This paper improves autoregressive video distillation methods by aligning the initialization and distribution matching stages, focusing on matching the target distribution's mode coverage rather than just visual quality. Practitioners can benefit from this approach to generate higher-quality videos with better diversity and coverage.
Firehose
Filtered to Papers, tagged “autoregressive video models” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives