Dianyi Yang | 杨殿一

I am a first-year Ph.D. student at the School of Computer Science and Technology, Beijing Institute of Technology, advised by Wei Liang. I received my Bachelor's degree in 2023 and Master's degree in 2025 from Beijing Institute of Technology, under the supervision of Yi Yang.

I'm currently working at General Vision Lab in BIGAI (Beijing Institute for General Artificial Intelligence) as a research intern, advised by Baoxiong Jia and Siyuan Huang.

Email  /  Github   

Currently, my research is centered on computer vision and embodied artificial intelligence, with a particular emphasis on visual perception, interactive reasoning, and 3D scene understanding. Looking ahead, my work will explore embodied scene interaction within the real2sim2real paradigm, aiming to advance methodologies that improve both the efficiency and fidelity of data acquisition. In parallel, I am investigating the development of more effective learning paradigms to support robust and scalable embodied intelligence across diverse environments.

Responsible for researching semantic scene representation based on 3DGS to achieve efficient object-level localization and semantic learning. Our current work focuses on embodied interaction and active perception.

Responsible for partial hardware debugging of the robot and tasks related to semantic cognition. Our future work will focus on vision-language navigation and monocular outdoor autonomous exploration.

Responsible for the development of the entire system, including multi-camera calibration, real-time image transmission, camera gimbal testing, and software design.

Responsible for the embedded development of the robot's core functionalities, including human-machine interaction devices and intelligent capacity detection systems.

Responsible for leading the team in an in-depth study of the laboratory's key research achievement—the intelligent unmanned logistics tractor—and participating in academic science and technology competitions.