{"total":17,"rows":[{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120,"area":"lr"},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"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":"2510.13418","title":"Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation","created":"2025-10-15","cited_by_count":14,"area":"lr"},{"id":"2602.12506","title":"On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2602.04486","title":"Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition","created":"2026-02-04","cited_by_count":6,"area":"lr"},{"id":"2511.19417","title":"Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2602.03380","title":"Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization","created":"2026-02-03","cited_by_count":5,"area":"lr"},{"id":"2512.22120","title":"See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning","created":"2025-12-26","cited_by_count":3,"area":"lr"},{"id":"2505.19100","title":"ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning","created":"2025-05-25","cited_by_count":2,"area":"lr"},{"id":"2512.22183","title":"Unbiased Visual Reasoning with Controlled Visual Inputs","created":"2025-12-19","cited_by_count":2,"area":"lr"},{"id":"2606.24636","title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2510.04196","title":"COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability","created":"2025-10-05","cited_by_count":0,"area":"lr"},{"id":"2510.21093","title":"MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2603.10300","title":"From Imitation to Intuition: Intrinsic Reasoning for Open-Instance Video Classification","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2609.16601","title":"SAVOR: Self-Aware Visual Grounding via Confidence-Calibrated Reinforcement Learning for Multimodal Hallucination Mitigation","created":"2026-09-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}