@article{institboostingmultimodalinstance, title = {Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning}, author = {Wujian Peng and Lingchen Meng and Yitong Chen and Yiweng Xie and Yang Liu and Tao Gui and Hang Xu and Xipeng Qiu and Zuxuan Wu and Yu-Gang Jiang}, year = {2024}, eprint = {2412.03565}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.03565v1}, }