I am Xiaohan Wang, a Ph.D. student in Computer Science at Vanderbilt University, advised by Kevin Leach. My research centers on reliable LLM-assisted decompilation and binary analysis, combining semantic recovery, program analysis, and behavioral feedback to reconstruct readable, executable code from compiled binaries.

As a Graduate Research Assistant at Vanderbilt, I contribute to healthcare cybersecurity and autonomous defense efforts under the ARPA-H DIGIHEALS and ARPA-H UPGRADE programs. Earlier in my Ph.D. and undergraduate studies, I worked on machine learning for scientific visualization and neural field exploration with Prof. Matthew Berger, and held a research internship at The Hong Kong University of Science and Technology.

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

Research Interests

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

Selected Publications

  • STILL overview: binary residues feed semantic extraction and STL hints for LLM refinement
    STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation
    Xiaohan Wang, Kevin Leach
    EMNLP 2026 Main Conference · 2026
  • ICL4Decomp overview: retrieved examples and optimization-aware context guide end-to-end decompilation
    ICL4Decomp: Towards Re-executable Reverse Engineering
    Xiaohan Wang, Yuxin Hu, Kevin Leach
    Findings of EMNLP 2026 · 2026
  • Agent4Decompile overview: syntax, compilation, and execution constraints guide specialized repair agents
    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 · 2026
  • Seeing the Many overview figure
    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 · 2025
  • Topology Guidance overview figure
    Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology
    Xiaohan Wang and Matthew Berger
    arXiv preprint · 2025
  • GitHub Impersonation overview figure
    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) · 2025
  • EmotionLens overview figure
    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 · 2025

News

  • Sep 2026
    Our paper “Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery” has been accepted to NeurIPS 2026 Workshop on Evaluation of Interactive Agents.
  • Aug 2026
    Our paper “STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation” has been accepted to EMNLP 2026 Main Conference.
  • Aug 2026
    Our paper “ICL4Decomp: Towards Re-executable Reverse Engineering” has been accepted to Findings of EMNLP 2026.
  • Nov 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.
  • May 2025
    Our work “Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology” is released as an arXiv preprint.
  • Mar 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.
  • Mar 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.
  • Nov 2024
    I passed my Ph.D. preliminary examination.
  • Aug 2023
    I started my Ph.D. in Computer Science at Vanderbilt University under the supervision of Prof. Berger.
  • 2020
    I was selected for Yingcai Honors College at Nanjing Normal University.

Awards

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