arXiv Machine Learning By \v{Z}iga Kova\v{c}i\v{c}, Kevin Ellis

MPMWorlds: Material-Point-Method Simulations for Inferring and Extrapolating Physical Dynamics

Read the original on arXiv Machine Learning →

arXiv:2606. 01538v1 Announce Type: cross Abstract: To study the ability to infer physical dynamics from videos and extrapolate them forward in time, we assemble a dataset of 2D Material Point Method (MPM) physical simulations covering rich physical phenomena such as deformable objects, fluids, kinetic objects, and emitters.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 29

Physics-Grounded Fluid Video Generation with a Simulation Dataset and Dual-Stream Optical-Flow Supervision

arXiv:2607. 25321v1 Announce Type: new Abstract: Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns break apart in mid-air, container water levels fail to rise as liquid is poured in, and splashes disperse without regard to momentum or gravity.

By Ruijie Su, Yuanzhi Liang, Xiaohua Xie, Jianhuang Lai
Hugging Face Trending Papers
Jul 21

Learning Explicit Physical Parameter Control and Benchmarking for Video Generation

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.