DreamX extracts 300x compressed latent actions from pretrained video diffusion models, enabling any-to-any video transfer and zero-shot action transfer across embodiments.
DreamX extracts compact latent actions from video diffusion models for transfer across embodiments and environments.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 749 readers · 886 views · 290 reads · all time 187K views