UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
- Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback d
Unverified
- Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback d
Sources: Arxiv