The authors study streamable video diffusion models that generate successive chunks while conditioning on a sliding window of previously generated frames.
Independent chunk scoring reduces drift in long autoregressive video rollouts
The authors separate per-chunk visual correction from sequence-level temporal refinement, improving quality well beyond the model’s five-second training horizon.
Chinese Tech
Chenjian Gao · Zhihao Hu · Jianqi Ma · Jun Zhang · Weidong Zhang · Tianfan Xue
MMLab · The Chinese University of Hong Kong · Tencent AIPD
Research Digest··2 min read
Gao et al.
Why this paper
From Tencent AIPD and 2 others
In one line
Rollout-Marginal Distillation scores each generated chunk independently against a teacher, then refines temporal coherence, preventing error accumulation in long autoregressive video generation.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (3 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§