{"total":32,"rows":[{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99,"area":"lr"},{"id":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42,"area":"lr"},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"area":"lr"},{"id":"2510.23473","title":"Video-Thinker: Sparking \"Thinking with Videos\" via Reinforcement Learning","created":"2025-10-27","cited_by_count":34,"area":"lr"},{"id":"2507.22607","title":"VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning","created":"2025-07-30","cited_by_count":26,"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":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"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":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2509.24494","title":"Why Tree-Style Branching Matters for Thought Advantage Estimation in GRPO","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.06870","title":"$\\lambda$-GRPO: Unifying the GRPO Frameworks with Learnable Token Preferences","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2601.04118","title":"GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning","created":"2026-01-07","cited_by_count":10,"area":"lr"},{"id":"2509.21854","title":"Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2511.22715","title":"ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering","created":"2025-11-27","cited_by_count":7,"area":"lr"},{"id":"2603.15600","title":"From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2606.02564","title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","created":"2026-06-01","cited_by_count":5,"area":"lr"},{"id":"2512.08511","title":"Thinking with Images via Self-Calling Agent","created":"2025-12-09","cited_by_count":4,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2602.18193","title":"BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards","created":"2026-02-20","cited_by_count":3,"area":"lr"},{"id":"2603.01301","title":"When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2603.25942","title":"Reinforcing Structured Chain-of-Thought for Video Understanding","created":"2026-03-26","cited_by_count":2,"area":"lr"},{"id":"2604.18892","title":"Prioritizing the Best: Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2512.02699","title":"Learning What to Attend First: Modality-Importance-Guided Reasoning for Reliable Multimodal Emotion Understanding","created":"2025-12-02","cited_by_count":1,"area":"lr"},{"id":"2603.18850","title":"HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"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":"2605.26680","title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2605.27154","title":"Touch-R1: Reinforcing Touch Reasoning in MLLMs","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2512.17213","title":"CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency","created":"2025-12-19","cited_by_count":0,"area":"lr"},{"id":"2606.18988","title":"ThinkDeception: A Progressive Reinforcement Learning Framework for Interpretable Multimodal Deception Detection","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2606.30217","title":"Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}