@misc{jin2024mmtomqa, title={MMToM-QA: Multimodal Theory of Mind Question Answering}, author={Chuanyang Jin and Yutong Wu and Jing Cao and Jiannan Xiang and Yen-Ling Kuo and Zhiting Hu and Tomer Ullman and Antonio Torralba and Joshua B. Tenenbaum and Tianmin Shu}, year={2024}, eprint={2401.08743}, archivePrefix={arXiv}, primaryClass={cs.AI} }