Dongfu Jiang (姜东甫)

University of Waterloo; Vector Institute;


350 Columbia St. West

Waterloo, Ontario

I’m a first-year CS Ph.D. student at University of Waterloo, advised by Wenhu Chen. I received my bachelor degree in Computer Science at Zhejiang University, where I was fortunate to work closely with Prof. Zhao Zhou. I work closely with (Bill)Yuchen Lin.

My research focus on General Artificial Intelligence and their applications. I am particularly interested in understanding the behavior of LLMs and and multimodality reasoning, as well as their evaluation.


Apr 14, 2024 We release Mantis Mantis, enhancing LMM with Interleaved Multi-Image Instruction Tuning!
Apr 8, 2024 WildVision Arena has been accepted to CVPR 2024 demo track and will be presented at the conference!
Apr 5, 2024 Description of the image MMMU is accepted to CVPR 2024 oral presentation!
Feb 20, 2024 I am excited to announce that I will be joining AI2 Mosaic Team as a research intern this summer!
Feb 12, 2024 GenAI arena is now also online! You can test popular image generation/editing models here!

selected publications


  1. VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation
    Max W.F. Ku, Dongfu Jiang, Cong Wei, and 2 more authors
    In , 2023
  2. MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI
    Xiang Yue, Yuansheng Ni, Kai Zhang, and 19 more authors
    In , 2023
  3. TIGERScore: Towards Building Explainable Metric for All Text Generation Tasks
    Dongfu Jiang, Yishan Li, Ge Zhang, and 3 more authors
    ArXiv, 2023
  4. LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
    Dongfu Jiang, Xiang Ren, and Bill Yuchen Lin
    In ACL 2023, Jul 2023