Papers
3
Total Citations
8
H-Index
2
About
Te Cui is a rising researcher in robotics and artificial intelligence, specializing in imitation learning, foundation models, and multimodal perception for robotic manipulation. Their work addresses critical challenges in skill acquisition by leveraging abundant, low-cost data sources. Cui’s major contributions include developing **GraphMimic**, a novel graph-to-graph generative model that learns robotic policies directly from video demonstrations, bypassing the need for expensive action-labeled data. This work has already garnered 4 citations since its 2025 publication. They further advanced the field with **FMimic**, demonstrating how foundation models—particularly vision-language models—can serve as fine-grained action learners from human videos, achieving 3 citations. Additionally, Cui has explored high-precision object pose estimation for dynamic robotic grasping by fusing visual and tactile information, a critical contribution for tasks like factory assembly. Their research consistently pushes toward more data-efficient, generalizable, and physically capable robotic systems. With a clear trajectory of impactful publications, Te Cui is establishing themselves as a key innovator in next-generation robot learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3