Views
No views yet
1 @misc{zhang2024visualquestiondecompositionmultimodal,
2 title={Visual Question Decomposition on Multimodal Large Language Models},
3 author={Haowei Zhang and Jianzhe Liu and Zhen Han and Shuo Chen and Bailan He and Volker Tresp and Zhiqiang Xu and Jindong Gu},
4 year={2024},
5 eprint={2409.19339},
6 archivePrefix={arXiv},
7 primaryClass={cs.CL},
8 url={https://arxiv.org/abs/2409.19339},
9}