Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control
Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control
This research proposes a JEPA-style world model with bilinear parameterization of latent dynamics, enabling efficient planning and control. The structured approach allows for action recoverability and prevents representation collapse, demonstrating success in both long-horizon planning and real-time control tasks.
Evidence and limits
Published automatically after robotics and source-evidence checks; no manual editorial approval is recorded. Source assertions are not independently verified. Missing information remains not reported.
- Environment:
- Not reported
- Control:
- Not reported
- Data origin:
- Not reported
- dataset: Not reported
Source excerpts and review record
No manual editorial approval recorded.
Original source quotation: “In this work, we propose a JEPA-style world model in which, rather than learning arbitrary latent dynamics, we restrict them to follow a bilinear parameterization.”
Source E1
Source：arXiv Robotics — research abstracts · arxiv.org