{"total":69,"rows":[{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255,"area":"lr"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2505.16673","title":"R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO","created":"2025-05-22","cited_by_count":52,"area":"lr"},{"id":"2505.17022","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","created":"2025-05-22","cited_by_count":52,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2509.01656","title":"Reinforced Visual Perception with Tools","created":"2025-09-01","cited_by_count":38,"area":"lr"},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38,"area":"lr"},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33,"area":"alignment"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27,"area":null},{"id":"2506.01908","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","created":"2025-06-02","cited_by_count":26,"area":"lr"},{"id":"2505.19877","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2512.04069","title":"SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL","created":"2025-12-03","cited_by_count":21,"area":"lr"},{"id":"2510.23569","title":"EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT","created":"2025-10-27","cited_by_count":16,"area":"lr"},{"id":"2504.03724","title":"CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward","created":"2025-03-31","cited_by_count":15,"area":"lr"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2506.21669","title":"SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents","created":"2025-06-26","cited_by_count":15,"area":"agents"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2505.19406","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","created":"2025-05-26","cited_by_count":14,"area":"lr"},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2505.24164","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13,"area":"lr"},{"id":"2512.05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2506.20168","title":"Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models","created":"2025-06-25","cited_by_count":12,"area":"mllm"},{"id":"2507.00748","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","created":"2025-07-01","cited_by_count":11,"area":"lr"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2506.08022","title":"Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining","created":"2025-05-20","cited_by_count":8,"area":"mllm"},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2506.14821","title":"Reinforcing VLMs to Use Tools for Detailed Visual Reasoning Under Resource Constraints","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2510.02665","title":"Self-Improvement in Multimodal Large Language Models: A Survey","created":"2025-10-03","cited_by_count":6,"area":"mllm"},{"id":"2512.04082","title":"PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2603.08652","title":"CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2026-03-09","cited_by_count":6,"area":"lr"},{"id":"2605.20177","title":"From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2506.19469","title":"Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning","created":"2025-06-24","cited_by_count":5,"area":"lr"},{"id":"2509.15566","title":"BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent","created":"2025-09-19","cited_by_count":5,"area":"lr"},{"id":"2511.18823","title":"VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models","created":"2025-11-24","cited_by_count":5,"area":"mllm"},{"id":"2512.08980","title":"Training Multi-Image Vision Agents via End2End Reinforcement Learning","created":"2025-12-05","cited_by_count":4,"area":"lr"},{"id":"2606.06294","title":"Towards One-to-Many Temporal Grounding","created":"2026-06-04","cited_by_count":4,"area":null},{"id":"2505.19611","title":"Align and Surpass Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2510.08964","title":"Unleashing Perception-Time Scaling to Multimodal Reasoning Models","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2511.23151","title":"Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2512.23169","title":"REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation","created":"2025-12-29","cited_by_count":3,"area":"lr"},{"id":"2602.23615","title":"HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2606.23557","title":"Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2509.03321","title":"Empowering Lightweight MLLMs with Reasoning via Long CoT SFT","created":"2025-09-03","cited_by_count":2,"area":"lr"},{"id":"2604.04379","title":"Reinforce to Learn, Elect to Reason: A Dual Paradigm for Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2605.01324","title":"Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs","created":"2026-05-02","cited_by_count":2,"area":"lr"},{"id":"2605.27906","title":"Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2509.06759","title":"Aligning Large Vision-Language Models by Deep Reinforcement Learning and Direct Preference Optimization","created":"2025-09-08","cited_by_count":1,"area":"mllm"},{"id":"2602.19442","title":"UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2605.03485","title":"MHPR: Multidimensional Human Perception and Reasoning Benchmark for Large Vision-Languate Models","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2508.07804","title":"Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.22283","title":"Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models","created":"2025-09-26","cited_by_count":0,"area":"lr"},{"id":"2509.25811","title":"Logo-VGR: Visual Grounded Reasoning for Open-world Logo Recognition","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2512.23090","title":"Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patients","created":"2025-12-28","cited_by_count":0,"area":"lr"},{"id":"2602.03300","title":"R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?","created":"2026-02-03","cited_by_count":0,"area":"mllm"},{"id":"2603.16929","title":"MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning","created":"2026-03-14","cited_by_count":0,"area":"deeprl"},{"id":"2604.08230","title":"Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.15210","title":"Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.19218","title":"Thinking Before Matching: A Reinforcement Reasoning Paradigm Towards General Person Re-Identification","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.06121","title":"Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2606.26196","title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","created":"2026-06-24","cited_by_count":0,"area":"mllm"},{"id":"2607.02504","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.10147","title":"REVA-PO: Stabilizing Reinforcement Learning for Chest X-ray Report Generation","created":"2026-07-11","cited_by_count":0,"area":"deeprl"},{"id":"2610.07018","title":"When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}