Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning

@inproceedings{xu2024visionflan,
  title = {Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning},
  author = {Zhiyang Xu and Chao Feng and Rulin Shao and Trevor Ashby and Ying Shen and dingnan jin and Yu Cheng and Qifan Wang and Lifu Huang},
  year = {2024},
  booktitle = {Annual Meeting of the Association for Computational Linguistics},
  eprint = {2402.11690},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.11690},
}