AI RESEARCH
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
arXiv CS.CV
•
ArXi:2412.15689v2 Announce Type: replace Diffusion probabilistic models have shown significant progress in video generation; however, their computational efficiency is limited by the large number of sampling steps required. Reducing sampling steps often compromises video quality or generation diversity. In this work, we