Our team focuses on advancing text-to-video editing and text-to-4D generation technologies to enable more dynamic and immersive content creation. Our core projects explore how to achieve more precise text-to-video editing and stronger consistency in 3D/4D scene generation models.
Our team aims to identify and quantify potential safety issues in large language models such as inconsistency and privacy leakage, which will be mitigated by developing novel AI techniques to finetune standard large language models.
AI research is both theoretical and computational. It is important to have a deep understanding of different AI models’ error bounds and associated factors. One of our recent studies is to analyze the impact of data distribution on fairness guarantees in equitable deep learning.
AI-powered smart devices and robotics for low vision
AI-powered smart devices such as smart glasses and robotics have emerged as a promising way to assist people with low vision. We are developing multimodal AI models that are optimized for visually impaired individuals, which will be used with smart glasses and robotics.
Our team is dedicated to developing equitable AI models for disease screening with a special focus on ocular diseases. Recently, we have developed a fair identity normalization technique to improve model performance equity.
Our team is dedicated to developing AI-based data cleaning technologies, aiming to provide cleaner data and enhance diagnostic outcomes for eye diseases.
Our team aim to better characterize the functional loss from ocular diseases with the goals of developing novel diagnostic methods and improving the progression prediction.
Our team aims to design a deep learning model to quantify the retinal layer importance and regional importance of each retinal layer in predicting various ocular and systematic diseases.
