PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding

Recommended citation: @inproceedings{tri-physbench, author={Wei Chow and Jiageng Mao and Boyi Li and Daniel Seita and Vitor Guizilini and Yue Wang}, title={PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding}, booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)}, year={2025} }