This project aims to develop a computational framework combining computer vision, computer graphics, and machine learning to accelerate and improve the design and simulation of camera lenses.

Abstract: In recent years, reinforcement learning control theory has been well developed. However, model-free value iteration needs many iterations to achieve the desired precision, and model-free ...

Abstract: In this paper, we consider the model merging process for large language models (LLMs) under a two-stage optimization framework. Traditional merging methods usually apply fixed blending rates ...