DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.
Direct Reward Gradient In this section, we discuss in details why the direct reward gradient methods like ReFL [67] and DRaFT [8], cannot fit into the memory efficiently
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization
DOLLAR combines variational score and consistency distillation for few-step video generation plus latent reward optimization, reporting 82.57 VBench score and up to 278x speedup over the teacher diffusion model for 128-frame 10-second videos.