[
    {
        "id": "osp-14948",
        "type": "article-journal",
        "title": "LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC",
        "author": [
            {
                "family": "Hegde",
                "given": "Shashank"
            },
            {
                "family": "Popov",
                "given": "Alexander"
            },
            {
                "family": "Aljalbout",
                "given": "Elie"
            },
            {
                "family": "Smolyanskiy",
                "given": "Nikolai"
            }
        ],
        "URL": "https://omanscience.com/ar/articles/lewam-a-jepa-world-action-model-with-diffusion-steering-based-mpc",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]