Simin Chen

Simin Chen

Postdoctoral Researcher at Columbia University

Computer Science Department at Columbia University

Biography

I am a postdoctoral researcher in the Computer Science Department at Columbia University, working with Prof.Baishakhi Ray on research related to large language models for code (LLM4Code). I earned my Ph.D. from the University of Texas at Dallas (UTD), and I was fortunate to be advised by Prof.Wei Yang and Prof.Cong Liu. Before joining UTD, I received my master degree from Tongji University in May 2018. My research interest lies in machine learning, computer security, and program analysis.

📢 Prospective Students: I’m actively looking for self-motivated students to join my research group at GMU CS. If you are interested in

(1) LLMs for Code / Software Engineering,

(2) Trustworthy AI Systems,

You are also welcome to drop me an email with subject line “Research Internship Application - [Your Name]” to discuss potential research opportunities at siminchen.phd@gmail.com.

Download my resumé.

Interests
  • Machine Learning
  • Computer Security
  • Software Engineering
Education

  • Ph.D., 2019 - 2024

    The University of Texas at Dallas

  • Master, 2015 - 2018

    Tongji University

  • Bachelor, 2011 - 2015

    Tongji University

News

May 2026 -- Our paper received the Distinguished Paper Award at IEEE S&P 2026!
October 2024 -- Serve as a reviewer of CVPR 2025.
August 2025 -- Serve as a reviewer for ICLR 2025.
July 2024 -- Serve as a program committee on the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024).
June 2024 -- Serve as a Program Committee for AAAI 2025.
See all posts

Publications

Simin Chen, Jinjun Peng, Yixin He, Junfeng Yang, Baishakhi Ray (2026). Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers. In S&P 2026 🏆 Distinguished Paper Award.

PDF Code

Junxian Li, Beining Xu, Simin Chen, Jiatong Li, Jingdi Lei, Haodong Zhao, Di Zhang (2026). IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding. In CVPR 2026.

Yuan Yao, Lixu Wang, Jiaqi Wu, Jin Song, Simin Chen, Zehua Wang, Zijian Tian, Wei Chen, Huixia Li, Xiaoxiao Li (2026). FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning. In CVPR 2026.

Monoshi Kumar Roy, Simin Chen, Benjamin Steenhoek, Jinjun Peng, Gail Kaiser, Baishakhi Ray, Wei Le (2026). CodeSense: a Real-World Benchmark and Dataset for Code Semantic Reasoning. In ICLR 2026.

Dezhi Ran, Yuan Cao, Mengzhou Wu, Simin Chen, Yuzhe Guo, Jun Ren, Zihe Song, Hao Yu, Jialei Wei, Linyi Li, Wei Yang, Baishakhi Ray, Tao Xie (2026). From Assistant to Independent Developer — Are GPTs Ready for Software Development?. In ICLR 2026.

Zhixin Zhao, Yitao Hu, Simin Chen, Mingfang Ji, Wei Yang, Yuhao Zhang, Laiping Zhao, Wenxin Li, Xiulong Liu, Wenyu Qu, Hao Wang (2025). PARD: Enhancing Goodput for Inference Pipeline via Proactive Request Dropping. In EuroSys 2026.

Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, Baishakhi Ray (2025). TITLE_TODO -- please fill in the EMNLP 2025 paper title. In EMNLP 2025.

Simin Chen, Pranav Pusarla, Baishakhi Ray (2025). DyCodeEval: Dynamic Benchmarking of Reasoning Capabilities in Code Large Language Models Under Data Contamination. In ICML 2025.

PDF Code Dataset Project

Ravishka Rathnasuriya, Tingxi Li, Zexin Xu, Zihe Song, Mirazul Haque, Simin Chen, Wei Yang (2025). SOK: Efficiency Robustness of Dynamic Deep Learning Systems. In USENIX Security 2025.

Jiaqi Wu, Simin Chen, Jing Tang, Yuzhe Yang, Yiming Chen, Lixu Wang, Song Lin, Zehua Wang, Wei Chen, Zijian Tian (2025). FDPT: Federated Discrete Prompt Tuning for Black-Box Visual-Language Models. In ICCV 2025.

Dezhi Ran, Yuan Cao, Yuzhe Guo, Yuetong Li, Mengzhou Wu, Simin Chen, Wei Yang, Tao Xie (2025). Medusa: A Framework for Collaborative Development of Foundation Models with Automated Parameter Ownership Assignment. In FSE 2025.

Simin Chen, Zexin Li, Wei Yang, Cong Liu (2024). DeciX: Explain Deep Learning Based Code Generation Applications. In ESEC/FSE 2024.

Simin Chen, Xiaoning Feng, Xiaohong Han, Cong Liu, Wei Yang (2024). PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models. In ESEC/FSE 2024.

PDF Code

Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby Tan, Haizhou Li (2023). Dynamic Transformer Provide a False Sense of Efficiency. In ACL 2023.

Simin Chen, Hanlin Chen, Mirazul Haque, Cong Liu, Wei Yang (2023). The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection. In CVPR 2023.

Zexin Li, Bangjie Yin, Taiping Yao, Junfeng Guo, Shouhong Ding, Simin Chen, Cong Liu (2023). Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition. In CVPR 2023.

Simin Chen, Shiyi Wei, Cong Liu, Wei Yang (2023). DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization. In ISSTA 2023.

Simin Chen, Mirazul Haque, Cong Liu, Wei Yang (2022). DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks. In ASE 2022.

PDF Code

Simin Chen, Cong Liu, Mirazul Haque, Zihe Song, Wei Yang (2022). NMTSloth: Understanding and Testing Efficiency Degradation of Neural Machine Translation Systems. In ESEC/FSE 2022.

PDF Code

Simin Chen, Hamed Khanpour, Cong Liu, Wei Yang (2022). Learning to Reverse DNNs from AI Programs Automatically. In IJCAI 2022.

PDF

Simin Chen, Zihe Song, Mirazul Haque, Cong Liu, Wei Yang (2022). NICGSlowDown: Evaluating the Efficiency Robustness of Neural Caption Generation Models. In CVPR 2022.

PDF Code

Simin Chen, Soroush Bateni, Sampath Grandhi, Xiaodi Li, Cong Liu, Wei Yang (2020). DENAS: automated rule generation by knowledge extraction from neural networks. In ESEC/FSE 2020.

PDF Code DOI

Experience

 
 
 
 
 
Research Assistant
Amazon Web Service
May 2023 – Aug 2023 Arlington Area, VA
Applying large language model for Cedar authorization policy language.
 
 
 
 
 
Research Assistant
Microsoft Research
May 2021 – Jul 2020 Seattle
Evaluate the model leakage risk of on-device DNNs.
 
 
 
 
 
Research Assistant
NEC Laboratories America
Jan 2020 – May 2020 New Jersey
Apply ML techniques for program analysis.

Services

Program Committee Member -- NeurIPS 2025, ICML 2025, ICCV 2025, ACL 2025, ASE 2024, CVPR 2024, AAAI 2024, ICA3PP 2023, ICCV 2023, MSR 2023, CVPR 2023, AAAI 2023, WACV 2022, ECCV 2022
Sub-Reviewer -- ISSRE 2023, ASE 2023, ICSE 2023, ICST 2023, ASE 2022, ICST 2022, ICSE 2021

Contact