{"ID":6267660,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-11T16:11:27.930961336Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08436","arxiv_id":"2607.08436","title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","abstract":"Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task semantics, with non-transferable factors like human morphology, head motion, and behavioral style. We study whether World Action Models (WAMs) provide a better training signal by requiring policies to predict not only actions, but also how the scene evolves. The central question is what world representation best enables human-to-robot transfer. We hypothesize that an effective world target should abstract appearance, capture agent-invariant physical effects, and separate camera motion from environment change. We introduce EgoWAM, a controlled human-robot co-training framework that fixes the policy backbone, action head, and data mixture while varying only the world prediction target, comparing Pixel, DINO, and 3D motion flow. Across three real-world bimanual tasks, WAM co-training scales more effectively with in-the-wild egocentric human data than behavior cloning. Pixel-based prediction transfers weakly, while DINO and 3D flow yield substantial gains: DINO improves out-of-distribution object and scene generalization by up to 4x, and 3D flow improves in-domain performance by 20-30%. More details: https://gatech-rl2.github.io/egowam.github.io","short_abstract":"Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task semantics, with non-transferable factors like human morphology, head motion, and behavioral style. We study whether World Action Models (WAMs) provide a bette...","url_abs":"https://arxiv.org/abs/2607.08436","url_pdf":"https://arxiv.org/pdf/2607.08436v1","authors":"[\"Baoyu Li\",\"Xinchen Yin\",\"Mengying Lin\",\"Yixin Zhang\",\"Danfei Xu\"]","published":"2026-07-08T16:11:37Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}