Scholar
Qi Zhu
Google Scholar ID: TN09YMcAAAAJ
Professor of Computer Engineering
Citations & Impact
Citations
5,399
H-index
36
i10-index
116
Publications
20
Co-authors
19
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published numerous papers, including but not limited to 'Split Adaptation for Pre-trained Vision Transformers' at CVPR 2025; an article on efficient and assured reinforcement learning-based building HVAC control in Scientific Reports; two ICLR 2025 accepted papers on large language model continual unlearning and exploring backdoor attacks against embodied LLM decision-making systems; Neurips 2024 accepted works on semantic feature learning and variational delayed policy optimization; IROS 2024 included studies on graph neural network-based multi-agent reinforcement learning for resilient distributed coordination of multi-robot systems among others.
Research Experience
- Engaged in multiple cross-layer design, verification, and adaptation projects for learning-enabled cyber-physical systems (LE-CPS), particularly addressing safety, robustness, security, energy, and data challenges when using deep neural networks in CPS and operating CPS within dynamic and uncertain environments.
Background
- Research interests include design automation for intelligent cyber-physical systems (CPS) and IoT applications, safe and robust machine learning for embodied AI systems, cyber-physical security, and energy-efficient CPS.
Miscellany
- Research spans across various application domains such as connected and autonomous vehicles, smart buildings and infrastructures, robotics, advanced manufacturing, and IoT.
