@article{instructsequnifyingvisiontaskswith,
  title = {InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation},
  author = {Rongyao Fang and Shilin Yan and Zhaoyang Huang and Jingqiu Zhou and Hao Tian and Jifeng Dai and Hongsheng Li},
  year = {2023},
  eprint = {2311.18835},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.18835v1},
}