{"ID":5675264,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01938","arxiv_id":"2607.01938","title":"PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation","abstract":"Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action models and world models struggle with accurate 3D geometry and physically meaningful forecasting. We propose PhysMani, a framework that couples a physics-principled 3D Gaussian world model with a future-aware action policy model. The world model learns a divergence-free Gaussian velocity field via online optimization for fast and physically grounded future dynamics prediction. The policy model integrates the predicted 3D scene future dynamics through a learnable token based cross-attention module. We introduce PhysMani-Bench, a dynamic manipulation benchmark with 16 tasks, and demonstrate a superior success rate over strong baselines in both simulation and real-world robot experiments.","short_abstract":"Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action models and world models struggle with accurate 3D geometry and physically meaningful forecasting. We propose PhysMani, a framework that couples a physics-principled 3D Ga...","url_abs":"https://arxiv.org/abs/2607.01938","url_pdf":"https://arxiv.org/pdf/2607.01938v1","authors":"[\"Peng Yun\",\"Shouwang Huang\",\"Hao Li\",\"Jinxi Li\",\"Jianan Wang\",\"Bo Yang\"]","published":"2026-07-02T09:32:39Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CL\",\"cs.CV\",\"cs.LG\"]","methods":"[]","has_code":false}