Papers
1
Total Citations
15
H-Index
1
About
Yu Su is a prominent researcher at the intersection of artificial intelligence, robotics, and vision-language modeling, with a particular focus on enabling machines to understand and interact with the physical world. His work spans spatial reasoning, multimodal learning, and the application of large language models to real-world robotic systems. Su's most notable recent contribution, "RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics" (2025), addresses a fundamental challenge in modern robotics: equipping vision-language models with the spatial perception capabilities necessary for meaningful environmental interaction. This work has already garnered 15 citations since its publication, a remarkable early indicator of its impact within the robotics and AI communities. By bridging the gap between language-grounded reasoning and three-dimensional spatial understanding, Su's research pushes the boundaries of what autonomous systems can perceive and accomplish. His contributions are particularly valuable for researchers working on embodied AI, robot manipulation, and scene understanding. Students and practitioners in robotics and computer vision will find Su's work essential reading for understanding how next-generation intelligent systems can be trained to navigate and act within complex physical environments.
Research Focus
Key Achievements
Top Papers
- 1