OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning Paper • 2505.08617 • Published 4 days ago • 26
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement Paper • 2504.07934 • Published Apr 10 • 18
V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models Paper • 2504.06148 • Published Apr 8 • 13
Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models Paper • 2503.20198 • Published Mar 26 • 4