Author

Wen-Tao Zhou

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Mutually Adversarial Self-Training with Evolving Data for Unified Multimodal Models

MATE (Mutually Adversarial self-Training with Evolving data), a reinforcement-learning-based post-training framework in which the two branches instead challenge each other, and the challenges evolve as the model trains, turns the training into self-play in data space.

Wen-Tao Zhou, Wei-Jie Gan, Jia-Yun Wang · 0 citations