Geng Li

Biography

Hi there! Welcome to my personal pages!

I am Geng Li, a first-year PhD student at Nanyang Technological University, majoring in Mechanical and Aerospace Engineering.

My research interests currently lie in Doule E AI, which means Embodied AI and Efficient AI.

If you are interested in my work or would simply like to chat, feel free to send me an email!

Please feel free to check my CV.

	UniRiT: Towards Few-Shot Non-Rigid Point Cloud Registration. Geng Li, Haozhi Cao, Mingyang Liu, Chenxi Jiang, Jianfei Yang. Under review [arxiv] [paper] The MedMatch3D dataset of real organ point clouds is introduced, addressing the few-shot problem by decomposing non-rigid motion and proposing a novel method for few-shot N-PCR.
	GERA: Geometric Embedding for Efficient Point Registration Analysis. Geng Li, Haozhi Cao, Mingyang Liu, Shenghai Yuan, Jianfei Yang. International Conference on Robotics and Automation(ICRA 2025) [arxiv] [paper] [video] GERA introduces an offline geometric encoder for efficient non-rigid point cloud registration, using supervised training to minimize differences in high-dimensional geometric features instead of absolute positions.
	LCNet: A Robust and Accurate Non-Rigid 3D Point Set Registration Approach for Image-Guided Liver Surgery. Mingyang Liu, Geng Li, Hao Yu, Rui Song, Yibin Li, Max Q.-H. Meng, Zhe Min. IEEE Transactions on Medical Robotics and Bionics [paper ] This work presents LCNet, an unsupervised learning-based method for non-rigid 3D point set registration, specifically designed for enhancing image-guided liver surgery.

Fitting

Cooking

Basketball

Hiking

Shooting