About

Hi, I’m Shengliang Deng. I’m a Ph.D. student at The University of Hong Kong, advised by Prof. Heming Cui. I received my B.Eng. degree from The University of Science and Technology of China.

I enjoy tackling challenges and difficulties. My academic journey began with a focus on robotic systems and networking. However, as time passed, I came to realize that the major roadblocks of contemporary robotics arise from algorithms and engineering practices, instead of scheduling, networking, etc. Therefore, I paused my Ph.D. study during 2023 to gain a deeper understanding of real-world problems, through industry internships in Momenta and Tusimple, and had a wonderful engineering journey.

With a strong engineering background and a high aptitude for learning new things, in early 2024, I was privileged to collaborate on embodied multimodal LLMs with esteemed researchers from BAAI and Galbot. Our goal is to develop generalizable skills and embodied models for robots to facilitate embodied AGI.

Publications

• ROG: A High Performance and Robust Distributed Training System for Robotic IoT (paper | code)

  Xiuxian Guan, Zekai Sun, Shengliang Deng, Xusheng Chen, Shixiong Zhao*, Zongyuan Zhang, Tianyang Duan, Yuexuan Wang, Chenshu Wu, Yong Cui, Libo Zhang, Yanjun Wu, Rui Wang, Heming Cui

  International Symposium on Microarchitecture (MICRO), 2022

• COORP: Satisfying Low-Latency and High-Throughput Requirements of Wireless Network for Coordinated Robotic Learning (paper | code)

  Shengliang Deng, Xiuxian Guan, Zekai Sun, Shixiong Zhao, Tianxiang Shen, Xusheng Chen, Tianyang Duan, Yuexuan Wang, Jia Pan, Yanjun Wu, Libo Zhang, Heming Cui*

  IEEE Internet of Things Journal, 2022