PhysInOne is a new dataset of 2 million videos across 153,810 dynamic 3D scenes covering 71 physical phenomena, shown to improve AI performance on physics-aware video generation, prediction, property estimation, and motion transfer.
Intphys 2: Benchmarking intuitive physics understanding in complex synthetic environments
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
baseline 1
citation-polarity summary
representative citing papers
YoCausal benchmark shows video diffusion models detect the arrow of time but lack genuine causal understanding relative to humans.
CRONOS benchmark shows recent open-source video generators fail to preserve physical consistency under controlled changes to viewpoint, scene, object category, and appearance.
Temporal information in Video-LLMs is encoded well by video-centric encoders but disrupted by standard projectors; time-preserved MLPs plus AoT supervision yield 98.1% accuracy on arrow-of-time and gains on other temporal tasks.
TIME is a motion-based embedding from point tracks, trained only on synthetic data via masked autoencoding, that matches state-of-the-art video model performance with up to 10,000x less training data.
VisPhyWorld evaluates MLLMs' physical reasoning via executable code generation for video reconstruction, with VisPhyBench showing strong semantics but weak parameter inference and dynamics simulation.
Video foundation models infer dynamic physical properties such as elasticity, viscosity, and friction from videos at levels close to classical oracles while outperforming current MLLMs with suitable prompting.
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.