Abstract
World models jointly learn latent representations and dynamics that predict how high-dimensional observations evolve under actions. 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. This structure enables efficient planning and control while shifting the modeling burden onto the encoder, encouraging richer representations that expose the controllable geometry of the system. In particular, this structured parameterization allows us to structurally enforce action recoverability, thereby preventing representation collapse by construction. Although prescribing a bilinear parametrization may appear restrictive, we show that a broad class of nonlinear dynamical systems admits a transformation under which the dynamics become bilinear. Empirically, we show across standard 2D and 3D control tasks that representations with bilinear-parameterized dynamics can be learned directly from high-dimensional observations, reducing planning time by nearly three orders of magnitude while retaining or even improving control accuracy. We also propose more demanding regimes of longer-horizon planning and real-time control, and demonstrate that our method succeeds in both, moving JEPA-style world models beyond short-horizon offline planning.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Pariente, A., Boero, I., Matni, N., & Ribeiro, A. (2026). Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control. https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control
MLA 9
Pariente, Antonio, et al. "Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control." https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control.
Chicago (author–date)
Pariente, Antonio, Ignacio Boero, Nikolai Matni, and Alejandro Ribeiro. 2026. "Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control." https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control.
Harvard
Pariente, A., Boero, I., Matni, N. and Ribeiro, A. (2026) 'Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control', Available at: https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control.
Vancouver
Pariente A, Boero I, Matni N, Ribeiro A. Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control. https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control
IEEE
A. Pariente, I. Boero, N. Matni, and A. Ribeiro, "Bilinear World Models: Learning Representations with Structured Dynamics for Efficient Control," https://omanscience.com/en/articles/bilinear-world-models-learning-representations-with-structured-dynamics-for-efficient-control.