@InProceedings{Xu_2025_ICCV, author = {Xu, Guowei and Jin, Peng and Wu, Ziang and Li, Hao and Song, Yibing and Sun, Lichao and Yuan, Li}, title = {LLaVA-CoT: Let Vision Language Models Reason Step-by-Step}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2025}, pages = {2087-2098} }