I am a CS Ph.D. student at the University of Illinois Urbana-Champaign in the PL/FM/SE group, advised by Prof. Lingming Zhang. You can find my CV here.

My research fields are Software Engineering and Machine Learning. Specifically, I focus on building large language models to solve software engineering tasks, with a specific interest in improving LLM’s reasoning and planning capabilities for code generation and repair through pre-training and post-training.

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.

Selected Publications (See full list on Google Scholar)

• Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning
  Yifeng Ding, Hantian Ding, Shiqi Wang, Qing Sun, Varun Kumar, and Zijian Wang
  arXiv; NeurIPS 2024 System 2 Reasoning Workshop. [preprint] [summary]
• XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
  Yifeng Ding, Jiawei Liu, Yuxiang Wei, and Lingming Zhang
  62nd Annual Meeting of the Association for Computational Linguistics
  (ACL 2024), Pages 12941–-12955, August 2024. [paper] [summary] [code]
• SelfCodeAlign: Self-Alignment for Code Generation
  Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro Von Werra, Arjun Guha, and Lingming Zhang
  Thirty-eighth Conference on Neural Information Processing Systems
  (NeurIPS 2024), To appear, December 2024. [preprint] [code] [model] [dataset]
• Magicoder: Empowering Code Generation with OSS-Instruct
  Yuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding, and Lingming Zhang
  Forty-first International Conference on Machine Learning
  (ICML 2024), Pages 52632–52657, July 2024. [paper] [code] [model] [dataset]
• Evaluating Language Models for Efficient Code Generation
  Jiawei Liu, Songrun Xie, Junhao Wang, Yuxiang Wei, Yifeng Ding, and Lingming Zhang
  First Conference on Language Modeling
  (COLM 2024), October 2024. [paper] [code]
• RepoQA: Evaluating Long Context Code Understanding
  Jiawei Liu, Jia Le Tian, Vijay Daita, Yuxiang Wei, Yifeng Ding, Yuhan Katherine Wang, Jun Yang, Lingming Zhang
  First Workshop on Long-Context Foundation Models @ ICML 2024
  (LCFM @ ICML 2024), July 2024. [paper] [code]
• 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]

Academic Services

• Reviewer: AISTATS’25, ICLR’25, NeurIPS’24, ACL’24, EMNLP’24, NAACL’25
• Organizing Committee: LLM4Code@ICSE’25 (International Workshop on Large Language Models for Code, co-organized with ICSE’25), LLM4Code@ICSE’24

Invited Talks

• CAMEL-AI.org (11/2024): “Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning”
• UCLA AGI Lab (11/2024): “Improving Code Language Modeling via Horizon-Length Prediction”
• UIUC FM/SE Seminar (10/2024): “Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning”
• Amazon Comprehend Team (07/2024): “XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts”
• Uber Programming Systems Team (04/2023): “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