Meng Ding

I am currently a Ph.D. student advised by Prof. Jinhui Xu and Prof. Kaiyi Ji at the State University of New York at Buffalo(UB). I am also very fortunate to closely work with Prof. Di Wang. Previously, I received my Bachelor’s degree in Mathematics from China Agricultural University and a second major in Economics from Peking University.

My research interest lies in using mathematical insights into deep learning to enable better and safer AI.

The best way to reach me is at [my first name][my last name] (at) buffalo (dot) edu.

Pulications

* indicates equal contribution, † indicates corresponding author.

Preprints

One day.
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons
Wenshuo Dong, Qingsong Yang, Shu Yang, Lijie Hu, Meng Ding, Wanyu Lin, Tianhang Zheng, Di Wang
In-Run Data Shapley for Adam Optimizer
Meng Ding*, Zeqing Zhang*, Di Wang, Lijie Hu.
Benign Overfitting in Adversarial Training for Vision Transformers
Jiaming Zhang, Meng Ding, Shaopeng Fu, Jingfeng Zhang, Di Wang.
ICLR 2026 DATA-FM Workshop;
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 DATA-FM Workshop;

Selected Papers

Black-box Optimization of LLM Outputs by Asking for Directions
Jie Zhang, Meng Ding, Yang Liu, Jue Hong, Florian Tramèr.
ICLR Trustworthy AI workshop 2026, Oral;
Evaluating Data Influence in Meta Learning
Chenyang Ren, Huanyi Xie, Shu Yang, Meng Ding, Lijie Hu, Di Wang.
ICLR 2026;
Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
Meng Ding, Jinhui Xu, Kaiyi Ji.
AISTATS 2026;
Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
Meng Ding, Rohan Sharma, Changyou Chen, Jinhui Xu, Kaiyi Ji.
TMLR 2025;
Towards User-level Private Reinforcement Learning with Human Feedback
Jiaming Zhang*, Mingxi Lei*, Meng Ding, Mengdi Li, Zihang Xiang, Difei Xu, Jinhui Xu, Di Wang.
CoLM 2025;
Understanding Private Learning From Feature Perspective
Meng Ding, Mingxi Lei, Shaopeng Fu, Shaowei Wang, Di Wang, Jinhui Xu.
TPDP 2025;
Nearly Optimal Differentially Private ReLU Regression
Meng Ding, Mingxi Lei, Shaowei Wang, Tianhang Zheng, Di Wang, Jinhui Xu.
UAI 2025;
Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization
Ruijia Zhang*, Mingxi Lei*, Meng Ding, Zihang Xiang, Jinhui Xu, Di Wang.
AAAI 2024;
Revisiting Differentially Private ReLU Regression
Meng Ding, Mingxi Lei, Liyang Zhu, Shaowei Wang, Di Wang, Jinhui Xu.
NeurIPS 2024;
Truthful High Dimensional Sparse Linear Regression
Liyang Zhu, Amina Manseur, Meng Ding, Jinyan Liu, Jinhui Xu, Di Wang.
NeurIPS 2024;
Understanding Forgetting in Continual Learning with Linear Regression
Meng Ding, Kaiyi Ji, Di Wang, Jinhui Xu.
ICML 2024;
Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
Liyang Zhu*, Meng Ding*, Jinhui Xu, Di Wang.
ICLR 2024;

Services

Conference Reviewer
ICML, NeurIPS, ICLR, AISTATS, UAI, CVPR,