Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation
Interactive autoregressive video generation demands both low-latency rollouts and precise online control. Few-step distillation accelerates generation by reducing denoising steps, while online control imposes a causal constraint: frames and blocks should depend on history and controls available during generation. Existing video distribution matching distillation (DMD) pipelines, however, often supervise causal few-step students using bidirectional teachers that score complete clips. The score for a target can therefore depend on future frames and controls that were unavailable when the student generated it, misaligning teacher supervision with the student's causal information set. We intr...
| Authors | Hmrishav Bandyopadhyay, Xuanchi Ren, Zijian Huang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 13 August 2026 |
| Last updated at source | 13 August 2026 |
Connected in the knowledge graph
- nvidia/cmdModel · cited by
Models and datasets referencing this paper
- nvidia/cmdModel
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 Information may be incomplete or out of date.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.