Xin Jin

Research Scientist at Meta, Ph.D.

xin.jpg

Hi! :wave: I’m a research scientist recently joining Meta GenAI, where I build coding copilots. I obtained my Ph.D. degree from Department of Computer Science and Engineering at The Ohio State University in 2024, advised by Prof. Zhiqiang Lin. I was a research intern at Microsoft Research and Cisco Research during summer 2023 and summer 2022.

I am broadly interested in large language models (LLMs), program analysis, and security. I am particularly interested in:

  • Program Comprehension and Generation: Understanding program semantics with LLMs/machine learning and generating program code in various programming languages.
  • Software Security: Securing software systems by program analysis and machine learning.
  • Threat Intelligence: Collecting, interpreting, and enriching cybersecurity data to identify and mitigate potential threats and assist decision-making processes.

I am always looking for opportunities to collaborate. The best way to reach me is via email: jin (dot) 967 (at) osu (dot) edu.

Selected Publications

  1. ACM FSE
    SimLLM: Calculating Semantic Similarity in Code Summaries Using a Large Language Model-Based Approach
    Xin Jin, and Zhiqiang Lin
    ACM International Conference on the Foundations of Software Engineering (FSE), 2024
  2. arXiv
    Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models
    Xin Jin, Jonathan Larson, Weiwei Yang, and Zhiqiang Lin
    arXiv preprint arXiv:2312.09601, 2023
    PDF Code
  3. ACM CCS
    SymLM: Predicting Function Names in Stripped Binaries via Context-Sensitive Execution-Aware Code Embeddings
    Xin Jin, Kexin Pei, Jun Yeon Won, and Zhiqiang Lin
    ACM Conference on Computer and Communications Security (CCS), 2022
    PDF Code Poster Slides
  4. ACM CCS
    Understanding IoT Security from a Market-Scale Perspective
    Xin Jin*, Sunil Manandhar*, Kaushal Kafle, Zhiqiang Lin, and 1 more author
    ACM Conference on Computer and Communications Security (CCS), 2022
    PDF Code Slides