Yizhi Li

💍📖💻🐶⛰️🤿.

prof_pic.jpg

w/ Jolly at Llandudno, Wales, 2023

I am currently a Computer Science PhD student funded by the University of Manchester, supervised by Prof. Chenghua Lin. I am also a co-founder of the Multimodal Art Projection (M-A-P) research community, which aims to drive open-source academia-level research to cutting-edge level as the industry. I’ve collaborated with Dr. Jie Fu and had a lot fun.


Research

My current research study involves post-training of LLMs and multi-modal alignment, and the research questions including:

  • How to build an effective and robust self-evolved framework for LLMs with data synthesis (maingly during post-trianing)? Deriving important sub questions:
    1. What is a good criteria for evaluating what the model acutally understand?
    2. How to verify the quality of the generated contents, considering domain knowledge and general metrics?
  • How to unifiy the understanding and generation of vision-langauge models?
  • The paradgim of aligning model among the text, vision and audio modalities.

Before the LLM era, my research interests could be concluded as these topics: language model evaluation, information retrieval, fairness in NLP, music modelling, and general topics natural language modelling. More recent and detailed topics can be referred to my publication pages.


Passed Experience

Academic Service: reviewer at ACL, EACL, EMNLP, INLG, ISMIR, ICLR, ICASSP, NeurIPS.

news

May 30, 2024 Four papers are accepted by the ACL’24.
Jan 16, 2024 MERT is accepted by ICLR’24.
Dec 1, 2023 M-A-P models at Hugging Face achieve over 50K+ monthly downloads.
Nov 7, 2023 MARBLE is accepted by NeurIPS’23.
Oct 8, 2023 LA(SER)^3 is accepted by EMNLP’23.
Aug 15, 2023 Gave a talk at AI Time (Chinese), with over 20K+ views.
Jun 27, 2023 Received the best student pitch at MultimodalAI’23 workshop.
Jun 23, 2023 Two papers accepted by the ISMIR’23.
Jun 19, 2023 Successfully organized the Music and Audio Processing workshop hosted at HKUST.
Jun 2, 2023 Our work done with MAP was reported by the University of Sheffield News.
Nov 7, 2022 TranSHER is accepted by EMNLP’22.