Zhen DongFudan University
Zhen Dong

Zhen Dong

Associate Professor
PhD Supervisor
Fudan University

Trustworthy AI-Enabled Systems

I study the reliability, robustness, and authorization of software and embodied agents, drawing on program analysis, systematic testing, and learning-based methods, including targeted post-training.

BiographyTeamResearch fundingEmail ↗

Research Highlights

Mobile GUI agent case study with successful and failed paths under visual perturbations

GUI Agent Robustness & Authorization

Studying visual robustness and permission boundaries. This case illustrates failures caused by viewport exclusion and visual ambiguity.

Read the case study ↗
AGV navigation and mapping demonstrations indoors and outdoors

Autonomous Navigation

We study reliable autonomous operation in real-world environments. These AGV demonstrations connect mapping, perception, and motion planning.

View demonstration image ↗
Robot arm grasping a bottle

VLA-Based Robotic Manipulation

We study VLA execution reliability and targeted post-training. Real-robot grasping demonstrates the manipulation setting behind this research.

View demonstration image ↗

Recent Publications

All publications ↗
  1. ISSTA2026

    RESTOR: Automated Test Oracle Generation for RESTful APIs via Reinforcement Learning

    PDF ↗Details ↗
  2. ASE2026

    Verifier-in-the-Loop LLM Solving of Heap Constraints for Concolic Execution

    PDF ↗Details ↗
  3. ISSTA2025

    Inferring PID Parameter Specification for Flight Control Program by Coordinate Search

    PDF ↗Details ↗

Awards & Honors

Details ↗