Jin Huang

Background

About Jin Huang

I am an Applied Researcher at Pixocial, focusing on Generative AI — specifically on image and video generation and editing. My work centers on state-of-the-art diffusion-based and transformer-driven large generative models, advancing algorithms for high-quality, controllable video synthesis and editing. Before joining Pixocial, I completed my Ph.D. in Computer Science at the University of Notre Dame, working with Dr. Walter Scheirer at Computer Vision Research Lab (CVRL). My Ph.D. research combined Computer Vision and Machine Learning with cognitive science, exploring how human perception can guide or enhance machine learning, proposing a human-in-the-loop framework to assist AI models. During the past decade, I have worked on a broad range of topics that are related with Computer Vision, ranging from fundamental problems in vision such as segmentation, classification and detection, to most recent multi-modal foundational models and Large Language Models.