Skip to content
NewA calmer, faster ZeroHour

MovieRoll framework extends streaming video beyond its training length

Original title: MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos

Hugging Face daily papersby Yunyang Ge, Weijie Kong, Ryan Xu ()1 min read
AI summary · x-ai/grok-4.7Summaries by Vani AI

On HeliosBench, the distilled model posts the highest compared scores for clips up to 60 seconds after training on videos of at most 15 seconds.

MovieRoll is a base-to-distilled framework for streaming video that combines window-wise teacher forcing, hierarchical KV-cache compression, and cumulative long tuning with distribution matching distillation. Hierarchical compression is reported to cut cache memory by up to 78% while improving quality. KV recomputation and guidance annealing are used to generate past the training horizon. The paper says MovieRoll-Base stays competitive at 30 seconds and MovieRoll-Distilled leads the compared methods through 60 seconds.

Unconfirmed: Quality and memory figures are the authors' HeliosBench results, not an independent evaluation.

Key facts
  • Training videos are at most 15 seconds; evaluation runs to 30 and 60 seconds.
  • HieraKV keeps full history in shallow layers and sink-recent history deeper.
  • CuLT-DMD averages local gradients while holding parameters fixed during each rollout.
  • FBCA attention and PS-VAE decoding support training and streaming output.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-tuning, long-rollout distillation, and long-horizon inference.

Hugging Face daily papers

By Yunyang Ge, Weijie Kong, Ryan Xu · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.