About

I am Xiaohan Wang, a Ph.D. student in Computer Science at Vanderbilt University. My research aims to design representations for different data modalities and leverage AI/machine learning methods to make data exploration and understanding more efficient and accessible.

🎓 Education

  • Ph.D. in Computer Science
    Vanderbilt University
    Aug. 2023 – Expected May 2028
  • B.Eng. in Software Engineering
    Nanjing Normal University, Yingcai Honors College
    Sep. 2019 – Jun. 2023

🌱 Interests

  • Code and program understanding with large language models
  • Large-scale scientific simulation data exploration using machine learning techniques

📚 Selected Publications

  • 2026
    STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation
    Xiaohan Wang, Kevin Leach
    EMNLP 2026 Main Conference
    STILL overview: binary residues feed semantic extraction and STL hints for LLM refinement
  • 2026
    ICL4Decomp: Towards Re-executable Reverse Engineering
    Xiaohan Wang, Yuxin Hu, Kevin Leach
    Previously titled Context-Guided Decompilation: A Step Towards Re-executability.
    Findings of EMNLP 2026
    ICL4Decomp overview: retrieved examples and optimization-aware context guide end-to-end decompilation
  • 2026
    Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery
    Yifan Zhang*, Xiaohan Wang*, Yueke Zhang, Yu Huang, Kevin Leach
    *Equal contribution.
    NeurIPS 2026 Workshop on Evaluation of Interactive Agents
    Agent4Decompile overview: syntax, compilation, and execution constraints guide specialized repair agents
  • 2025
    Seeing the Many: Exploring Parameter Distributions Conditioned on Features in Surrogates 🏅Best Paper Award
    Xiaohan Wang, Zhimin Li, Joshua A. Levine, and Matthew Berger
    IEEE Workshop on Uncertainty Visualization
    Seeing the Many Teaser
  • 2025
    Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology
    Xiaohan Wang and Matthew Berger
    arXiv preprint
    Topology Guidance Teaser
  • 2025
    Who's Pushing the Code? An Exploration of GitHub Impersonation
    Yueke Zhang, Anda Liang, Xiaohan Wang, ..., Kevin Leach, and Yu Huang.
    IEEE/ACM International Conference on Software Engineering (ICSE)
    GitHub Impersonation Teaser
  • 2025
    EmotionLens: Interactive visual exploration of the circumplex emotion space in literary works via affective word clouds
    Bingyuan Wang, Qing Shi, Xiaohan Wang, You Zhou, ..., and Zeyu Wang.
    Visual Informatics
    EmotionLens Teaser

đź“° News

  • Update — 10/2026
    Our paper “STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation” has been accepted to EMNLP 2026 Main Conference.
  • Update — 10/2026
    Our paper “ICL4Decomp: Towards Re-executable Reverse Engineering” has been accepted to Findings of EMNLP 2026.
  • Update — 10/2026
    Our paper “Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery” has been accepted to NeurIPS 2026 Workshop on Evaluation of Interactive Agents.
  • 🏆 11/2025
    Our paper “Seeing the Many: Exploring Parameter Distributions Conditioned on Features in Surrogates” is accepted and received the Best Paper Award at the IEEE Workshop on Uncertainty Visualization.
  • đź“„ 5/2025
    Our work “Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology” is released as an arXiv preprint.
  • đź“„ 3/2025
    Our collaborative project “EmotionLens: Interactive visual exploration of the circumplex emotion space in literary works via affective word clouds” is published in Visual Informatics.
  • đź“„ 3/2025
    Our paper “Who's Pushing the Code? An Exploration of GitHub Impersonation” is accepted by ICSE.
  • 🎓 2025
    I began a new research direction under the guidance of Prof. Leach.
  • 🎓 11/2024
    I passed my PhD preliminary examination.
  • 🎓 8/2023
    I started my PhD in Computer Science at Vanderbilt University under the supervision of Prof. Berger.
  • 🎓 2020
    I was selected for Yingcai Honors College.

🏅 Awards

  • 2020 - 2022
    Outstanding Student Scholarship - First Prize Top 5% of cohort