UniEvo-VL: Self-Distillation Training for Multimodal Model Self-Improvement

Automated excerpt

Abstract:Modern multimodal models bring generation and understanding into a single unified system, which enables them to provide and learn from their own feedback. Motivated by this unified capacity, we introduce UniEvo-VL, a self-evolving framework for multimodal models to learn from this constructive self-correction feedback during test-time compute. Experiments demonstrate that UniEvo-VL improves the image generation capabilities of multimodal models, while maintaining their sensitivity to additional reflection information.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.