Hu, Lin, Lee, Su, Lee, Tsai, Lin, Chen, Ke, Liu: See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation https://arxiv.org/abs/2509.22653 https://arxiv.org/pdf/2509.22653 https://arxiv.org/html/2509.22653

Ke Wang, Houxing Ren, Zimu Lu, Mingjie Zhan, Hongsheng Li: VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing https://arxiv.org/abs/2509.22651 https://arxiv.org/pdf/2509.22651 https://arxiv.org/html/2509.22651

Arsham Ghavasieh, Meritxell Vila-Minana, Akanksha Khurd, John Beggs, Gerardo Ortiz, Santo Fortunato: Toward a Physics of Deep Learning and Brains https://arxiv.org/abs/2509.22649 https://arxiv.org/pdf/2509.22649 https://arxiv.org/html/2509.22649

Long Xing, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jianze Liang, Qidong Huang, Jiaqi Wang, Feng Wu, Dahua Lin: CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning https://arxiv.org/abs/2509.22647 https://arxiv.org/pdf/2509.22647 https://arxiv.org/html/2509.22647

Fu, Liu, Xu, Lu, Hu, Yang, Anantasagar, Shen, Mao, Liu, Shah, Lee, Choi, Zou, Roth, Callison-Burch: Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs https://arxiv.org/abs/2509.22646 https://arxiv.org/pdf/2509.22646 https://arxiv.org/html/2509.22646

Zhen-Hao Wen, Yan Wang, Ji Feng, Han-Jia Ye, De-Chuan Zhan, Da-Wei Zhou: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning https://arxiv.org/abs/2509.22645 https://arxiv.org/pdf/2509.22645 https://arxiv.org/html/2509.22645

Lu, Ren, Yang, Wang, Zong, Pan, Zhan, Li: WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning https://arxiv.org/abs/2509.22644 https://arxiv.org/pdf/2509.22644 https://arxiv.org/html/2509.22644

Arkadiy Saakyan, Najoung Kim, Smaranda Muresan, Tuhin Chakrabarty: Death of the Novel(ty): Beyond n-Gram Novelty as a Metric for Textual Creativity https://arxiv.org/abs/2509.22641 https://arxiv.org/pdf/2509.22641 https://arxiv.org/html/2509.22641

Renjie Luo, Zichen Liu, Xiangyan Liu, Chao Du, Min Lin, Wenhu Chen, Wei Lu, Tianyu Pang: Language Models Can Learn from Verbal Feedback Without Scalar Rewards https://arxiv.org/abs/2509.22638 https://arxiv.org/pdf/2509.22638 https://arxiv.org/html/2509.22638

Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang: Variational Reasoning for Language Models https://arxiv.org/abs/2509.22637 https://arxiv.org/pdf/2509.22637 https://arxiv.org/html/2509.22637

Gen Li, Yuling Yan: Towards Efficient Online Exploration for Reinforcement Learning with Human Feedback https://arxiv.org/abs/2509.22633 https://arxiv.org/pdf/2509.22633 https://arxiv.org/html/2509.22633

Xingyu Shen, Yingfa Chen, Zhen Leng Thai, Xu Han, Zhiyuan Liu, Maosong Sun: StateX: Enhancing RNN Recall via Post-training State Expansion https://arxiv.org/abs/2509.22630 https://arxiv.org/pdf/2509.22630 https://arxiv.org/html/2509.22630

Ehsan Futuhi, Nathan R. Sturtevant: Learning Admissible Heuristics for A*: Theory and Practice https://arxiv.org/abs/2509.22626 https://arxiv.org/pdf/2509.22626 https://arxiv.org/html/2509.22626

Maojiang Su, Mingcheng Lu, Jerry Yao-Chieh Hu, Shang Wu, Zhao Song, Alex Reneau, Han Liu: A Theoretical Analysis of Discrete Flow Matching Generative Models https://arxiv.org/abs/2509.22623 https://arxiv.org/pdf/2509.22623 https://arxiv.org/html/2509.22623

Aayush Mishra, Daniel Khashabi, Anqi Liu: IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning https://arxiv.org/abs/2509.22621 https://arxiv.org/pdf/2509.22621 https://arxiv.org/html/2509.22621

Yasmine Omri, Connor Ding, Tsachy Weissman, Thierry Tambe: Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting https://arxiv.org/abs/2509.22615 https://arxiv.org/pdf/2509.22615 https://arxiv.org/html/2509.22615

Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He: Quantile Advantage Estimation for Entropy-Safe Reasoning https://arxiv.org/abs/2509.22611 https://arxiv.org/pdf/2509.22611 https://arxiv.org/html/2509.22611

Qin, Tan, He, Li, Lin, Li, Xu, Shi, Cai, Rui, Cai, Cai, Zhang, Ye, Li, Sun: Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning https://arxiv.org/abs/2509.22601 https://arxiv.org/pdf/2509.22601 https://arxiv.org/html/2509.22601

Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli: From Parameters to Behavior: Unsupervised Compression of the Policy Space https://arxiv.org/abs/2509.22566 https://arxiv.org/pdf/2509.22566 https://arxiv.org/html/2509.22566

Chen, Haredasht, Black, Grolleau, Alsentzer, Chen, P.: Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation https://arxiv.org/abs/2509.22565 https://arxiv.org/pdf/2509.22565 https://arxiv.org/html/2509.22565

Lute Lillo, Nick Cheney: Activation Function Design Sustains Plasticity in Continual Learning https://arxiv.org/abs/2509.22562 https://arxiv.org/pdf/2509.22562 https://arxiv.org/html/2509.22562

Zou, Duan, Fleming, Liu, Kompella, Ren, Xu: ConQuER: Modular Architectures for Control and Bias Mitigation in IQP Quantum Generative Models https://arxiv.org/abs/2509.22551 https://arxiv.org/pdf/2509.22551 https://arxiv.org/html/2509.22551

Veda Duddu, Jash Rajesh Parekh, Andy Mao, Hanyi Min, Ziang Xiao, Vedant Das Swain, Koustuv Saha: Does AI Coaching Prepare us for Workplace Negotiations? https://arxiv.org/abs/2509.22545 https://arxiv.org/pdf/2509.22545 https://arxiv.org/html/2509.22545

Wang, Cai, Xie, Feng, Zhang, Li, Yang, Li, Cao, Xie, Yang: InfiR2: A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models https://arxiv.org/abs/2509.22536 https://arxiv.org/pdf/2509.22536 https://arxiv.org/html/2509.22536

Yunhao Yuan, Jiaxun Zhang, Talayeh Aledavood, Renwen Zhang, Koustuv Saha: Mental Health Impacts of AI Companions: Triangulating Social Media Quasi-Experiments, User Perspectives, and Relation... https://arxiv.org/abs/2509.22505 https://arxiv.org/pdf/2509.22505 https://arxiv.org/html/2509.22505

Alberto Olivares-Alarcos, Sergi Foix, J\'ulia Borr\`as, Gerard Canal, Guillem Aleny\`a: Ontological foundations for contrastive explanatory narration of robot plans https://arxiv.org/abs/2509.22493 https://arxiv.org/pdf/2509.22493 https://arxiv.org/html/2509.22493

Punzo, Galfr\`e, Massafra, Maglione, Priami, S\^irbu: A Machine Learning Pipeline for Multiple Sclerosis Biomarker Discovery: Comparing explainable AI and Traditional Statistical Approaches https://arxiv.org/abs/2509.22484 https://arxiv.org/pdf/2509.22484 https://arxiv.org/html/2509.22484

Sadia Asif, Mohammad Mohammadi Amiri: OFMU: Optimization-Driven Framework for Machine Unlearning https://arxiv.org/abs/2509.22483 https://arxiv.org/pdf/2509.22483 https://arxiv.org/html/2509.22483

Hang Li, Kaiqi Yang, Yucheng Chu, Hui Liu, Jiliang Tang: Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving https://arxiv.org/abs/2509.22480 https://arxiv.org/pdf/2509.22480 https://arxiv.org/html/2509.22480

Antreas Ioannou, Andreas Shiamishis, Nora Hollenstein, Nezihe Merve G\"urel: Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning https://arxiv.org/abs/2509.22472 https://arxiv.org/pdf/2509.22472 https://arxiv.org/html/2509.22472

Boshra Ariguib, Mathias Niepert, Andrei Manolache: Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining https://arxiv.org/abs/2509.22468 https://arxiv.org/pdf/2509.22468 https://arxiv.org/html/2509.22468

Li, Jiang, Wang, Zhang, Sun, Yang, Cao, Dou, Fan, Fan, Ji, Gui, Zhang, Huang: MDAR: A Multi-scene Dynamic Audio Reasoning Benchmark https://arxiv.org/abs/2509.22461 https://arxiv.org/pdf/2509.22461 https://arxiv.org/html/2509.22461

Changhun Kim, et al.: Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator https://arxiv.org/abs/2509.22458 https://arxiv.org/pdf/2509.22458 https://arxiv.org/html/2509.22458

Peter Shaw, James Cohan, Jacob Eisenstein, Kristina Toutanova: Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers https://arxiv.org/abs/2509.22445 https://arxiv.org/pdf/2509.22445 https://arxiv.org/html/2509.22445

Pei Xu, Zhen Wu, Ruocheng Wang, Vishnu Sarukkai, Kayvon Fatahalian, Ioannis Karamouzas, Victor Zordan, C. Karen Liu: Learning to Ball: Composing Policies for Long-Horizon Basketball Moves https://arxiv.org/abs/2509.22442 https://arxiv.org/pdf/2509.22442 https://arxiv.org/html/2509.22442

Ziheng Chi, Yifan Hou, Chenxi Pang, Shaobo Cui, Mubashara Akhtar, Mrinmaya Sachan: Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding https://arxiv.org/abs/2509.22437 https://arxiv.org/pdf/2509.22437 https://arxiv.org/html/2509.22437

Tianxiang Gao, Siyuan Sun, Hailiang Liu, Hongyang Gao: Global Convergence in Neural ODEs: Impact of Activation Functions https://arxiv.org/abs/2509.22436 https://arxiv.org/pdf/2509.22436 https://arxiv.org/html/2509.22436

Margherita Martorana, Francesca Urgese, Ilaria Tiddi, Stefan Schlobach: An Ontology for Unified Modeling of Tasks, Actions, Environments, and Capabilities in Personal Service Robotics https://arxiv.org/abs/2509.22434 https://arxiv.org/pdf/2509.22434 https://arxiv.org/html/2509.22434

Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert: Partial Parameter Updates for Efficient Distributed Training https://arxiv.org/abs/2509.22418 https://arxiv.org/pdf/2509.22418 https://arxiv.org/html/2509.22418

Jiawei Liang, Ruoyu Chen, Xianghao Jiao, Siyuan Liang, Shiming Liu, Qunli Zhang, Zheng Hu, Xiaochun Cao: Explaining multimodal LLMs via intra-modal token interactions https://arxiv.org/abs/2509.22415 https://arxiv.org/pdf/2509.22415 https://arxiv.org/html/2509.22415

Li, Liu, Guo, Zhao, Zhang, Chen, Mailhe, Mukherjee, Chen, Sun: RAU: Reference-based Anatomical Understanding with Vision Language Models https://arxiv.org/abs/2509.22404 https://arxiv.org/pdf/2509.22404 https://arxiv.org/html/2509.22404

Gonz\'alez, Longuefosse, Benito, Mart\'in, Baldacci: Deep Learning-Based Cross-Anatomy CT Synthesis Using Adapted nnResU-Net with Anatomical Feature Prioritized Loss https://arxiv.org/abs/2509.22394 https://arxiv.org/pdf/2509.22394 https://arxiv.org/html/2509.22394

Narada Maugin, Tristan Cazenave: SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly https://arxiv.org/abs/2509.22387 https://arxiv.org/pdf/2509.22387 https://arxiv.org/html/2509.22387

Zijian Zhao, Dian Jin, Zijing Zhou: Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach https://arxiv.org/abs/2509.22378 https://arxiv.org/pdf/2509.22378 https://arxiv.org/html/2509.22378

Tanise Ceron, Dmitry Nikolaev, Dominik Stammbach, Debora Nozza: What Is The Political Content in LLMs' Pre- and Post-Training Data? https://arxiv.org/abs/2509.22367 https://arxiv.org/pdf/2509.22367 https://arxiv.org/html/2509.22367

Hegde, Paul, Joel-Frey, Brack, Kersting, Mundt, Schramowski: CHRONOBERG: Capturing Language Evolution and Temporal Awareness in Foundation Models https://arxiv.org/abs/2509.22360 https://arxiv.org/pdf/2509.22360 https://arxiv.org/html/2509.22360

Jacob B. Landsberg, Elizabeth A. Barnes: Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models https://arxiv.org/abs/2509.22359 https://arxiv.org/pdf/2509.22359 https://arxiv.org/html/2509.22359

Maria Lomeli, Matthijs Douze, Gergely Szilvasy, Loic Cabannes, Jade Copet, Sainbayar Sukhbaatar, Jason Weston, Gabriel Synnaeve, Pierre-Emmanuel Mazar\'e, Herv\'e J\'egou: Stochastic activations https://arxiv.org/abs/2509.22358 https://arxiv.org/pdf/2509.22358 https://arxiv.org/html/2509.22358

Wang, Chen, Zhong, Zheng, Shao, Yu, Liu, Wang, Ding, Cao, Kang: Context and Diversity Matter: The Emergence of In-Context Learning in World Models https://arxiv.org/abs/2509.22353 https://arxiv.org/pdf/2509.22353 https://arxiv.org/html/2509.22353

Marie Brockschmidt, Maresa Schr\"oder, Stefan Feuerriegel: SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis https://arxiv.org/abs/2509.22352 https://arxiv.org/pdf/2509.22352 https://arxiv.org/html/2509.22352