Xin Jin

Research Scientist at Meta, Ph.D.

xin.jpg

Hi! :wave: I’m a research scientist at the Llama Research team, Meta GenAI. I focus on advancing the coding capabilities of next-generation Llama models.

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. My research interests broadly lie in large language models (LLMs), program analysis, and security.

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. NDSS
    Repurposing Neural Networks for Efficient Cryptographic Computation
    Xin Jin, Shiqing Ma, and Zhiqiang Lin
    Network and Distributed System Security (NDSS) Symposium, 2025
    PDF
  2. NDSS
    Beyond Classification: Inferring Function Names in Stripped Binaries via Domain Adapted LLMs
    Linxi Jiang*, Xin Jin*, and Zhiqiang Lin (* Co-first Author)
    Network and Distributed System Security (NDSS) Symposium, 2025
    PDF
  3. 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
    PDF
  4. 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
  5. 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
  6. 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