Live
DreamX model released
Trending storyPast story
DreamX model released
1 reports1 outlets15 days agoUpdate
The story so far
AI overview
DreamX uses pre-trained video diffusion models to learn compact, appearance-invariant latent actions, enabling cross-subject transfer and efficient policy learning. DreamX extracts latent actions from the rich spatiotemporal features of video models, compressing each frame 300 times (1200→4 tokens).
AI-written from the reports · Updated 15 days ago
Latest4 Nov, 08:00
DreamX: Video Diffusion Model as a Universal Latent Action LearnerCoverage timeline
Follow the coverage to see every side of the story.
4 Nov
- Hugging Face Daily PapersDreamX: Video Diffusion Model is a Universal Latent Action Learner
DreamX uses pre-trained video diffusion models to learn compact, appearance-invariant latent actions, achieving cross-subject transfer and efficient policy learning. DreamX extracts latent actions from the rich spatiotemporal features of the video model, compressing each frame 300 times (1200→4 tokens).