CV

Yuanhao Zou

Orlando, FL | yuanhaoz@ucf.edu | 734-358-6400

University of Central Florida, Orlando | PhD. in Computer Science Aug 2025 – Present

Advisor: Chen Chen
Research Interest: Video Understanding, Efficient Vision Language Model, Video Anomaly Detection.

University of Michigan, Ann Arbor | MS in Electrical and Computer Engineering Aug 2023 – May 2025

GPA: 4.0/4.0
Coursework: Computer Vision (A), Machine Learning (A), Advanced Computer Vision (A), Robotic Mathematics (A+), Large Language Model.

Central South University, China | BE in Computer Science and Technology Sep 2019 – Jun 2023

GPA: 88/100
Coursework: Machine Learning, Distributed System & Cloud Computing, Digital Image Processing, Computer Vision, Android Development, Bioinformatics, Computer Architecture, Data Structure & Algorithm.

Axon Oct. 2025 – Dec. 2025

Efficient Vision Language Model: Developing efficient video anomaly detection model for edge devices like Axon AB4, effectively handling images in low-level and extreme conditions.

University of Central Florida | Advisor: Prof. Chen Chen Feb. 2025 – Present

Video Understanding: Frame Selection Model integrates fast lightweight models like CLIP and heavy vision language model, achieving better performance and efficiency. A paper submitted to ICLR 2026.
Efficient Vision Language Model: Developing efficient vision language models that used on edge devices. A current internship with Axon.

Stony Brook University | Advisor: Prof. Zhaozheng Yin Feb 2024 – Nov 2024

Medical Vision-Language model: (1) Addressed challenges in cross-modality understanding and the underutilization of multi-view images in medical radiology datasets, and applied to Medical VQA and Medical Image-Report Retrieval. (2) Developed a unified representation alignment approach with hard negative mining and selective knowledge fusion to enhance Med-VQA performance significantly.
Outcomes: First Author of two research papers to CVPR 2025.

University of Nottingham Ningbo China (UNNC) | Advisor: Prof. Xiangjian He Sep 2022 – Aug 2023

Medical Image Segmentation: Developed a deep learning network integrating U-Net and Transformer for hybrid attention and multi-scale fusion modules to address challenges with limited samples and small objects in a new cervical dataset.
Outcomes: A paper published to Journal Knowledge-Based Systems.

Proficient Technologies: Pytorch, Linux, Lightning, Git