About

I am a second-year CS Ph.D. student at the University of Illinois Urbana-Champaign in the PL/FM/SE group, advised by Prof. Lingming Zhang.

My research interest lies in Large Language Models (LLM) for Code. My ongoing works include improving LLMs with Instruction Tuning and Mixture-of-Experts (MoE) for better code generation and automated debugging. You can find my CV here.

I obtained my bachelor’s degrees at Tsinghua University, including one in Software Engineering from the School of Software and one in Business Administration from the School of Economics and Management. I was a research assistant at Software System Security Assurance Group during my undergraduate years, advised by Prof. Yu Jiang.

News

• [2024-02] Check out our new preprint on Instruction Tuning for Code!
• [2023-09] One research paper on LLM for APR publised in ASE’23!
• [2023-07] One research paper on Deep Learning Robustness publised in ISSTA’23!
• [2022-01] I’m thrilled to get accepted into the Ph.D. program at Illinois CS!
• [2021-07] One research paper on Deep Learning Robustness published in ISSTA’21!

Publications

• ${\mathcal X}$FT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
  Yifeng Ding, Jiawei Liu, Yuxiang Wei, and Lingming Zhang
  Preprint, February 2024. [preprint]
• Magicoder: Source Code Is All You Need
  Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang
  arXiv, Preprint, December 2023. [preprint]
• The Plastic Surgery Hypothesis in the Era of Large Language Models
  Chunqiu Steven Xia, Yifeng Ding, and Lingming Zhang
  38th IEEE/ACM International Conference on Automated Software Engineering
  (ASE 2023), Pages 522–534, September 2023. [paper]
• CoopHance: Cooperative Enhancement for Robustness of Deep Learning Systems
  Quan Zhang, Yongqiang Tian, Yifeng Ding, Shanshan Li, Chengnian Sun, Yu Jiang, Jiaguang Sun
  32nd ACM International Symposium on Software Testing and Analysis
  (ISSTA 2023), Pages 753–765, July 2023. [paper]
• AdvDoor: Adversarial Backdoor Attack of Deep Learning System
  Quan Zhang, Yifeng Ding, Yongqiang Tian, Jianmin Guo, Min Yuan, Yu Jiang
  30th ACM International Symposium on Software Testing and Analysis
  (ISSTA 2021), Pages 127–138, July 2021. [paper]

Academic Service

• Reviewer: ACL/ARR 2024 Feb
• Web Chair of LLM4Code Workshop 2024, co-located with ICSE 2024.

Talk

• Uber Programming Systems Team: Equipping Large Language Models with Domain-Specific Knowledge for Automated Program Repair.

Contacts

• Email: yifeng6@illinois.edu
• Address: 2107 Thomas M. Siebel Center for Computer Science