Cheng Shi (石骋) PhD Student Department of Computer Science The University of Hong Kong Email: shicheng2025 [at] connect [dot] hku [dot] hk GitHub | Google Scholar

Biography

I am currently a first-year Ph.D. student at Department of Computer Science, The University of Hong Kong, where I have the privilege of being supervised by Prof. Yizhou Yu (ACM/IEEE Fellow). Previously, I obtained my Master's degree from ShanghaiTech University in 2024, where I was advised by Prof. Sibei Yang, and my Bachelor's degree from ShanghaiTech University in 2022.

My research interests lie at the intersection of computer vision, natural language processing, and multimodal AI. My current research focuses on open-world visual perception and vision foundation models.

News

Education

Ph.D
The University of Hong Kong, Hong Kong, China
2025.09 - now

Master & Bachelor
ShanghaiTech University, Shanghai, China
Outstanding Graduate of Shanghai / Outstanding Graduate of ShanghaiTech University
2018.09 - 2025.06

Selected Publications

* denotes equal contribution and † corresponding author

	Vision Transformer Needs More Than Register In submission, 2025 Cheng Shi and Sibei Yang† Paper
	Vision Function Layer in Multimodal LLMs NeurIPS 2025 Cheng Shi, Yizhou Yu and Sibei Yang Paper Code
	Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video NeurIPS 2025 Yulin Zhang, Cheng Shi, Yang Wang and Sibei Yang† Paper
	Part2Object: Hierarchical Unsupervised 3D Instance Segmentation ECCV 2024 Cheng Shi*, Yuling Zhang*, Bin Yang, Jiajin Tang, Yuexin Ma and Sibei Yang† Paper Code
	Plain-DNet: A Plain Multi-Dataset Object Detector ECCV 2024 Cheng Shi*, Yuchen Zhu* and Sibei Yang† Paper Code
	Zip-Your-CLIP: CLIP Itself is a Good Object-detector ICLR 2024 Cheng Shi and Sibei Yang† Paper Code