Papers
1
Total Citations
6
H-Index
1
About
Keling Yao is a leading researcher at the intersection of robotics and artificial intelligence, with a primary focus on generalizable robotic manipulation and the transfer learning of foundation models. Their most-cited work, "Transferring Foundation Models for Generalizable Robotic Manipulation" (2025), tackles the critical challenge of enabling robots to adapt to novel tasks and environments without the prohibitive cost of collecting massive, diverse real-world datasets. By demonstrating how pre-trained foundation models can be effectively transferred to robotic systems, Yao’s research offers a scalable pathway toward more versatile and cost-efficient general-purpose robots. This contribution has already garnered 6 citations in its early release, signaling strong interest from the robotics community. Yao’s work is particularly notable for addressing the longstanding bottleneck of data diversity in robotic learning, proposing solutions that reduce reliance on expensive data collection while improving real-world generalization. Their achievements position them as a rising figure in the push toward truly adaptable, foundation-model-driven robotics, with implications for both academic research and practical deployment in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1Transferring Foundation Models for Generalizable Robotic Manipulation6 citations · 2025