DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Existing autoregressive video distillation methods commonly adopt a Distribution Matching Distillation (DMD)-based multi-stage pipeline. However, they typically decouple the initialization and DMD stages -- which then pursue different target distributions -- and judge the intermediate student mainly by visual scores such as VBench. In this paper, we revisit this design from a distributional perspective. Given the mode-seeking nature of the distribution matching loss, a good initialization should match the mode coverage of the target DMD teacher, rather than merely pursuing high quality. To analyze this, we introduce a distributional evaluation protocol that measures precision and coverage...
| Authors | Jiaxing Li, Kai Zou, Cindy Zhou et al. |
|---|---|
| Primary category | cs.CV |
| Published | 29 July 2026 |
| Last updated at source | 29 July 2026 |
Connected in the knowledge graph
- LiJiaxing/DistillAlign_1p3b_25KDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.