WEAVER: Better, Faster, Longer: An Effective World Model for Robotic Manipulation
Presents an action-conditioned latent world model for future-state prediction, multi-view decoding, and latent-space planning.
Evidence notes
- Focuses on fidelity, long-horizon consistency, and fast inference through sparse memory, KV caching, and rectified flow.
- Project page reports policy evaluation, policy improvement, and test-time planning results on DROID/OOD manipulation data.
Company context
Research university with robotics groups publishing robot-learning hardware, manipulation research and open-source robotic hand resources.