GPWM: Modeling the World as 3D Particle Motion
Overview
This research presents GPWM, a generative particle world model that predicts how 3D scenes evolve by generating the motion of particles and rigid bodies over time. Unlike video-based world models that focus on appearance, GPWM operates directly in 3D physical space using a unified architecture for rigid, deformable, cloth, and granular materials. The model enables contact-rich planning by learning a generative prior over joint actuator-object motion, allowing open-loop execution in simulation for goal-directed manipulation tasks like pushing and picking without reference action trajectories.
Generated from attributed reports · Updated 2 days ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“sequences are hard to discover. Executed open-loop in simulation, the resulting plans achieve goal-directed manipulation without reference action trajectories or goal-specific policies.”
Exact source · revision 1Source owner not reported
Data origin: robot trajectories
“ysics and robotic interaction. GPWM is an object-aware multi-resolution transformer that combines flow matching with diffusion forcing to generate coherent physical trajectories far beyond its training horizon. We train and evaluate GPWM on ParticleWorlds, a 25.5-million-frame corpus spanning diverse geometries, materials, interactions, and robot embodiments. GPWM outperforms the best prior learned-dynamics baseline”
Exact source · revision 1Source owner not reported
Reported quantity · training frames: 25.5 other · Basis not reported
“ysics and robotic interaction. GPWM is an object-aware multi-resolution transformer that combines flow matching with diffusion forcing to generate coherent physical trajectories far beyond its training horizon. We train and evaluate GPWM on ParticleWorlds, a 25.5-million-frame corpus spanning diverse geometries, materials, interactions, and robot embodiments. GPWM outperforms the best prior learned-dynamics baseline”
Exact source · revision 1Source owner not reported
Reported quantity · physical domains: 6 other · Basis not reported
“in each of six physical domains, reducing prediction error by 31% on average. Breaking from the domain-specific setting of prior methods, a single Unified GPWM models these heterogeneous regimes with one set of weights, largely outperforming per-domain baselines and even surpassing our own specialist models in two domains. GPWM further generalizes to unseen geometries, physical properties, object counts, and rollout”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalGPWM: Modeling the World as 3D Particle Motion
This research presents GPWM, a generative particle world model that predicts how 3D scenes evolve by generating the motion of particles and rigid bodies over time. Unlike video-based world models that focus on appearance, GPWM operates directly in 3D physical space using a unified architecture for rigid, deformable, cloth, and granular materials. The model enables contact-rich planning by learning a generative prior over joint actuator-object motion, allowing open-loop execution in simulation for goal-directed manipulation tasks like pushing and picking without reference action trajectories.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).