Yu Cui

Papers

Total Citations

H-Index

About

Yu Cui is an emerging researcher at the forefront of robotic manipulation and representation learning, with a particular focus on dexterous grasping and multimodal sensory integration. His work addresses some of the most technically demanding challenges in robotics — enabling machines to grasp and manipulate objects with human-like dexterity and adaptability. Cui's most-cited contribution, *DexRepNet* (2023, 21 citations), advances dexterous robotic grasping by combining geometric and spatial hand-object representations within a deep reinforcement learning framework, significantly reducing the sample complexity that typically plagues high-degree-of-freedom robotic systems. Building on this foundation, his 2024 work on masked visual-tactile pre-training pioneers the integration of tactile feedback into robot manipulation learning — a dimension frequently overlooked by vision- and language-centric approaches. His subsequent work, *InterRep*, further refines how pre-trained vision models can extract richer interaction representations for robotic grasping tasks. Together, these contributions signal a cohesive research vision: bridging perception, touch, and motor control to create more capable and generalizable robotic systems. With a growing citation record and innovative cross-modal approaches, Cui represents a promising voice in next-generation robot learning research.