Yuanzhi Liang
Papers
1
Total Citations
3
H-Index
1
About
Yuanzhi Liang is a rising researcher in computer vision and robotics, with a focused interest in 3D scene understanding and interactive perception. His work centers on the challenging problem of affordance learning—teaching machines to infer how to interact with objects in the physical world. In his notable 2023 paper, "MAAL: Multimodality-Aware Autoencoder-based Affordance Learning for 3D Articulated Objects," Liang introduces a novel framework that addresses the dual challenge of "where to act" and "how to act" on complex, articulated 3D objects. By leveraging a multimodality-aware autoencoder, his approach enables robots to better understand functional interaction points, a critical step toward deploying autonomous systems in unstructured, real-world environments. While still early in his career, Liang’s work is gaining traction, with his most-cited paper already accumulating 3 citations. His research bridges the gap between static 3D perception and dynamic robotic manipulation, promising to advance the field of embodied AI. For students and researchers, Liang’s work offers a compelling glimpse into the future of intelligent, physically capable machines.
Research Focus
Key Achievements
Top Papers
- 1