Huanyi Xie

MS student, King Abdullah University of Science and Technology

Joined

January 2024

Names

Huanyi Xie (Preferred)

Emails

****@stu.hit.edu.cn (Confirmed)

****@outlook.com (Confirmed)

****@kth.se (Confirmed)

****@kaust.edu.sa (Confirmed)

Personal Links

Homepage

Google Scholar

ORCID

Career & Education History

MS student

King Abdullah University of Science and Technology (kaust.edu.sa)

2025 – 2026

Undergrad student

Harbin Institute of Technology (stu.hit.edu.cn)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Lijie Hu

Present

PhD Advisor

Di Wang

Present

Expertise

LLMs

Present

machine learning interpretability

Present

Publications

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
Jiaming Zhang, Huanyi Xie, Meng Ding, Shaopeng Fu, Jinyan Liu, Di Wang
- ICLR 2026 Workshop DATA-FM
- Readers: Everyone
Efficient and Stable Grouped RL Training for Large Language Models
Liangyu Wang, Huanyi Xie, Xinhai Wang, Tianjin Huang, Mengdi Li, Di Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Predicting LLM Output Length via Entropy-Guided Representations
Huanyi Xie, Yubin Chen, Liangyu Wang, Lijie Hu, Di Wang
- ICLR 2026 Poster
- Readers: Everyone
Dissecting Representation Misalignment in Contrastive Learning via Influence Function
Huanyi Xie, Chenyang Ren, Khouloud Saadi, Shu Yang, Zhen Tan, Jingfeng Zhang, Lijie Hu, Di Wang
- ICLR 2026 Poster
- Readers: Everyone
Attributing Data for Sharpness-Aware Minimization
Chenyang Ren, Yifan Jia, Huanyi Xie, Zhaobin Xu, Tianxing Wei, Liangyu Wang, Guimin Hu, Lijie Hu, Di Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Evaluating Data Influence in Meta Learning
Chenyang Ren, Huanyi Xie, Shu Yang, Meng Ding, Dongrui Liu, Lijie Hu, Di Wang
- ICLR 2026 Poster
- Readers: Everyone
Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
Liangyu Wang, Jie Ren, Hang Xu, Junxiao Wang, Huanyi Xie, David E. Keyes, Di Wang
- COLM 2025
- Readers: Everyone
Dissecting Misalignment of Multimodal Large Language Models via Influence Function
Lijie Hu, Chenyang Ren, Huanyi Xie, Khouloud Saadi, Shu Yang, Jingfeng Zhang, Di Wang
- Submitted to ICLR 2025
- Readers: Everyone
Low-cost Enhancer for Text Attributed Graph Learning via Graph Alignment
Lijie Hu, Huanyi Xie, Lu Yu, Tianhao Huang, Longfei Li, Meng Li, JUN ZHOU, Di Wang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

Co-Authors

View all 30 co-authors