Generalized Dynamics Generation towards Scannable Physical World Model

• URL: http://arxiv.org/abs/2510.15041v1
• Date: Thu, 16 Oct 2025 18:00:58 GMT
• Title: Generalized Dynamics Generation towards Scannable Physical World Model
• Authors: Yichen Li, Zhiyi Li, Brandon Feng, Dinghuai Zhang, Antonio Torralba,
• Abstract summary: We present GDGen, a framework that takes a potential energy perspective to seamlessly integrate rigid body, articulated body, and soft body dynamics.<n>We extend classic elastodynamics by introducing directional stiffness to capture a broad spectrum of physical behaviors.<n>We propose a specialized network to model the extended material property and employ a neural field to represent deformation in a geometry-agnostic manner.
• Score: 35.123614858826066
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Digital twin worlds with realistic interactive dynamics presents a new opportunity to develop generalist embodied agents in scannable environments with complex physical behaviors. To this end, we present GDGen (Generalized Representation for Generalized Dynamics Generation), a framework that takes a potential energy perspective to seamlessly integrate rigid body, articulated body, and soft body dynamics into a unified, geometry-agnostic system. GDGen operates from the governing principle that the potential energy for any stable physical system should be low. This fresh perspective allows us to treat the world as one holistic entity and infer underlying physical properties from simple motion observations. We extend classic elastodynamics by introducing directional stiffness to capture a broad spectrum of physical behaviors, covering soft elastic, articulated, and rigid body systems. We propose a specialized network to model the extended material property and employ a neural field to represent deformation in a geometry-agnostic manner. Extensive experiments demonstrate that GDGen robustly unifies diverse simulation paradigms, offering a versatile foundation for creating interactive virtual environments and training robotic agents in complex, dynamically rich scenarios.

Related papers

• Advancing Opinion Dynamics Modeling with Neural Diffusion-Convection-Reaction Equation [13.884804908187391]
  We present the OPINN, a physics-informed neural framework for opinion dynamics modeling.<n>Building upon the Neural ODEs, we define the neural opinion dynamics to coordinate neural networks with physical priors.<n> OPINN achieves state-of-the-art performance in opinion evolution forecasting.
  arXiv  Detail & Related papers  (2026-02-05T07:41:19Z)
• Aligning Agentic World Models via Knowledgeable Experience Learning [68.85843641222186]
  We introduce WorldMind, a framework that constructs a symbolic World Knowledge Repository by synthesizing environmental feedback.<n>WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
  arXiv  Detail & Related papers  (2026-01-19T17:33:31Z)
• Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems [38.4555621948915]
  Prismatic World Model (PRISM-WM) is designed to decompose complex hybrid dynamics into composable primitives.<n>PRISM-WM significantly reduces rollout drift by accurately modeling sharp mode transitions in system dynamics.
  arXiv  Detail & Related papers  (2025-12-09T09:40:34Z)
• ProPhy: Progressive Physical Alignment for Dynamic World Simulation [55.456455952212416]
  ProPhy is a Progressive Physical Alignment Framework that enables explicit physics-aware conditioning and anisotropic generation.<n>We show that ProPhy produces more realistic, dynamic, and physically coherent results than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-05T09:39:26Z)
• Geometric Contact Flows: Contactomorphisms for Dynamics and Control [16.973611363085624]
  This paper introduces Geometric Contact Flows (GFC), a novel framework to learn complex systems.<n>GFC constructs a latent contact Hamiltonian model encoding desirable properties like stability or energy conservation.<n>Experiments on learning dynamics for physical systems and for controlling robots on interaction tasks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-06-22T01:52:21Z)
• MetaSym: A Symplectic Meta-learning Framework for Physical Intelligence [8.047222674695288]
  We introduce a novel deep learning framework, MetaSym.<n>In particular, MetaSym combines a strong symplectic inductive bias obtained from a symplectic encoder, and an autoregressive decoder with meta-attention.<n>This principled design ensures that core physical invariants remain intact, while allowing flexible, data-efficient adaptation to system heterogeneities.
  arXiv  Detail & Related papers  (2025-02-23T17:52:07Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.<n>We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter.<n>In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics [48.99021224773799]
  We propose the Neural Material Adaptor (NeuMA), which integrates existing physical laws with learned corrections. We also propose Particle-GS, a particle-driven 3D Gaussian Splatting variant that bridges simulation and observed images.
  arXiv  Detail & Related papers  (2024-10-10T17:43:36Z)
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems [74.80320120264459]
  We present an approach to learn such motions from a limited number of human demonstrations. The complex motions are encoded as rollouts of a stable dynamical system. The efficacy of this approach is demonstrated through validation on an established benchmark as well demonstrations collected on a real-world robotic system.
  arXiv  Detail & Related papers  (2020-05-27T03:51:57Z)
• Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control [14.24939133094439]
  We introduce Symplectic ODE-Net (SymODEN), a deep learning framework which can infer the dynamics of a physical system. In particular, we enforce Hamiltonian dynamics with control to learn the underlying dynamics in a transparent way. This framework, by offering interpretable, physically-consistent models for physical systems, opens up new possibilities for synthesizing model-based control strategies.
  arXiv  Detail & Related papers  (2019-09-26T13:13:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.