RL makes MLLMs see better than SFT
Paper
•
2510.16333
•
Published
•
48
RL
-
-
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
Paper • 2510.16888 • Published • 21 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 47 -
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation
Paper • 2510.21583 • Published • 30 -
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Paper • 2510.23451 • Published • 26 -
Tongyi DeepResearch Technical Report
Paper • 2510.24701 • Published • 96 -
Reasoning-Aware GRPO using Process Mining
Paper • 2510.25065 • Published • 41