UniEvo-VL: On-Policy Self-Distillation for Multimodal Image Generation
This story is from 2026-10-01. It is preserved in the archive; the latest stories are on the live feed.
UniEvo-VL trains a unified multimodal model to internalize its own image critiques by matching a critique-conditioned EMA teacher along denoising trajectories sampled from the student’s current policy. From inference-time reflection to learned behavior A multimodal model that can both generate and…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-10-01 15:54 · DEV Community — Machine Learning
UniEvo-VL: On-Policy Self-Distillation for Multimodal Image Generation