Metraipolis › archive › dc_c2d978359475

Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation — arXiv:2608.13391

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13391
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:54.541Z
SHA-256 of the archived text
11dede089d1974782828777360fb8356a1ed2774b5d9f4508725f490193bd364
Stable URL of this page
https://metraipolis.com/documento/dc_c2d978359475

How to cite

Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation — arXiv:2608.13391 — arXiv (en), https://arxiv.org/abs/2608.13391 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2d978359475 (Metraipolis archive dc_c2d978359475, sha256 11dede089d1974782828777360fb8356a1ed2774b5d9f4508725f490193bd364)
BibTeX
@misc{dcc2d978359475,
  title = {Context-Matched Distillation: Teacher Causality for Autoregressive Video Distillation — arXiv:2608.13391},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13391},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2d978359475; sha256 11dede089d1974782828777360fb8356a1ed2774b5d9f4508725f490193bd364},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13391. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 introduce Context-Matched Distillation (CMD), a causal DMD framework that aligns teacher supervision with the information available when each target is generated. CMD replaces bidirectional full-clip scoring with a causal teacher that evaluates each target without access to future frames or controls. The same causal teacher initializes the few-step student, establishing a consistent causal formulation across teacher training, student distillation, and inference. Beyond aligning the temporal information boundary, Prefix Scoring matches supervision to the student's realized rollout context by evaluating each target under the cached student-generated prefix that produced it. Prefix Corruption further stabilizes training by perturbing unreliable prefixes produced early in training while preserving this target-context alignment. With a simple causal formulation, CMD naturally extends to frame-wise and chunk-wise generation, long video distillation, and camera-conditioned distillation. Experiments demonstrate state-of-the-art aggregate performance among autoregressive methods on both short- and long-video benchmarks, together with substantially improved adherence to time-varying camera controls.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13391 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:46:30.244Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).