Preprint
Sep 2026
Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models
Unified multimodal models integrate visual understanding and generation within a single network, yet the two capabilities are commonly optimized as separate tasks. We introduce Generative Grounding Feedback(GGF), a self-evolving post-training framework that uses only text prompts and the model's own visual experience....
Ke-Chun Hao, Yuan-Zhi Liang, Ting Chen et al.
· 1 citation
· ⚡1