@article{visualwebinstructscalingupmultimodal, title = {VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search}, author = {Yiming Jia and Jiachen Li and Xiang Yue and Bo Li and Ping Nie and Kai Zou and Wenhu Chen}, year = {2025}, eprint = {2503.10582}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.10582v1}, }