{"total":29,"rows":[{"id":"2509.24251","title":"Latent Visual Reasoning","created":"2025-09-29","cited_by_count":104,"area":"lr"},{"id":"2510.14958","title":"MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning","created":"2025-10-16","cited_by_count":35,"area":"lr"},{"id":"2601.21821","title":"MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods","created":"2026-01-29","cited_by_count":30,"area":"lr"},{"id":"2509.23652","title":"ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis","created":"2025-09-28","cited_by_count":26,"area":"lr"},{"id":"2510.02240","title":"RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning","created":"2025-10-02","cited_by_count":21,"area":"lr"},{"id":"2506.09736","title":"Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation","created":"2025-06-11","cited_by_count":14,"area":"lr"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2510.16062","title":"Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs","created":"2025-10-17","cited_by_count":14,"area":"lr"},{"id":"2507.07562","title":"The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs","created":"2025-07-10","cited_by_count":12,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","cited_by_count":12,"area":"lr"},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2510.14738","title":"AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning","created":"2025-10-16","cited_by_count":11,"area":"lr"},{"id":"2512.02361","title":"VACoT: Rethinking Visual Data Augmentation with VLMs","created":"2025-12-02","cited_by_count":9,"area":"lr"},{"id":"2603.25077","title":"Bridging Perception and Reasoning: Token Reweighting for RLVR in Multimodal LLMs","created":"2026-03-26","cited_by_count":9,"area":"lr"},{"id":"2603.03825","title":"From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning","created":"2026-03-04","cited_by_count":8,"area":"lr"},{"id":"2506.09557","title":"Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes","created":"2025-06-11","cited_by_count":7,"area":"lr"},{"id":"2601.02983","title":"Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2509.03906","title":"Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning","created":"2025-09-04","cited_by_count":5,"area":"lr"},{"id":"2512.12690","title":"Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2602.21743","title":"Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization","created":"2026-02-25","cited_by_count":4,"area":"lr"},{"id":"2604.14646","title":"Targeted Exploration via Unified Entropy Control for Reinforcement Learning","created":"2026-04-16","cited_by_count":3,"area":"lr"},{"id":"2605.12163","title":"Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2608.00743","title":"LUT: Latent Utility Training for Visual Reasoning","created":"2026-08-01","cited_by_count":2,"area":"lr"},{"id":"2603.26126","title":"Beyond Where to Look: Trajectory-Guided Reinforcement Learning for Multimodal RLVR","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2610.01352","title":"MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2508.02506","title":"R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms","created":"2025-08-04","cited_by_count":0,"area":"lr"},{"id":"2606.29984","title":"Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement Learning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2608.10954","title":"Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes","created":"2026-08-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}