Yueke Zhang (张跃柯)

I am a Ph.D. candidate in Computer Science at Vanderbilt University, advised by Prof. Yu Huang, with an expected graduation in 2027. Here is my CV.

My research develops trustworthy and efficient AI for software systems by connecting software engineering, security, and neuroscience. I study how human cognition can guide AI learning and adaptation, how program analysis and formal reasoning can improve reliability, and how contribution accountability can protect open-source ecosystems as AI agents become contributors. My long-term goal is to build agents that learn from experience, improve their capabilities, and carry out complex technical tasks while preserving user intent and human control.

My email is yueke.zhang@vanderbilt.edu. Feel free to contact me.


Email  |  Google Scholar  |  GitHub  |  LinkedIn

profile photo

Education

  • Vanderbilt University
    Nashville, United States
    2023-2027 (expected)

    Ph.D. in Computer Science; Ph.D. Candidate
    Advisor: Yu Huang
    Research: Trustworthy AI for Software Systems, Security, Human Cognition

  • Southwest University
    Chongqing, China
    2019-2023

    Bachelor's Degree in Management Information System

Publications

ScanCoder: Leveraging Human Attention Patterns to Enhance LLMs for Code — approach overview (Figure 1)
ScanCoder: Leveraging Human Attention Patterns to Enhance LLMs for Code
Yueke Zhang, Yifan Zhang, Zihan Fang, Greg Trafton, Daniel Levin, Kevin Leach, Yu Huang
Proceedings of the ACM on Software Engineering (FSE 2026)
Paper

Understanding and Detecting GitHub Impersonation through Automated Authorship Attribution — approach overview (Figure 4)
Understanding and Detecting GitHub Impersonation through Automated Authorship Attribution
Yueke Zhang, Yifan Zhang, Pamela Wisniewski, Fengwei Zhang, Kevin Leach, Yu Huang
ACM Transactions on Software Engineering and Methodology (TOSEM 2026)
Paper

Locating Software Vulnerabilities With Static Analyzers: How Far Are We? — approach overview (Figure 3)
Locating Software Vulnerabilities With Static Analyzers: How Far Are We?
Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
International Conference on Evaluation and Assessment in Software Engineering (EASE 2026)
Paper

Stop the Retrieval Thrash: Brain-Guided Episodic Memory for Repository-Scale Coding Agents — approach overview (Figure 1)
Stop the Retrieval Thrash: Brain-Guided Episodic Memory for Repository-Scale Coding Agents
Yueke Zhang, Zihan Fang, Kevin Leach
FSE Companion, HumanAISE Workshop (2026)
Paper

Eye-Mulator: Improving Code Language Models by Mimicking Human Visual Attention — approach overview (Figure 1)
Eye-Mulator: Improving Code Language Models by Mimicking Human Visual Attention
Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang
Annual Meeting of the Association for Computational Linguistics (ACL 2026)
Paper

Contribution Patterns in Open Source Software for Social Good: Dynamics, Individuals, and Impact — approach overview (Figure 1)
Contribution Patterns in Open Source Software for Social Good: Dynamics, Individuals, and Impact
Zihan Fang, Yueke Zhang, Thomas Zimmermann, Denae Ford, Yu Huang
Proceedings of the ACM on Human-Computer Interaction (CSCW 2026)
Paper

VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving — approach overview (Figure 1)
VERITAS: Verifier-Guided Proof Search for Zero-Shot Formal Theorem Proving
Manish Acharya, Zhenyu Liao, Yueke Zhang, Kevin Leach, Yu Huang, Yifan Zhang
AI for Math Workshop at ICML (AI4Math 2026)
arXiv

Who’s Pushing the Code? An Exploration of GitHub Impersonation
Yueke Zhang, Anda Liang, Xiaohan Wang, Pamela Wisniewski, Fengwei Zhang, Kevin Leach, Yu Huang
IEEE/ACM International Conference on Software Engineering (ICSE 2025)
PDF / Code

CodeACT-R: A Cognitive Simulation Framework for Human Attention in Code Reading
Yueke Zhang, Zihan Fang, Greg Trafton, Daniel Levin, Kevin Leach, Yu Huang
IEEE/ACM International Conference on Automated Software Engineering, NIER Track (ASE 2025)
PDF / Code

Pre-Training Representations of Binary Code Using Contrastive Learning
Yifan Zhang, Chen Huang, Yueke Zhang, Huajie Shao, Kevin Leach, Yu Huang
Transactions on Machine Learning Research (TMLR 2025)
PDF / Paper

Leveraging Evidence Theory to Improve Fault Localization: An Exploratory Study
Yueke Zhang, Kevin Leach, Yu Huang
ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM 2023)
PDF

Leveraging Fuzzy System to Reduce Uncertainty of Decision Making in Software Engineering Automation
Yueke Zhang, Yu Huang
Genetic Improvement Workshop at GECCO (GI 2022)
Paper

Preprints and Manuscripts Under Review

GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation — approach overview (Figure 3)
GraphAlignCoder: Aligning Program and Proof Graphs for Code Generation
Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
Under review
arXiv

SCOPE: Leveraging Subgoal Critiques for Code Generation — approach overview (Figure 4)
SCOPE: Leveraging Subgoal Critiques for Code Generation
Yueke Zhang, Yifan Zhang, Zihan Fang, Kevin Leach, Wei Zhang, Yu Huang
Under review
arXiv

CogCoder: Cognitive Supervision for Code Language Models — approach overview (Figure 3)
CogCoder: Cognitive Supervision for Code Language Models
Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
Under review

Unclaimed Territory: Analyzing Subdomain Takeover Risks in GitHub Pages — approach overview (Figure 2)
Unclaimed Territory: Analyzing Subdomain Takeover Risks in GitHub Pages
Yueke Zhang, Zihan Fang, Kevin Leach, Yu Huang
Under review

CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement — approach overview (Figure 1)
CodeGrad: Integrating Multi-Step Verification with Gradient-Based LLM Refinement
Yueke Zhang, Yifan Zhang, Kevin Leach, Yu Huang
Under review
arXiv

DPO-F+: Aligning Code Repair Feedback with Developers’ Preferences — approach overview (Figure 2)
DPO-F+: Aligning Code Repair Feedback with Developers’ Preferences
Zihan Fang, Yifan Zhang, Yueke Zhang, Kevin Leach, Yu Huang
Under review
arXiv

From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software — approach overview (Figure 1)
From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software
Zihan Fang, Yueke Zhang, Ningzhi Tang, Collin McMillan, Toby Jia-Jun Li, Yu Huang
Under review
arXiv

AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering — approach overview (Figure 1)
AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering
Zihan Fang, Yueke Zhang, Yu Huang
Under review
arXiv

Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery — approach overview (Figure 2)
Constraint-Guided Multi-Agent Decompilation for Executable Binary Recovery
Yifan Zhang, Xiaohan Wang, Yueke Zhang, Yu Huang, Kevin Leach
Preprint, 2026
arXiv

Research and Industry Experience

  • Research Assistant, Vanderbilt University
    2023-Present

    Conduct research on trustworthy code intelligence, spanning cognitive supervision, code-model training, verification-guided generation and repair, authorship attribution, and empirical software security.

Research Mentoring

  • Anda Liang, Undergraduate Researcher
    Fall 2023-Summer 2024

    Co-authored an ICSE 2025 paper on GitHub impersonation; later joined NASA Jet Propulsion Laboratory.

Teaching Experience

Vanderbilt University

  • CS8395 Special Topics: Advanced Topics in Software Engineering
  • CS-5278 Principles of Software Engineering

Technical Skills

  • Programming and ML: Python, Java, Shell, PyTorch, TensorFlow.
  • Methods: Supervised fine-tuning, preference optimization, reinforcement learning, LoRA/QLoRA, Lean, program graphs, static analysis, and empirical software engineering.
  • Languages: Mandarin (native), English (fluent).

Presentations

Leveraging Fuzzy System to Reduce Uncertainty of Decision Making in Software Engineering Automation (GI 2022)

Date: June 8, 2022
Slides: Link

Academic Performance

Overall GPA: 3.9/4