analiza aiqbench
LeWAM introduces a bidirectional transformer architecture for World Action Models (WAMs) that leverages decoder-free JEPA latents to improve state alignment, policy acting, and planning efficiency. By enabling end-to-end training across forward, backward, inverse dynamics, and policy prediction modes, this approach reduces noisy redundancy in latent representations while enhancing closed-loop performance in robotics tasks. The method demonstrates how integrating diffusion-steering-based Model Predictive Control (MPC) can better exploit dynamics-model inaccuracies compared to traditional reconstruction-based approaches.
LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
arXiv:2610.12407v1 Announce Type: cross Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream predictions. We introduce LeWAM, a bidirectional transformer for forward, backward, inverse dynamics and policy prediction, on a decoder-free JEPA latent trained end-to-end through all four modes. We see the following benefits: 1) Alignment: linear probes read robot and object state from LeWAM's latent better than from a regular Le World Model (a forward-only JEPA world model), while the latent ignores visual distractors as well as LeWM does and far better than a reconstruction-based WAM. 2) Acting: Closed-loop evaluations of LeWAM match a regular flow-matching policy trained on the same encoder at matched size, while also providing a world model. 3) Planning: Sampling raw actions when planning with WAMs lets MPC exploit dynamics-model inaccuracies; planning in the noise space of the policy head instead improves the closed-loop performance of these WAMs.
Abstract:World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream predictions. We introduce LeWAM, a bidirectional transformer for forward, backward, inverse dynamics and policy prediction, on a decoder-free JEPA latent trained end-to-end through all four modes. We see the following benefits: 1) Alignment: linear probes read robot and object state from LeWAM's latent better than from a regular Le World Model (a forward-only JEPA world model), while the latent ignores visual distractors as well as LeWM does and far better than a reconstruction-based WAM. 2) Acting: Closed-loop evaluations of LeWAM match a regular flow-matching policy trained on the same encoder at matched size, while also providing a world model. 3) Planning: Sampling raw actions when planning with WAMs lets MPC exploit dynamics-model inaccuracies; planning in the noise space of the policy head instead improves the closed-loop performance of these WAMs.
Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
arXiv:2610.12407 [cs.RO]
(or arXiv:2610.12407v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.12407 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 255 cuvinte
Subiecte conexe
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
Latent evolving World Action Model
arXiv · 25 sept. 2026
LeRobot v0.6.0: Imagine, Evaluate, Improve
Hugging Face · 7 iul. 2026
Diffusion Transformer World-Action Model for AV Scene Prediction
arXiv · 12 iun. 2026