Sheng Zhang

I am currently a research assitant at MBZUAI (Mohamed Bin Zayed University of AI) advised by Prof. Kun Zhang from Carnegie Mellon University. Prior to this, I earned a Master degree at MBZUAI, where I was fortunate to be advised by Prof. Salman Khan and co-advised by Prof. Zhiqiang Shen. I completed my undergraduate studies in Software Engineering at Tongji University in China. Besides, I am collaborating closely with Dr. Guangyi Chen and Dr. Muzammal Naseer.

My primary research interests lie in learning visual concepts within the open-world contexts, based on self-supervised learning, latent-variable modeling, and causality. My goal is generalizing to novel visual concepts as well as understanding their physical properties/relationships, with few human supervision.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github  /  Twitter  / 

profile photo
PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery
Sheng Zhang, Salman Khan, Zhiqiang Shen, Muzammal Naseer, Guangyi Chen, Fahad Khan
CVPR, 2023
project page / arXiv / paper /

Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment
Sheng Zhang, Muzammal Naseer, Guangyi Chen, Zhiqiang Shen, Salman Khan, Kun Zhang, Fahad Khan
AAAI, 2024 ( Oral Presentation )
project page / arXiv /

Academic Services

Volunteer at AAAI 2024

Reviewer for CVPR 2024

Reviewer for ACM Computing Surveys 2023

Reviewer for AISTATS 2024

Reviewer for ICCV-Workshop 2023

Volunteer at EMNLP 2023