datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
IntPhys2
IntPhys 2
Dataset |
Hugging Face |
Paper |
Blog
IntPhys 2 is a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original IntPhys benchmark, IntPhys 2 focuses on four core principles related to macroscopic objects: Permanence, Immutability, Spatio-Temporal Continuity, and Solidity. These conditions are inspired by research into intuitive physical understanding emerging during early childhood. IntPhys 2… See the full description on the dataset page: https://huggingface.co/datasets/facebook/IntPhys2.IntPhys2VideoZeroShot
IntPhys2VideoZeroShot
An MTEB dataset
Massive Text Embedding Benchmark
Classify synthetic videos as physically possible or impossible across permanence, immutability, continuity, and solidity conditions.
This MTEB-formatted version contains all 1,012 videos from IntPhys2's official Main split. The four source variants are mapped to balanced physically possible and impossible classes (506 videos each).
Task category
VideoZeroshotClassification (video-to-text)
Domains… See the full description on the dataset page: https://huggingface.co/datasets/mteb/IntPhys2VideoZeroShot.IntPhys2VideoZeroShot
IntPhys2VideoZeroShot
An MTEB dataset
Massive Text Embedding Benchmark
Classify synthetic videos as physically possible or impossible across permanence, immutability, continuity, and solidity conditions.
This MTEB-formatted version contains all 1,012 videos from IntPhys2's official Main split. The four source variants are mapped to balanced physically possible and impossible classes (506 videos each).
Task category
VideoZeroshotClassification (video-to-text)
Domains… See the full description on the dataset page: https://huggingface.co/datasets/artist/IntPhys2VideoZeroShot.IntPhys2
IntPhys 2
Dataset |
Hugging Face |
Paper |
Blog
IntPhys 2 is a video benchmark designed to evaluate the intuitive physics understanding of deep learning models. Building on the original IntPhys benchmark, IntPhys 2 focuses on four core principles related to macroscopic objects: Permanence, Immutability, Spatio-Temporal Continuity, and Solidity. These conditions are inspired by research into intuitive physical understanding emerging during early childhood. IntPhys 2… See the full description on the dataset page: https://huggingface.co/datasets/4lph4v3rs3/IntPhys2.IntPhys2_directionintphys2IntPhys 2 dataset from:
@misc{bordes2025intphys2benchmarkingintuitive,
title={IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments},
author={Florian Bordes and Quentin Garrido and Justine T Kao and Adina Williams and Michael Rabbat and Emmanuel Dupoux},
year={2025},
eprint={2506.09849},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2506.09849},
}
BENCHMARK DATA SHOULD NEVER APPEAR IN… See the full description on the dataset page: https://huggingface.co/datasets/justinphan3110/intphys2.