@article{dvsftdirectvisionsupervisionforfinegrain, title = {DV-SFT: Direct Vision Supervision for Fine-Grained Visual Understanding}, author = {Jianfei Zhao and Feng Zhang and Xin Sun and Chong Feng and Bing Wang and Zhixing Tan}, year = {2026}, eprint = {2605.26656}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.26656}, }