About me

I’m a second-year PhD student at the University of Colorado Boulder in the Image and Video Computing Group, advised by Prof. Danna Gurari. My research focuses on vision-language models that capture hierarchical object compositions for visual grounding and accessibility. I also help organize the VizWiz Grand Challenge, an annual CVPR workshop advancing accessibility research in computer vision.

Before starting my PhD, I co-founded RoastPic with Prof. William Ristenpart, a platform that helps coffee companies such as Peet’s and Starbucks evaluate roast profiles through visual analysis. I also worked with Prof. Jiawei Zhang at UC Davis on vision-language modeling and video quality assessment.

Outside of research, I enjoy climbing, skiing, and specialty coffee (I’m a certified Q Arabica Grader). You can find some of my climbs on my Mountain Project page.

Publications and Technical Reports

• Accounting for Focus Ambiguity in Visual Questions
  Chongyan Chen*, Yu-Yun Tseng*, Zhuoheng Li, Anush Venkatesh, Danna Gurari
  ICCV 2025

• Pathogenic potential prediction of Vibrio parahaemolyticus by using pangenome data with high performance machine learning algorithms
  Zhuosheng Liu, Zhuoheng Li, Jiawei Zhang, C Titus Brown, Luxin Wang
  bioRxiv Preprint

• A Survey of AI-Generated Video Evaluation
  Xiao Liu, Xinhao Xiang, Zizhong Li, Yongheng Wang, Zhuoheng Li, Zhuosheng Liu, Weidi Zhang, Weiqi Ye, Jiawei Zhang
  arXiv Preprint

• Parameter-Efficient Fine-Tuning for Vision-Language Models
  Zhuoheng Li, Zhuosheng Liu, Jiawei Zhang
  Technical Report

• CLIPath: Fine-tune CLIP with Visual Feature Fusion for Pathology Image Analysis Towards Minimizing Data Collection Efforts
  Zhengfeng Lai, Zhuoheng Li, Luca Cerny Oliveira, Joohi Chauhan, Brittany N. Dugger, Chen-Nee Chuah
  ICCV 2023 Workshop on Computer Vision for Automated Medical Diagnosis