Yushun Zhang

Joined

May 2021

Names

Yushun Zhang (Preferred)

Emails

****@link.cuhk.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

School of Data Science, The Chinese University of Hong Kong, Shenzhen (cuhk.edu.cn)

2019 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

Optimization

Present

Publications

Towards Quantifying the Hessian Structure of Neural Networks
Zhaorui Dong, Yushun Zhang, Jianfeng Yao, Ruoyu Sun
- NeurIPS 2025 Workshop
- Readers: Everyone
MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
Yupeng Chen, Senmiao Wang, Yushun Zhang, Zhihang Lin, Haozhe Zhang, Weijian Sun, Tian Ding, Ruoyu Sun
- Accepted by TMLR
- Readers: Everyone
Exploring and Improving Initialization for Deep Graph Neural Networks: A Signal Propagation Perspective
Senmiao Wang, Yupeng Chen, Yushun Zhang, Ruoyu Sun, Tian Ding
- Accepted by TMLR
- Readers: Everyone
GaLore-mini: Low Rank Gradient Learning with Fewer Learning Rates
Weihao Huang, Zhenyu Zhang, Yushun Zhang, Zhi-Quan Luo, Ruoyu Sun, Zhangyang Wang
- FITML 2024 Poster
- Readers: Everyone
MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
Yupeng Chen, Senmiao Wang, Zhihang Lin, Yushun Zhang, Haozhe Zhang, Weijian Sun, Tian Ding, Ruoyu Sun
- Submitted to ICLR 2025
- Readers: Everyone
Adam-mini: Use Fewer Learning Rates To Gain More
Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Diederik P Kingma, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
- ICLR 2025 Poster
- Readers: Everyone
Adam-mini: Use Fewer Learning Rates To Gain More
Yushun Zhang, Congliang Chen, Ziniu Li, Tian Ding, Chenwei Wu, Yinyu Ye, Zhi-Quan Luo, Ruoyu Sun
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Why Transformers Need Adam: A Hessian Perspective
Yushun Zhang, Congliang Chen, Tian Ding, Ziniu Li, Ruoyu Sun, Zhi-Quan Luo
- ES-FoMo-II 2024 Poster
- Readers: Everyone
Why Transformers Need Adam: A Hessian Perspective
Yushun Zhang, Congliang Chen, Tian Ding, Ziniu Li, Ruoyu Sun, Zhi-Quan Luo
- NeurIPS 2024 poster
- Readers: Everyone
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang, Zhihang Lin, Yang Yu, Ruoyu Sun, Zhi-Quan Luo
- ICML 2024 Poster
- Readers: Everyone

View all 24 publications

Co-Authors

View all 32 co-authors