News


2 Jan 2025
Thrilled to get the Amazon Machine Learning System Fellowship !

1 Sept 2024
Thrilled to start Ph.D journal at UMN !

Xinnan Zhang 

Department of Electrical and Computer Engineering
The University of Minnesota, Twin Cities

117 Pleasant St. S.E. Minneapolis MN 55455

Email: zhan9359@umn.edu

[CV] [Github] [Google Scholar]

I am a first-year Ph.D. student @ University of Minnesota, Twin Cities since Sep 2024, supervised by Prof. Mingyi Hong.

I obtained B.Eng in Artificial Intelligence and Electronic and Information Engineering in the University of Science and Technology of China. I was affiliated with the School of the Gifted Young, which originates from the first undegraduate program for special young talents in China.

My research interests include RLHF and Large Language Models (LLM). Previously I actively researched in the field of parameter estimation in signal processing.

Publications

AI4S stands for AI for Science. LLM stands for Large Language Model. SP stands for Signal Processing.
* indicates equal contributions

LLM Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Kaixiang Lin, Songtao Lu, Alfredo Garcia, Mingyi Hong
In submission
LLM Reinforcement Learning in Inference Time: A Perspective from Successive Policy Iterations
Xinnan Zhang, Chenliang Li, Siliang Zeng, Jiaxiang Li, Zhongruo Wang, Songtao Lu, Alfredo Garcia, Mingyi Hong
Workshop on Reasoning and Planning for Large Language Models at ICLR 2025
LLM Llm alignment through successive policy re-weighting
Xinnan Zhang, Siliang Zeng, Jiaxiang Li, Kaixiang Lin, Mingyi Hong
NeurIPS 2024 Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability
pdf The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
Kun Wang, Guibin Zhang, Xinnan Zhang, Junfeng Fang, Xun Wu, Guohao Li, Shirui Pan, Wei Huang, Yuxuan Liang
KDD-24
AI4S Benchmark on Drug Target Interaction Modeling from a Structure Perspective
Xinnan Zhang, Jialin Wu, Junyi Xie, Tianlong Chen, Kaixiong Zhou
Preprint
SP CRB analysis for mixed-ADC based DOA estimation
Xinnan Zhang, Yuanbo Cheng, Xiaolei Shang, Jun Liu
IEEE Transactions on Signal Processing (TSP)
SP A Novel Mixed-ADC Architecture for DOA Estimation
Xinnan Zhang, Yuanbo Cheng, Hing Cheung So, Jian Li
IEEE Signal Processing Letters (SPL)
SP Mixed-Precision Arrangement via CRB for DOA Estimation Using SLA
Xinnan Zhang, Yuanbo Cheng, Xiaolei Shang, Jun Liu
2023 31st European Signal Processing Conference (EUSIPCO-23)
SP Optimal Mixed-ADC arrangement for DOA Estimation via CRB using ULA
Xinnan Zhang, Yuanbo Cheng, Xiaolei Shang, Jun Liu
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-23)

Presentation

Mixed-Precision Arrangement via CRB for DOA Estimation Using SLA
- EUSIPCO 2023 (Oral)
Optimal Mixed-ADC arrangement for DOA Estimation via CRB using ULA
- ICASSP 2023 (Poster)

Education

The University of Minnesota, Twin Cities
Ph.D student in Electronic Engineering                                                         Sep 2024 - Minnesota, USA
Advisor: Prof. Mingyi Hong
University of Science and Technology of China
Master student in Electronic Engineering                                                         Sep 2021 - June 2024, Hefei, Anhui, China
University of Science and Technology of China
B.Eng. in Electronic & Information Engineering and Artificial Intelligence              Sep 2017 - June 2021, Hefei, Anhui, China

Selected Awards


Amazon Machine Learning System Fellowship, 2025
Neural Network Intelligence (NNI) by MSRA, Outstanding Project 2020

Activities

Teaching Assistant
• Signals and System 2021 @USTC
• Numerical Methods B 2020 @USTC
• Mathematical equation B 2019 @USTC