Future Representation Distillation for Imagination-free World Action Models
DR E A M FR E E distills a video diffusion model's knowledge into current-observation features, delivering faster robot control and promising video-only task transfer.
ls ./papers | grep "#video diffusion models"
Trending AI research papers from Hugging Face, summarized in plain language: what each paper does, why it matters and where to read more.
2 papers · #video diffusion models
DR E A M FR E E distills a video diffusion model's knowledge into current-observation features, delivering faster robot control and promising video-only task transfer.
Wave Forcing combines causal wavefront denoising, specialized training, and multi-GPU runtime scheduling to make long-video generation faster without sacrificing stability.