfeng Wang, Yu Wang Published: 2025-11-13 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2511.10232v1 Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex flow-matching models for speech synthesis. To overcome this, we introduce VocalNet-M2, a novel low-latency SLM that integrates a multi-codebook tokenizer and a multi-token prediction (MTP) strategy. Our model directly generates multi-codebook speech tokens, thus eliminating the need for a latency-inducing flow-matching model. Furthermore, our MTP strategy enhances generation efficiency and improves overall performance. Extensive experiments demonstrate that VocalNet-M2 achieves a substantial reduction in first chunk latency (from approximately 725ms to 350ms) while maintaining competitive performance across mainstream SLMs. This work also provides a comprehensive comparison of single-codebook and multi-codebook strategies, offering valuable insights for developing efficient and high-performance SLMs for real-time interactive applications. --- ### LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning Authors: Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin Published: 2025-11-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10229v1 Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs), but the resulting multilingual capability remains highly sensitive to the composition and selection of the training data. Existing selection methods, often based on features like text quality, diversity, or task relevance, typically overlook the intrinsic linguistic structure of multilingual data. In this paper, we propose LangGPS, a lightweight two-stage pre-selection framework guided by language separability which quantifies how well samples in different languages can be distinguished in the model's representation space. LangGPS first filters training data based on separability scores and then refines the subset using existing selection methods. Extensive experiments across six benchmarks and 22 languages demonstrate that applying LangGPS on top of existing selection methods improves their effectiveness and generalizability in multilingual training, especially for understanding tasks and low-resource languages. Further analysis reveals that highly separable samples facilitate the formation of clearer language boundaries and support faster adaptation, while low-separability samples tend to function as bridges for cross-lingual alignment. Besides, we also find that language separability can serve as an effective signal for multilingual curriculum learning, where interleaving samples with diverse separability levels yields stable and generalizable gains. Together, we hope our work offers a new perspective on data utility in multilingual contexts and support the development of more linguistically informed LLMs. --- ### FedCure: Mitigating Participation Bias in Semi-Asynchronous Federated Learning with Non-IID Data Authors: Yue Chen, Jianfeng Lu, Shuqing Cao, Wei Wang, Gang Li, Guanghui Wen Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10227v1 While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated by non-IID data distributions. More importantly, hierarchical architecture shifts participation from individual clients to client groups, thereby further intensifying this issue. Despite notable advancements in SAFL research, most existing works still focus on conventional cloud-end architectures while largely overlooking the critical impact of non-IID data on scheduling across the cloud-edge-client hierarchy. To tackle these challenges, we propose FedCure, an innovative semi-asynchronous Federated learning framework that leverages coalition construction and participation-aware scheduling to mitigate participation bias with non-IID data. Specifically, FedCure operates through three key rules: (1) a preference rule that optimizes coalition formation by maximizing collective benefits and establishing theoretically stable partitions to reduce non-IID-induced performance degradation; (2) a scheduling rule that integrates the virtual queue technique with Bayesian-estimated coalition dynamics, mitigating efficiency loss while ensuring mean rate stability; and (3) a resource allocation rule that enhances computational efficiency by optimizing client CPU frequencies based on estimated coalition dynamics while satisfying delay requirements. Comprehensive experiments on four real-world datasets demonstrate that FedCure improves accuracy by up to 5.1x compared with four state-of-the-art baselines, while significantly enhancing efficiency with the lowest coefficient of variation 0.0223 for per-round latency and maintaining long-term balance across diverse scenarios. --- ### Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard Authors: Yudong Yang, Xuezhen Zhang, Zhifeng Han, Siyin Wang, Jimin Zhuang, Zengrui Jin, Jing Shao, Guangzhi Sun, Chao Zhang Published: 2025-11-13 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.10222v3 Recent progress in LLMs has enabled understanding of audio signals, but has also exposed new safety risks arising from complex audio inputs that are inadequately handled by current safeguards. We introduce SACRED-Bench (Speech-Audio Composition for RED-teaming) to evaluate the robustness of LLMs under complex audio-based attacks. Unlike existing perturbation-based methods that rely on noise optimization or white-box access, SACRED-Bench exploits speech-audio composition to enable effective black-box attacks. SACRED-Bench adopts three composition mechanisms: (a) overlap of harmful and benign speech, (b) mixture of benign speech with harmful non-speech audio, and (c) multi-speaker dialogue. These mechanisms focus on evaluating safety in settings where benign and harmful intents co-occur within a single auditory scene. Moreover, questions in SACRED-Bench are designed to implicitly refer to content in the audio, such that no explicit harmful information appears in the text prompt alone. Experiments demonstrate that even Gemini 2.5 Pro, a state-of-the-art proprietary LLM with safety guardrails fully enabled, still exhibits a 66% attack success rate. To bridge this gap, we propose SALMONN-Guard, the first guard model that jointly inspects speech, audio, and text for safety judgments, reducing the attack success rate to 20%. Our results highlight the need for audio-aware defenses to ensure the safety of multimodal LLMs. The dataset and SALMONN-Guard checkpoints can be found at https://huggingface.co/datasets/tsinghua-ee/SACRED-Bench. --- ### MTP: Exploring Multimodal Urban Traffic Profiling with Modality Augmentation and Spectrum Fusion Authors: Haolong Xiang, Peisi Wang, Xiaolong Xu, Kun Yi, Xuyun Zhang, Quanzheng Sheng, Amin Beheshti, Wei Fan Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10218v2 With rapid urbanization in the modern era, traffic signals from various sensors have been playing a significant role in monitoring the states of cities, which provides a strong foundation in ensuring safe travel, reducing traffic congestion and optimizing urban mobility. Most existing methods for traffic signal modeling often rely on the original data modality, i.e., numerical direct readings from the sensors in cities. However, this unimodal approach overlooks the semantic information existing in multimodal heterogeneous urban data in different perspectives, which hinders a comprehensive understanding of traffic signals and limits the accurate prediction of complex traffic dynamics. To address this problem, we propose a novel Multimodal framework, MTP, for urban Traffic Profiling, which learns multimodal features through numeric, visual, and textual perspectives. The three branches drive for a multimodal perspective of urban traffic signal learning in the frequency domain, while the frequency learning strategies delicately refine the information for extraction. Specifically, we first conduct the visual augmentation for the traffic signals, which transforms the original modality into frequency images and periodicity images for visual learning. Also, we augment descriptive texts for the traffic signals based on the specific topic, background information and item description for textual learning. To complement the numeric information, we utilize frequency multilayer perceptrons for learning on the original modality. We design a hierarchical contrastive learning on the three branches to fuse the spectrum of three modalities. Finally, extensive experiments on six real-world datasets demonstrate superior performance compared with the state-of-the-art approaches. --- ### Persona-Aware Alignment Framework for Personalized Dialogue Generation Authors: Guanrong Li, Xinyu Liu, Zhen Wu, Xinyu Dai Published: 2025-11-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10215v1 Personalized dialogue generation aims to leverage persona profiles and dialogue history to generate persona-relevant and consistent responses. Mainstream models typically rely on token-level language model training with persona dialogue data, such as Next Token Prediction, to implicitly achieve personalization, making these methods tend to neglect the given personas and generate generic responses. To address this issue, we propose a novel Persona-Aware Alignment Framework (PAL), which directly treats persona alignment as the training objective of dialogue generation. Specifically, PAL employs a two-stage training method including Persona-aware Learning and Persona Alignment, equipped with an easy-to-use inference strategy Select then Generate, to improve persona sensitivity and generate more persona-relevant responses at the semantics level. Through extensive experiments, we demonstrate that our framework outperforms many state-of-the-art personalized dialogue methods and large language models. --- ### Out-of-Context Misinformation Detection via Variational Domain-Invariant Learning with Test-Time Training Authors: Xi Yang, Han Zhang, Zhijian Lin, Yibiao Hu, Hong Han Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10213v2 Out-of-context misinformation (OOC) is a low-cost form of misinformation in news reports, which refers to place authentic images into out-of-context or fabricated image-text pairings. This problem has attracted significant attention from researchers in recent years. Current methods focus on assessing image-text consistency or generating explanations. However, these approaches assume that the training and test data are drawn from the same distribution. When encountering novel news domains, models tend to perform poorly due to the lack of prior knowledge. To address this challenge, we propose \textbf{VDT} to enhance the domain adaptation capability for OOC misinformation detection by learning domain-invariant features and test-time training mechanisms. Domain-Invariant Variational Align module is employed to jointly encodes source and target domain data to learn a separable distributional space domain-invariant features. For preserving semantic integrity, we utilize domain consistency constraint module to reconstruct the source and target domain latent distribution. During testing phase, we adopt the test-time training strategy and confidence-variance filtering module to dynamically updating the VAE encoder and classifier, facilitating the model's adaptation to the target domain distribution. Extensive experiments conducted on the benchmark dataset NewsCLIPpings demonstrate that our method outperforms state-of-the-art baselines under most domain adaptation settings. --- ### Next-Frame Feature Prediction for Multimodal Deepfake Detection and Temporal Localization Authors: Ashutosh Anshul, Shreyas Gopal, Deepu Rajan, Eng Siong Chng Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10212v1 Recent multimodal deepfake detection methods designed for generalization conjecture that single-stage supervised training struggles to generalize across unseen manipulations and datasets. However, such approaches that target generalization require pretraining over real samples. Additionally, these methods primarily focus on detecting audio-visual inconsistencies and may overlook intra-modal artifacts causing them to fail against manipulations that preserve audio-visual alignment. To address these limitations, we propose a single-stage training framework that enhances generalization by incorporating next-frame prediction for both uni-modal and cross-modal features. Additionally, we introduce a window-level attention mechanism to capture discrepancies between predicted and actual frames, enabling the model to detect local artifacts around every frame, which is crucial for accurately classifying fully manipulated videos and effectively localizing deepfake segments in partially spoofed samples. Our model, evaluated on multiple benchmark datasets, demonstrates strong generalization and precise temporal localization. --- ### HeatV2X: Scalable Heterogeneous Collaborative Perception via Efficient Alignment and Interaction Authors: Yueran Zhao, Zhang Zhang, Chao Sun, Tianze Wang, Chao Yue, Nuoran Li Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10211v1 Vehicle-to-Everything (V2X) collaborative perception extends sensing beyond single vehicle limits through transmission. However, as more agents participate, existing frameworks face two key challenges: (1) the participating agents are inherently multi-modal and heterogeneous, and (2) the collaborative framework must be scalable to accommodate new agents. The former requires effective cross-agent feature alignment to mitigate heterogeneity loss, while the latter renders full-parameter training impractical, highlighting the importance of scalable adaptation. To address these issues, we propose Heterogeneous Adaptation (HeatV2X), a scalable collaborative framework. We first train a high-performance agent based on heterogeneous graph attention as the foundation for collaborative learning. Then, we design Local Heterogeneous Fine-Tuning and Global Collaborative Fine-Tuning to achieve effective alignment and interaction among heterogeneous agents. The former efficiently extracts modality-specific differences using Hetero-Aware Adapters, while the latter employs the Multi-Cognitive Adapter to enhance cross-agent collaboration and fully exploit the fusion potential. These designs enable substantial performance improvement of the collaborative framework with minimal training cost. We evaluate our approach on the OPV2V-H and DAIR-V2X datasets. Experimental results demonstrate that our method achieves superior perception performance with significantly reduced training overhead, outperforming existing state-of-the-art approaches. Our implementation will be released soon. --- ### Advanced Black-Box Tuning of Large Language Models with Limited API Calls Authors: Zhikang Xie, Weilin Wan, Peizhu Gong, Weizhong Zhang, Cheng Jin Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10210v3 Black-box tuning is an emerging paradigm for adapting large language models (LLMs) to better achieve desired behaviors, particularly when direct access to model parameters is unavailable. Current strategies, however, often present a dilemma of suboptimal extremes: either separately train a small proxy model and then use it to shift the predictions of the foundation model, offering notable efficiency but often yielding limited improvement; or making API calls in each tuning iteration to the foundation model, which entails prohibitive computational costs. Therefore, we propose a novel advanced black-box tuning method for LLMs with limited API calls. Our core strategy involves training a Gaussian Process (GP) surrogate model with "LogitMap Pairs" derived from querying the foundation model on a minimal but highly informative training subset. This surrogate can approximate the outputs of the foundation model to guide the training of the proxy model, thereby effectively reducing the need for direct queries to the foundation model. Extensive experiments verify that our approach elevates pre-trained language model accuracy from 55.92% to 86.85%, reducing the frequency of API queries to merely 1.38%. This significantly outperforms offline approaches that operate entirely without API access. Notably, our method also achieves comparable or superior accuracy to query-intensive approaches, while significantly reducing API costs. This offers a robust and high-efficiency paradigm for language model adaptation. --- ### LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures Authors: Wenzhe He, Xiaojun Chen, Ruiqi Wang, Ruihui Li, Huilong Pi, Jiapeng Zhang, Zhuo Tang, Kenli Li Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10209v2 3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models for high-fidelity reconstruction. However, their multi-step iterative sampling incurs significant computational overhead, limiting its real-time applicability. To address this, we propose LiNeXt-a lightweight, non-diffusion network optimized for rapid and accurate point cloud completion. Specifically, LiNeXt first applies the Noise-to-Coarse (N2C) Module to denoise the input noisy point cloud in a single pass, thereby obviating the multi-step iterative sampling of diffusion-based methods. The Refine Module then takes the coarse point cloud and its intermediate features from the N2C Module to perform more precise refinement, further enhancing structural completeness. Furthermore, we observe that LiDAR point clouds exhibit a distance-dependent spatial distribution, being densely sampled at proximal ranges and sparsely sampled at distal ranges. Accordingly, we propose the Distance-aware Selected Repeat strategy to generate a more uniformly distributed noisy point cloud. On the SemanticKITTI dataset, LiNeXt achieves a 199.8x speedup in inference, reduces Chamfer Distance by 50.7%, and uses only 6.1% of the parameters compared with LiDiff. These results demonstrate the superior efficiency and effectiveness of LiNeXt for real-time scene completion. --- ### Fractional neural attention for efficient multiscale sequence processing Authors: Cheng Kevin Qu, Andrew Ly, Pulin Gong Published: 2025-11-13 Categories: cs.LG, cs.AI, math.DS, math.PR, physics.bio-ph arXiv: https://arxiv.org/abs/2511.10208v1 Attention mechanisms underpin the computational power of Transformer models, which have achieved remarkable success across diverse domains. Yet understanding and extending the principles underlying self-attention remains a key challenge for advancing artificial intelligence. Drawing inspiration from the multiscale dynamics of biological attention and from dynamical systems theory, we introduce Fractional Neural Attention (FNA), a principled, neuroscience-inspired framework for multiscale information processing. FNA models token interactions through Lévy diffusion governed by the fractional Laplacian, intrinsically realizing simultaneous short- and long-range dependencies across multiple scales. This mechanism yields greater expressivity and faster information mixing, advancing the foundational capacity of Transformers. Theoretically, we show that FNA's dynamics are governed by the fractional diffusion equation, and that the resulting attention networks exhibit larger spectral gaps and shorter path lengths -- mechanistic signatures of enhanced computational efficiency. Empirically, FNA achieves competitive text-classification performance even with a single layer and a single head; it also improves performance in image processing and neural machine translation. Finally, the diffusion map algorithm from geometric harmonics enables dimensionality reduction of FNA weights while preserving the intrinsic structure of embeddings and hidden states. Together, these results establish FNA as a principled mechanism connecting self-attention, stochastic dynamics, and geometry, providing an interpretable, biologically grounded foundation for powerful, neuroscience-inspired AI. --- ### VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction Authors: Stephane Da Silva Martins, Emanuel Aldea, Sylvie Le Hégarat-Mascle Published: 2025-11-13 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.10203v1 Multi-agent trajectory prediction is crucial for autonomous systems operating in dense, interactive environments. Existing methods often fail to jointly capture agents' long-term goals and their fine-grained social interactions, which leads to unrealistic multi-agent futures. We propose VISTA, a recursive goal-conditioned transformer for multi-agent trajectory forecasting. VISTA combines (i) a cross-attention fusion module that integrates long-horizon intent with past motion, (ii) a social-token attention mechanism for flexible interaction modeling across agents, and (iii) pairwise attention maps that make social influence patterns interpretable at inference time. Our model turns single-agent goal-conditioned prediction into a coherent multi-agent forecasting framework. Beyond standard displacement metrics, we evaluate trajectory collision rates as a measure of joint realism. On the high-density MADRAS benchmark and on SDD, VISTA achieves state-of-the-art accuracy and substantially fewer collisions. On MADRAS, it reduces the average collision rate of strong baselines from 2.14 to 0.03 percent, and on SDD it attains zero collisions while improving ADE, FDE, and minFDE. These results show that VISTA generates socially compliant, goal-aware, and interpretable trajectories, making it promising for safety-critical autonomous systems. --- ### EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models Authors: Junquan Huang, Haotian Wu, Yubo Gao, Yibo Yan, Junyan Zhang, Yonghua Hei, Song Dai, Jie Zhang, Puay Siew Tan, Xuming Hu Published: 2025-11-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10201v1 Large language models (LLMs) with Chain-of-Thought (CoT) prompting achieve strong reasoning but often produce unnecessarily long explanations, increasing cost and sometimes reducing accuracy. Fair comparison of efficiency-oriented approaches is hindered by fragmented evaluation practices. We introduce EffiReason-Bench, a unified benchmark for rigorous cross-paradigm evaluation of efficient reasoning methods across three categories: Reasoning Blueprints, Dynamic Execution, and Post-hoc Refinement. To enable step-by-step evaluation, we construct verified CoT annotations for CommonsenseQA and LogiQA via a pipeline that enforces standardized reasoning structures, comprehensive option-wise analysis, and human verification. We evaluate 7 methods across 6 open-source LLMs (1B-70B) on 4 datasets spanning mathematics, commonsense, and logic, and propose the E3-Score, a principled metric inspired by economic trade-off modeling that provides smooth, stable evaluation without discontinuities or heavy reliance on heuristics. Experiments show that no single method universally dominates; optimal strategies depend on backbone scale, task complexity, and architecture. --- ### Beyond MSE: Ordinal Cross-Entropy for Probabilistic Time Series Forecasting Authors: Jieting Wang, Huimei Shi, Feijiang Li, Xiaolei Shang Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10200v2 Time series forecasting is an important task that involves analyzing temporal dependencies and underlying patterns (such as trends, cyclicality, and seasonality) in historical data to predict future values or trends. Current deep learning-based forecasting models primarily employ Mean Squared Error (MSE) loss functions for regression modeling. Despite enabling direct value prediction, this method offers no uncertainty estimation and exhibits poor outlier robustness. To address these limitations, we propose OCE-TS, a novel ordinal classification approach for time series forecasting that replaces MSE with Ordinal Cross-Entropy (OCE) loss, preserving prediction order while quantifying uncertainty through probability output. Specifically, OCE-TS begins by discretizing observed values into ordered intervals and deriving their probabilities via a parametric distribution as supervision signals. Using a simple linear model, we then predict probability distributions for each timestep. The OCE loss is computed between the cumulative distributions of predicted and ground-truth probabilities, explicitly preserving ordinal relationships among forecasted values. Through theoretical analysis using influence functions, we establish that cross-entropy (CE) loss exhibits superior stability and outlier robustness compared to MSE loss. Empirically, we compared OCE-TS with five baseline models-Autoformer, DLinear, iTransformer, TimeXer, and TimeBridge-on seven public time series datasets. Using MSE and Mean Absolute Error (MAE) as evaluation metrics, the results demonstrate that OCE-TS consistently outperforms benchmark models. The codeis publicly available at: https://github.com/Shi-hm/OCE-TS. --- ### Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQL Authors: Qifeng Cai, Hao Liang, Chang Xu, Tao Xie, Wentao Zhang, Bin Cui Published: 2025-11-13 Categories: cs.CL, cs.DB arXiv: https://arxiv.org/abs/2511.10192v4 The data-centric paradigm has emerged as a pivotal direction in artificial intelligence (AI), emphasizing the role of high-quality training data. This shift is especially critical in the Text-to-SQL task, where the scarcity, limited diversity, and structural simplicity of existing datasets constrain model performance. To address these challenges, we propose Text2SQL-Flow, a SQL-aware data augmentation framework that systematically generates large-scale, semantically valid, and structurally diverse Text-to-SQL pairs from limited seed data. Our framework spans six augmentation dimensions and integrates an end-to-end pipeline with auxiliary database selection, SQL executability verification, natural language (NL) question generation, NL-SQL correspondence verification, and chain-of-thought (CoT) reasoning trace generation. Leveraging this framework, we construct SQLFlow, a high-quality dataset comprising 75,386 annotated examples. We demonstrate the utility of SQLFlow in both fine-tuning and prompt-based settings. (1) For open-source large language models (LLMs), fine-tuning with SQLFlow improves problem-solving ability, delivering competitive gains across multiple benchmarks under the same data budget. (2) For closed-source LLMs, we propose a masked alignment retrieval method that uses SQLFlow as both a knowledge base and training data for the retrieval model, enabling structure-aware example matching via fine-grained NL-SQL alignments. Experiments show that our retrieval strategy outperforms existing example retrieval methods, highlighting the combined value of SQLFlow's data quality and our retrieval technique. Overall, our work provides a scalable, data-centric foundation for advancing Text-to-SQL systems and underscores the importance of structured, high-fidelity data in modern AI development. Our code is available at https://github.com/TechNomad-ds/Text2SQL-Flow. --- ### Towards Leveraging Sequential Structure in Animal Vocalizations Authors: Eklavya Sarkar, Mathew Magimai. -Doss Published: 2025-11-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10190v1 Animal vocalizations contain sequential structures that carry important communicative information, yet most computational bioacoustics studies average the extracted frame-level features across the temporal axis, discarding the order of the sub-units within a vocalization. This paper investigates whether discrete acoustic token sequences, derived through vector quantization and gumbel-softmax vector quantization of extracted self-supervised speech model representations can effectively capture and leverage temporal information. To that end, pairwise distance analysis of token sequences generated from HuBERT embeddings shows that they can discriminate call-types and callers across four bioacoustics datasets. Sequence classification experiments using $k$-Nearest Neighbour with Levenshtein distance show that the vector-quantized token sequences yield reasonable call-type and caller classification performances, and hold promise as alternative feature representations towards leveraging sequential information in animal vocalizations. --- ### Improved Offline Reinforcement Learning via Quantum Metric Encoding Authors: Outongyi Lv, Yewei Yuan, Nana Liu Published: 2025-11-13 Categories: cs.LG, cs.AI, quant-ph arXiv: https://arxiv.org/abs/2511.10187v1 Reinforcement learning (RL) with limited samples is common in real-world applications. However, offline RL performance under this constraint is often suboptimal. We consider an alternative approach to dealing with limited samples by introducing the Quantum Metric Encoder (QME). In this methodology, instead of applying the RL framework directly on the original states and rewards, we embed the states into a more compact and meaningful representation, where the structure of the encoding is inspired by quantum circuits. For classical data, QME is a classically simulable, trainable unitary embedding and thus serves as a quantum-inspired module, on a classical device. For quantum data in the form of quantum states, QME can be implemented directly on quantum hardware, allowing for training without measurement or re-encoding. We evaluated QME on three datasets, each limited to 100 samples. We use Soft-Actor-Critic (SAC) and Implicit-Q-Learning (IQL), two well-known RL algorithms, to demonstrate the effectiveness of our approach. From the experimental results, we find that training offline RL agents on QME-embedded states with decoded rewards yields significantly better performance than training on the original states and rewards. On average across the three datasets, for maximum reward performance, we achieve a 116.2% improvement for SAC and 117.6% for IQL. We further investigate the $Δ$-hyperbolicity of our framework, a geometric property of the state space known to be important for the RL training efficacy. The QME-embedded states exhibit low $Δ$-hyperbolicity, suggesting that the improvement after embedding arises from the modified geometry of the state space induced by QME. Thus, the low $Δ$-hyperbolicity and the corresponding effectiveness of QME could provide valuable information for developing efficient offline RL methods under limited-sample conditions. --- ### Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA Authors: Yiran Zhang, Mingyang Lin, Mark Dras, Usman Naseem Published: 2025-11-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10182v1 Recent research has increasingly focused on the reasoning capabilities of Large Language Models (LLMs) in multi-turn interactions, as these scenarios more closely mirror real-world problem-solving. However, analyzing the intricate reasoning processes within these interactions presents a significant challenge due to complex contextual dependencies and a lack of specialized visualization tools, leading to a high cognitive load for researchers. To address this gap, we present VISTA, an web-based Visual Interactive System for Textual Analytics in multi-turn reasoning tasks. VISTA allows users to visualize the influence of context on model decisions and interactively modify conversation histories to conduct "what-if" analyses across different models. Furthermore, the platform can automatically parse a session and generate a reasoning dependency tree, offering a transparent view of the model's step-by-step logical path. By providing a unified and interactive framework, VISTA significantly reduces the complexity of analyzing reasoning chains, thereby facilitating a deeper understanding of the capabilities and limitations of current LLMs. The platform is open-source and supports easy integration of custom benchmarks and local models. --- ### Utilizing a Geospatial Foundation Model for Coastline Delineation in Small Sandy Islands Authors: Tishya Chhabra, Manisha Bajpai, Walter Zesk, Skylar Tibbits Published: 2025-11-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10177v1 We present an initial evaluation of NASA and IBM's Prithvi-EO-2.0 geospatial foundation model on shoreline delineation of small sandy islands using satellite images. We curated and labeled a dataset of 225 multispectral images of two Maldivian islands, which we publicly release, and fine-tuned both the 300M and 600M parameter versions of Prithvi on training subsets ranging from 5 to 181 images. Our experiments show that even with as few as 5 training images, the models achieve high performance (F1 of 0.94, IoU of 0.79). Our results demonstrate the strong transfer learning capability of Prithvi, underscoring the potential of such models to support coastal monitoring in data-poor regions. --- ### CephRes-MHNet: A Multi-Head Residual Network for Accurate and Robust Cephalometric Landmark Detection Authors: Ahmed Jaheen, Islam Hassan, Mohanad Abouserie, Abdelaty Rehab, Adham Elasfar, Knzy Elmasry, Mostafa El-Dawlatly, Seif Eldawlatly Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10173v2 Accurate localization of cephalometric landmarks from 2D lateral skull X-rays is vital for orthodontic diagnosis and treatment. Manual annotation is time-consuming and error-prone, whereas automated approaches often struggle with low contrast and anatomical complexity. This paper introduces CephRes-MHNet, a multi-head residual convolutional network for robust and efficient cephalometric landmark detection. The architecture integrates residual encoding, dual-attention mechanisms, and multi-head decoders to enhance contextual reasoning and anatomical precision. Trained on the Aariz Cephalometric dataset of 1,000 radiographs, CephRes-MHNet achieved a mean radial error (MRE) of 1.23 mm and a success detection rate (SDR) @ 2.0 mm of 85.5%, outperforming all evaluated models. In particular, it exceeded the strongest baseline, the attention-driven AFPF-Net (MRE = 1.25 mm, SDR @ 2.0 mm = 84.1%), while using less than 25% of its parameters. These results demonstrate that CephRes-MHNet attains state-of-the-art accuracy through architectural efficiency, providing a practical solution for real-world orthodontic analysis. --- ### Physically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution Authors: Hu Gao, Xiaoning Lei, Xichen Xu, Depeng Dang, Lizhuang Ma Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10166v1 Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noise, and haze, requiring models capable of handling diverse degradation types. Moreover, methods that improve performance through module stacking often suffer from limited interpretability. In this paper, we propose a novel interpretability-driven approach for multi-degradation image restoration, built upon a deep unfolding network that maps the iterative process of a mathematical optimization algorithm into a learnable network structure. Specifically, we employ an improved second-order semi-smooth Newton algorithm to ensure that each module maintains clear physical interpretability. To further enhance interpretability and adaptability, we design an explainable convolution module inspired by the human brain's flexible information processing and the intrinsic characteristics of images, allowing the network to flexibly leverage learned knowledge and autonomously adjust parameters for different input. The resulting tightly integrated architecture, named InterIR, demonstrates excellent performance in multi-degradation restoration while remaining highly competitive on single-degradation tasks. --- ### EPO: Diverse and Realistic Protein Ensemble Generation via Energy Preference Optimization Authors: Yuancheng Sun, Yuxuan Ren, Zhaoming Chen, Xu Han, Kang Liu, Qiwei Ye Published: 2025-11-13 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2511.10165v1 Accurate exploration of protein conformational ensembles is essential for uncovering function but remains hard because molecular-dynamics (MD) simulations suffer from high computational costs and energy-barrier trapping. This paper presents Energy Preference Optimization (EPO), an online refinement algorithm that turns a pretrained protein ensemble generator into an energy-aware sampler without extra MD trajectories. Specifically, EPO leverages stochastic differential equation sampling to explore the conformational landscape and incorporates a novel energy-ranking mechanism based on list-wise preference optimization. Crucially, EPO introduces a practical upper bound to efficiently approximate the intractable probability of long sampling trajectories in continuous-time generative models, making it easily adaptable to existing pretrained generators. On Tetrapeptides, ATLAS, and Fast-Folding benchmarks, EPO successfully generates diverse and physically realistic ensembles, establishing a new state-of-the-art in nine evaluation metrics. These results demonstrate that energy-only preference signals can efficiently steer generative models toward thermodynamically consistent conformational ensembles, providing an alternative to long MD simulations and widening the applicability of learned potentials in structural biology and drug discovery. --- ### Two Constraint Compilation Methods for Lifted Planning Authors: Periklis Mantenoglou, Luigi Bonassi, Enrico Scala, Pedro Zuidberg Dos Martires Published: 2025-11-13 Categories: cs.AI, cs.SC arXiv: https://arxiv.org/abs/2511.10164v2 We study planning in a fragment of PDDL with qualitative state-trajectory constraints, capturing safety requirements, task ordering conditions, and intermediate sub-goals commonly found in real-world problems. A prominent approach to tackle such problems is to compile their constraints away, leading to a problem that is supported by state-of-the-art planners. Unfortunately, existing compilers do not scale on problems with a large number of objects and high-arity actions, as they necessitate grounding the problem before compilation. To address this issue, we propose two methods for compiling away constraints without grounding, making them suitable for large-scale planning problems. We prove the correctness of our compilers and outline their worst-case time complexity. Moreover, we present a reproducible empirical evaluation on the domains used in the latest International Planning Competition. Our results demonstrate that our methods are efficient and produce planning specifications that are orders of magnitude more succinct than the ones produced by compilers that ground the domain, while remaining competitive when used for planning with a state-of-the-art planner. --- ### DenoGrad: A Gradient-Based Framework for Data Refinement in Tabular and Time-Series Learning Authors: J. Javier Alonso-Ramos, Ignacio Aguilera-Martos, Francisco Herrera, Andrés Herrera-Poyatos Published: 2025-11-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.10161v2 In the Data-Centric Artificial Intelligence (AI) paradigm, improving data quality is essential for robust machine learning. However, many denoising methods rely on rigid statistical assumptions or require clean reference data, which limits their applicability in real-world scenarios. In this work, we propose DenoGrad, a gradient-based framework for data refinement that leverages a pretrained neural network to iteratively correct noisy observations by optimizing the input space while keeping the model fixed. DenoGrad is applicable to both tabular regression and time-series forecasting, and incorporates a consensus-based strategy to ensure temporally coherent updates in sequential settings. Experiments on ten real-world datasets show that the proposed approach yields consistent improvements in downstream predictive performance while preserving the statistical structure of the data, as measured by distributional and correlation-based metrics. In addition, DenoGrad can improve generalization in nominally clean datasets, acting as a form of dataset-level regularization. These results support model-guided data refinement as a practical component of data-centric machine learning workflows. Code is available at: https://github.com/ari-dasci/S-DenoGrad. --- ### GEA: Generation-Enhanced Alignment for Text-to-Image Person Retrieval Authors: Hao Zou, Runqing Zhang, Xue Zhou, Jianxiao Zou Published: 2025-11-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10154v1 Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: (1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. (2) Generative Intermediate Fusion (GIF), which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The results justify the effectiveness of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA. --- ### Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection Authors: Feng Ding, Wenhui Yi, Yunpeng Zhou, Xinan He, Hong Rao, Shu Hu Published: 2025-11-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10150v5 Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead to systemic misjudgments, exacerbating the digital divide and social inequities. However, current fairness-enhanced detectors often improve fairness at the cost of detection accuracy. To address this challenge, we propose a dual-mechanism collaborative optimization framework. Our proposed method innovatively integrates structural fairness decoupling and global distribution alignment: decoupling channels sensitive to demographic groups at the model architectural level, and subsequently reducing the distance between the overall sample distribution and the distributions corresponding to each demographic group at the feature level. Experimental results demonstrate that, compared with other methods, our framework improves both inter-group and intra-group fairness while maintaining overall detection accuracy across domains. The code is available at https://github.com/ywh1093/Fairness-Optimization. --- ### UCPO: A Universal Constrained Combinatorial Optimization Method via Preference Optimization Authors: Zhanhong Fang, Debing Wang, Jinbiao Chen, Jiahai Wang, Zizhen Zhang Published: 2025-11-13 Categories: cs.NE arXiv: https://arxiv.org/abs/2511.10148v1 Neural solvers have demonstrated remarkable success in combinatorial optimization, often surpassing traditional heuristics in speed, solution quality, and generalization. However, their efficacy deteriorates significantly when confronted with complex constraints that cannot be effectively managed through simple masking mechanisms. To address this limitation, we introduce Universal Constrained Preference Optimization (UCPO), a novel plug-and-play framework that seamlessly integrates preference learning into existing neural solvers via a specially designed loss function, without requiring architectural modifications. UCPO embeds constraint satisfaction directly into a preference-based objective, eliminating the need for meticulous hyperparameter tuning. Leveraging a lightweight warm-start fine-tuning protocol, UCPO enables pre-trained models to consistently produce near-optimal, feasible solutions on challenging constraint-laden tasks, achieving exceptional performance with as little as 1\% of the original training budget. ---