Yijiang (William) Li

I’m Yijiang 1 (William) Li, a first-year PhD student in Machine Learning and Data Science, Electrical and Computer Engineering at UC San Diego.

My research focuses on the learning aspects of AI - to enable efficient (e.g. label efficiency ICCV23, CVPR23, sample effiency AAAI25, Wasserstein DD, and synthetic data) and robust learning (ICCV23, TMLR) in multi-modal (ICLR25, video-llm), interactive and 3D embodied environments. Particularly, I am interested in


  • Understanding and evaluating Multi-modal Large Language models (MLLMs), e.g. core-knowledge;
  • Can language (in nature semantic, abstracted and compositional) be used to scaffold vision learning (e.g. as anchor representation)?
  • Intrinsic 3D world: 3D-aware architecture for MLLMs, 3D representation emergence from 2D supervision, etc.
  • Embodiment theory, learning with indirect feedback (usually in social scenarios) and interactive learning (learn and inference simultaneously).

I am also broadly interested in the various applications of AI, e.g. LLM Agents (MAS), AI4Sci and AI4Health.

Bio     Contact     Github     G. Scholar     LinkedIn     Twitter    

Hi there, visitor . Welcome to my virtual home!

2025.04

Invited talk to @ploutosai on "Growing AI Like a Child"

2025.01

🎉 One paper accepted by ICLR 2025.

2024.12

🎉 One paper accepted by AAAI 2025.

2024.10

🎉 One paper accepted by TMLR. Check out here!

2024.09

I started my PhD in Machine Learning and Data Science at UC San Diego!

2023.10

Code for our ICCV 20203 paper "Diverse Co-training" is now available here on GitHub.

2023.10

🎉 Two papers accepted by ICCV 2023, including one first-author paper.

2023.06

🎉 Consistent-Teacher is presented at CVPR 2023 as Highlight (top 2.5%).

2023.02

I started my M.S.E. in Computer Science at Johns Hopkins University!

2022.06

🎉 My first first-author paper ”More than encoder" is presented at BIBM 2022!

2022.06

🎉 Awarded the outstanding thesis award.

2022.05

I graduated from the South China University of Technology.
https://arxiv.org/abs/2310.00616

Towards Understanding Adversarial Transferability in Federated Learning

Yijiang Li, Ying Gao, Haohan Wang
Transactions on Machine Learning Research
Paper

https://arxiv.org/abs/2403.05523

Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation.

Yijiang Li, Sucheng Ren, Weipeng Deng, Yuzhi Xu, Ying Gao, Haohan Wang
Preprint. Paper under review
Paper

https://arxiv.org/pdf/2403.10045

Towards Adversarially Robust Dataset Distillation by Curvature Regularization

Eric Xue, Yijiang Li, Haoyang Liu, Peiran Wang, Yifan Shen, Haohan Wang
AAAI Conference on Artificial Intelligence 2025
Paper

Dataset distillation via the wasserstein metric

Haoyang Liu, Yijiang Li, Tiancheng Xing, Vibhu Dalal, Luwei Li, Jingrui He, Haohan Wang
Preprint. Paper under review
Paper

Diverse co-training makes strong semi-supervised segmentor

Yijiang Li, Xinjiang Wang, Lihe Yang, Litong Feng, Wayne Zhang, Ying Gao
International Conference on Computer Vision (ICCV) 2023
Paper  •   Code

Multi-metrics adaptively identifies backdoors in federated learning

Siquan Huang, Yijiang Li, Chong Chen, Leyu Shi, Ying Gao
International Conference on Computer Vision (ICCV) 2023
Paper  •   Code

Consistent-teacher: Towards reducing inconsistent pseudo-targets in semi-supervised object detection

Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang
Computer Vision and Pattern Recognition (CVPR) 2023 ★ Highlight (Top 2.5%) ★
Webpage  •   Paper  •   Code

More than encoder: Introducing transformer decoder to upsample

Yijiang Li, Wentian Cai, Ying Gao, Chengming Li, Xiping Hu
IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2022
Paper

Beijing Academy of Artificial Intelligence

Intern Researcher | June. 2024 – Oct. 2024
Video Large Language Model

Sensetime Research

Intern Researcher | Jul. 2021 – Nov. 2022
Sample efficient learning (semi- and weakly-supervised learning)

WeBank

Machine Learning Engineer | Jun. 2020 - Sep. 2020
Large-scale Public Sentiment and Risk Control

University of California San Diego

Ph.D. in Machine Learning and Data Science, Electrical and Computer Engineering
Oct. 2024 - Present
GPA: 3.94 / 4.0

Johns Hopkins University

M.S.E. in Computer Science | Jan. 2023 - June. 2024
GPA: 4.0 / 4.0

South China University of Technology

B.E. in Computer Science | Sep. 2018 – Jul. 2022
GPA: 3.73 / 4.0
2018-19 Scholarship
Outstanding Thesis Awards

The Affiliated High School of South China Normal University

High School Diploma | Sep. 2015 – Jul. 2018

Reviewer

2025
Reviewer, ICML 2025, CVPR 2025, AISTATS 2025, ICLR 2025
2024
Reviewer, NeurIPS 2024

Teaching Assistant

EN.553.436/636 Introduction to Data Science (Fall 2023)

Teaching Assistant | Instructor: Prof. Tamás Budavári


EN 601.482/682 Machine Learning: Deep Learning (Fall 2023)

Course Assistant | Instructor: Prof. Mathias Unberath


EN.553.436/636 Introduction to Data Science (Spring 2023)

Teaching Assistant | Instructor: Prof. Tamás Budavári, Prof. Soledad Villar

Chat?

I am happy to discuss collaborations and chat about research. Please select a time slot and drop me a note below.



Football

I love playing football and enjoy being part of the Football Varsity Team of School of Computer Science and Engineering. Check out the trophies we won (left) and our team (right)!



team photo on the pitch trophies we won

Travel

Check out some pics from my travel! Here are Meili Snow Mountains(left) and Humble Administrator’s Garden(right).



Meili Snow Mountains Humble Administrator’s Garden