DreamX: video diffusion models as universal latent action learners for robots
kaist-ai · hf · 2026-11-04
KAIST and NVIDIA propose DreamX, leveraging pretrained video diffusion models to learn compact, appearance-invariant latent actions from human egocentric and robot videos. The universal latent action space enables cross-embodiment video/action transfer and efficient policy learning.
More from Embodied
- Baidu's Apollo Go wraps two-week public robotaxi test rides in Tung Chung, Hong Kong — Baidu_Inc · 2026-11-04
- imec neural probe integrates photonics directly into 130nm CMOS backend — jwt0625 · 2026-11-04
- Chris Paxton: interactive robot sim is the future but glaringly data-limited — Scobleizer · 2026-11-04
- RoboTryOn turns human videos into robot demos, lifting success rate from 2% to 60% — kaist-ai · 2026-11-04
- INMO Future glasses: dual 1080p displays, 125g, $799 early-bird on Kickstarter Dec 10 — Scobleizer · 2026-11-04
- DISCO distilled tree search named CoRL 2026 best-paper finalist, top 6 of 687 — yining_hong · 2026-11-04