PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
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 thr
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 60%Gradient-based Planning for World Models at Longer Horizons →
- PossiblePossibly related (embedding) · 48%grandgaming9321-prog/reality-engine →
- LinkedLinked via arxiv author · 85%Peng Yun →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”
- LinkedLinked via arxiv author · 85%Shouwang Huang →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”
- LinkedLinked via arxiv author · 85%Zhenghao Liu →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”
- LinkedLinked via arxiv author · 85%Jinxi Li →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”
- LinkedLinked via arxiv author · 85%Jianan Wang →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”
- LinkedLinked via arxiv author · 85%Bo Yang →
“PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation”