MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Published in Preprint, 2026
MM-Zero is the first RL-based framework to achieve zero-data self-evolution for VLM reasoning via a multi-role training framework with a Proposer, Coder, and Solver.
| arXiv | Code |
Recommended citation: Zongxia Li*, Hongyang Du*, Chengsong Huang*, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, et al. (2026). "MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data." Preprint.
Download Paper