AI RESEARCH
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
arXiv CS.LG
•
ArXi:2605.15055v1 Announce Type: new Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task