I received my Ph.D. in Computer Science at the University of Southern California in 2024. I am very fortunate to be advised by Prof. Ram Nevatia. My research interest lies in the area of multimodal perception with vision and language, including large-scale vision-language transformers, and compositional zero-shot learning. I am now especially interested in Large Multimodal Models (LMMs), Large Language Models (LLMs) and Generative AI.

I interned at Microsoft Research Redmond in 2023. In 2021 and 2022, I spent two wonderful summers as an Applied Scientist Intern at Amazon Alexa AI, working closely with Dr. Yue (Rex) Wu.

Prior to USC, I was a Master’s student at the University of Michigan, Ann Arbor, where I worked with Prof. David Fouhey and Prof. Jia Deng. I received my Bachelor’s degree from Tsinghua University in 2017. During my undergrad time, I worked with Prof. Shi-Min Hu.

Selected Publications (Full List)

Large Language Models are Good Prompt Learners for Low-Shot Image Classification
Zhaoheng Zheng, Jingmin Wei, Xuefeng Hu, Haidong Zhu, and Ram Nevatia
CVPR 2024
Paper Code

CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
Zhaoheng Zheng, Haidong Zhu, and Ram Nevatia
WACV 2024
Paper Code

MoMo: A shared encoder Model for text, image and multi-Modal representations
Rakesh Chada, Zhaoheng Zheng, and Pradeep Natarajan
arXiv Preprint
Paper

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Ke Xu*, Yao Xiao*, Zhaoheng Zheng, Kaijie Cai, and Ram Nevatia (*Equal Contribution)
WACV 2023
Paper

FashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback
Sonam Goenka*, Zhaoheng Zheng*, Ayush Jaiswal, Rakesh Chada, Yue Wu, Pradeep Natarajan, and Varsha Hedau (*Equal Contribution)
CVPR 2022
Paper

Improving Object Detection and Attribute Recognition by Feature Entanglement Reduction
Zhaoheng Zheng, Arka Sadhu, and Ram Nevatia
ICIP 2021
Paper

Image Based Cloth Changing System
Zhaoheng Zheng, Hao-Tian Zhang, Fang-Lue Zhang, and Tai-Jiang Mu
Computational Visual Media, 2017
Paper