👋 Zhexi Luo

I am Zhexi Luo, an undergraduate in Computer Science at Sun Yat-sen University, where I conduct research at ISEE@SYSU. Currently, I am a research intern at LinS Lab, advised by Lin Shao.

My research interests focus on robot learning. My research aims to integrate foundation models into robotic systems to enable general, dexterous, and robust manipulation, focusing on learning frameworks for reliable control in unstructured settings.

If you have any ideas or thoughts related to my research, feel free to reach out!

📧 Email  /  📄 CV  /  💻 Github  /  💬 WeChat

profile photo

📰 News

  • 2026.2 🎉 OmniDexGrasp accepted by ICRA 2026!
  • 2026.2 🎉 DriftTrace accepted by IEEE T-IFS!
  • 2026.1 🤝 Participated in the development of RoboVerse V2
  • 2025.11 🔬 Started research internship at LinS Lab@NUS, advised by Lin Shao
  • 2025.10 🤖 Attended CoRL 2025, met many fascinating robots!
  • 2025.9 📝 Completed my first work in robotics! Media coverage
  • 2025.4 🚀 Started my journey in robotics research

📚 Research

OmniDexGrasp: Generalizable Dexterous Grasping via Foundation Model and Force Feedback
Yi-Lin Wei*, Zhexi Luo*, Yuhao Lin, Mu Lin, Zhizhao Liang, Shuoyu Chen, Wei-Shi Zheng
Accepted, IEEE International Conference on Robotics and Automation (ICRA), 2026
arXiv / project page / code

A generalizable dexterous framework that leverages generative foundation models to achieve omni-capabilities across diverse user prompts, dexterous embodiments, and grasping tasks.

DriftTrace DriftTrace: Combating Concept Drift in Security Applications through Detection and Explanation
Yuedong Pan, Lixin Zhao, Tao Leng, Zhexi Luo, Lijun Cai, Aimin Yu, Dan Meng
Accepted, IEEE Transactions on Information Forensics and Security (T-IFS), 2026
IEEE Xplore

A unified framework that combines detecting, explaining, and adapting to out-of-training-distribution (OOD) data for improving model robustness in dynamic open-world environments.

🔬 Project

Smoke Removal Project Smoke Removal in Laparoscopic Surgical Videos Using Temporal Smoke-Free Semantic Information

Developed a novel framework that integrates video prediction and image desmoking to address surgical smoke in laparoscopic videos. By leveraging temporal semantic information from smoke-free frames within a Cycle-GAN based architecture, the framework achieves real-time smoke removal and demonstrates superior performance over existing approaches, improving surgical visibility and safety.

💼 Experience

LinS Lab

LinS Lab @ NUS

Research Intern, advised by Lin Shao

2025.11 - Present

SYSU

Sun Yat-sen University

Bachelor in Computer Science and Technology

2022 - Present

🏆 Awards

  • First Prize in National Mathematical Contest in Modeling, 2023






WeChat QR Code