Zhongzhu Chen

Zhongzhu Chen

Applied Scientist at Amazon AGI

Zhongzhu Chen

I am an Applied Scientist at Amazon AGI, where I build scalable foundation models and explore next-generation LLM modeling paradigms.

I earned my Ph.D. in optimization from the University of Michigan - Ann Arbor in 2024, where I was honored to be supervised by Prof. Jon Lee. Before that, I obtained my bachelor’s degree from the School of Mathematical Sciences at Peking University in 2019.

Current Research Focus:

  • Diffusion Language (MultiModal) Models
  • LLM Scaling Laws
  • Reinforcement Learning

Publications

DensePure: Understanding Diffusion Models for Adversarial Robustness
Chaowei Xiao*, Zhongzhu Chen*, Kun Jin*, Jiongxiao Wang*, Weili Nie, Mingyan Liu, Anima Anandkumar, Bo Li, and Dawn Song
The Eleventh International Conference on Learning Representations (ICLR 2023)
Paper

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing
Jiawei Zhang*, Zhongzhu Chen*, Huan Zhang, Chaowei Xiao, and Bo Li
32nd USENIX Security Symposium (USENIX Security 23), pp. 4787-4804
Paper

Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
Yiquan Li*, Zhongzhu Chen*, Kun Jin*, Jiongxiao Wang*, Jiachen Lei, Bo Li, Chaowei Xiao
The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)
Paper

Robust Representation Consistency Model via Contrastive Denoising
Jiachen Lei, Julius Berner, Jiongxiao Wang, Zhongzhu Chen, Zhongjia Ba, Kui Ren, Jun Zhu, Anima Anandkumar
The Thirteenth International Conference on Learning Representations (ICLR 2025)
Paper

Performative Federated Learning: A Solution to Model-Dependent and Heterogeneous Distribution Shift
Kun Jin*, Tongxin Yin*, Zhongzhu Chen*, Zeyu Sun, Xueru Zhang, Yang Liu, Mingyan Liu
Proceedings of the AAAI Conference on Artificial Intelligence, 38 (AAAI 2024)
Paper

Mixing Convex-Optimization Bounds for Maximum-Entropy Sampling
Zhongzhu Chen, Marcia Fampa, Amélie Lambert, and Jon Lee
Mathematical Programming (2021)
Paper

Technical Note - Masking Anstreicher’s Linx Bound for Improved Entropy Bounds
Zhongzhu Chen, Marcia Fampa, and Jon Lee
Operations Research (2022)
Paper

On Computing with Some Convex Relaxations for the Maximum-Entropy Sampling Problem
Zhongzhu Chen, Marcia Fampa, and Jon Lee
INFORMS Journal on Computing, 35(2), 2023: 368-385
Paper

Generalized Scaling for the Constrained Maximum-Entropy Sampling Problem
Zhongzhu Chen, Marcia Fampa, and Jon Lee
Mathematical Programming (2024)
Paper

On Algorithmic Advances for Maximum-Entropy Sampling
Zhongzhu Chen
Ph.D. Dissertation, University of Michigan - Ann Arbor (2024)
Thesis

* denotes first authorship when there are multiple first authors

Service

Conference Reviewer: NeurIPS, ICML, ICLR, WACV, AAAI, ISCO

Journal Reviewer: Operations Research