The authors distilled a pretrained bidirectional video diffusion teacher into a causal, few-step generator.
Two denoising experts make video diffusion distillation far more efficient
Glance Forcing converts a bidirectional video diffusion model into a few-step autoregressive generator using just one costly teacher trajectory.
Top University
Zhuobai Dong · Junchao Yi · Hu Jian Guo · Linjie Li · Rui Zhao · Alex Jinpeng Wang
Wuhan University · University of Electronic Science and Technology of China · Sun Yat-sen University · University of Washington · National University of Singapore
Research Digest··2 min read
Dong and colleagues investigate whether autoregressive video diffusion models really need large collections of precomputed denoising trajectories for distillation.
Why this paper
From Sun Yat-sen University and 5 others
In one line
Glance Forcing distills bidirectional video diffusion into a few-step autoregressive model using one PF-ODE trajectory, outperforming a fully trained baseline at far lower collection cost.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§