[colin@world ~]$ whoami

  1. Jinjun Peng

  2. 🎓 Ph.D. student in Computer Science, Columbia University
  3. 💻 Interested in AI and Coding Agents
  4. 🌟 GitHub | 📮 mail@co1in.me
[colin@world ~]$ cat interests.md
  1. My current research focuses on building code LLMs, including:
  2. - Continual Learning on Code can help efficiently handle complicated and evolving codebases, complementary to scaling model and data size up.
  3. - "World modeling" for Code is expected to improve code semantics understanding, but current results show limited benefits of transferability (e.g., to agentic settings), which motivates future work on "why" and "how".
[colin@world ~]$ cat ./pubs/*_selected*
  1. [arXiv] SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning
    Jinjun Peng*, Magnus Saebo*, Tianjun Zhong, Yi-Jie Cheng, Junfeng Yang, Baishakhi Ray, Simin Chen, Yangruibo Ding
    [arXiv:2601.21649] [side notes]
  2. [LLM4Code '25] CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation
    Jinjun Peng, Leyi Cui, Kele Huang, Junfeng Yang, Baishakhi Ray
    [arXiv:2501.08200] [code]
  3. [NeurIPS '24] SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning
    Yangruibo Ding, Jinjun Peng, Marcus J Min, Gail Kaiser, Junfeng Yang, Baishakhi Ray
    [arXiv:2406.01006] [code]
  4. [ESEC/FSE '23 Distinguished Paper] NeuRI: Diversifying DNN Generation via Inductive Rule Inference
    Jiawei Liu, Jinjun Peng, Yuyao Wang, and Lingming Zhang
    [arXiv:2302.02261] [code 0] [code 1]
  5. [OOPSLA '24] Quarl: A Learning-Based Quantum Circuit Optimizer
    Zikun Li, Jinjun Peng, Yixuan Mei, Sina Lin, Yi Wu, Oded Padon, Zhihao Jia
    [arXiv:2307.10120] [code]
[colin@world ~]$ cat ./exps/*
  1. Amazon, Applied Scientist Intern, 2025.05 - 2025.08
    - Agentic retrieval for coding tasks
  2. Columbia University, Ph.D. student in Computer Science, 2023.09 - ?
    - Advised by Professors Baishakhi Ray and Junfeng Yang.
  3. Tsinghua University, B.E. in Computer Science, 2019 - 2023
  4. Beijing National Day School, 2016 - 2019
    - Where dreams begin.
[colin@world ~]$ cat services.md
  1. Program Committee/Reviewer
    - ICLR ['26]
    - DL4C @ NeurIPS ['25], ASE NIER '25
    - TSE ['25], TOSEM ['25], TKDD ['25], Journal of Big Data
[colin@world ~]$ cat ack.md
  1. - [Always] My friends, mentors, and collaborators.
  2. Funding:
  3. - [2025] Capital One Fellow
  4. - [2024] Amazon Trusted AI Challenge ($250k)
  5. Compute:
  6. - [2024] NSF ACCESS Program
  7. - [2024] OpenAI Researcher Access Program
[colin@world ~]$ curl slow-science.org