Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning
Paper
• 2506.04207 • Published
• 48
reinforcement-learning
-
-
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Paper • 2504.11468 • Published • 30 -
RLPR: Extrapolating RLVR to General Domains without Verifiers
Paper • 2506.18254 • Published • 32 -
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Paper • 2507.05255 • Published • 75 -
Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
Paper • 2507.14137 • Published • 36 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 160 -
Group Sequence Policy Optimization
Paper • 2507.18071 • Published • 319 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 251 -
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 662 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 190 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 273 -
Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play
Paper • 2509.25541 • Published • 140