SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning Paper • 2506.24119 • Published 3 days ago • 35
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation Paper • 2506.18095 • Published 11 days ago • 63
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs Paper • 2506.10128 • Published 22 days ago • 22
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs Paper • 2506.10128 • Published 22 days ago • 22
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs Paper • 2506.10128 • Published 22 days ago • 22 • 2
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning Paper • 2506.05523 • Published 28 days ago • 33