Neural Voxel Dynamics introduces a self‑supervised framework that learns 3D latent dynamics from monocular video by unprojecting V‑JEPAs features into a voxel grid using depth priors. It then applies Volumetric Feature Advection, an action‑conditioned transition model, to predict the evolution of these latent features directly in 3D, without relying on privileged physics‑engine states. The method is evaluated on synthetic and real datasets, demonstrating predictive fidelity, 3D geometric consistency, and physical plausibility via Physics‑IQ metrics.
arXiv:2608.31025v1 Announce Type: new Abstract: Inferring object dynamics from visual observations is essential for intelligent agents to reason about and interact with the physical world, yet remain...
Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high-resolution 3D volumetric meshes is difficult: au...
arXiv:2610.07609v1 Announce Type: new Abstract: Neural simulation of high-fidelity deformable bodies is a foundational challenge in computer graphics and physical AI. Long-horizon prediction for high...
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by the high cost of action annotations and the heterogeneity of action spaces across platforms.
arXiv:2503. 24009v3 Announce Type: replace-cross Abstract: Realistic simulation is critical for applications ranging from robotics to animation.
arXiv:2610.08780v1 Announce Type: cross Abstract: World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and p...
Recent advances in image-to-video generation have improved visual realism, making physically grounded and controllable dynamics an important step toward future world simulation. Current models often generate plausible motion, but it is not reliably governed by explicit physical causes, and instance-level constraints can leak or become entangled in multi-object interactions.
arXiv:2605. 08832v3 Announce Type: replace Abstract: Neural surrogate models for computational fluid dynamics (CFD) are typically trained as forward operators that map explicit problem specifications, such as geometry and boundary conditions, to solution fields.
PhysPlan is a training‑free guidance framework that enhances video diffusion models by incorporating physical awareness through agentic physics simulation. It uses a vision‑language model to generate a Chain‑of‑Visual‑Thought representation of kinematic trajectories and 3D depth, which then drives an object‑centric test‑time optimization that isolates kinematic changes and locks the passive environment. The framework also employs Kinetic Intensity Profiling to adapt hyperparameters to varying physical deformations, and demonstrates superior performance on PhyGenBench and Physics‑IQ benchmarks compared to existing VDM baselines.
World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depend on faithful 3D ge...
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
arXiv:2603. 03485v3 Announce Type: replace-cross Abstract: Recent video diffusion models have achieved impressive capabilities as large-scale generative world models.