$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation
- Published
- Source
- arXiv
- Paper number
- 834
- Field
- Robotics
- arXiv ID
- 2608.06375
Key points
- We trained full-body cooperative motion in one model without separating locomotion and manipulation.
- Instead of future video generation, we improved action quality using latent embedding prediction, a lightweight world model.
- We built and released omega-HOME, a 40-hour real-home humanoid dataset.
- It performs 11 household tasks with a single model and outperforms prior imitation learning, VLA, and WAM methods.
- We propose a pipeline that converts human video data into robot-executable actions through simulation replay.
Paper links
External research summaries. These are not HDATF publications or measured product results.