Papers

5

Total Citations

36

H-Index

3

About

Guangyao Shi is an emerging researcher at the intersection of artificial intelligence, robotics, and computer vision, with a focus on multimodal learning, autonomous systems, and robot-assisted applications. His most-cited work, a comprehensive survey on Large Vision Language Models (2025, 18 citations), establishes him as a thoughtful synthesizer of cutting-edge developments in multimodal AI, examining how models like CLIP bridge visual and textual understanding. His work on LAVA (2024, 8 citations) demonstrates a strong applied dimension, advancing robotic-assisted feeding systems capable of handling complex, liquid-rich foods — a meaningful contribution to assistive technology for individuals with mobility impairments. Shi also investigates multi-robot coordination, as seen in his risk-aware resource allocation framework for UAV-UGV recharging rendezvous (2022), and pushes the boundaries of robust control theory through data-driven distributionally robust methods under state-dependent uncertainty (2023). His exploration of Large Language Models for robot routing further reflects his commitment to integrating generative AI into real-world autonomous systems. Across these diverse yet interconnected domains, Shi consistently bridges theoretical rigor with practical impact, making his work valuable reading for researchers in robotics, AI, and human-assistive technologies.

Research Focus

Key Achievements

3
H-Index
5
Papers
36
Total Citations
7
Avg Citations/Paper
🏆 Most Cited Paper
Benchmark Evaluations, Applications, and Challenges of Large Vision Language Models: A Survey
18 citations · 2025
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 16
🏛 Institutions: University of Southern California, University of Maryland, College Park

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago