Bio:I obtained my Ph.D. from Portland State University in 2024. I am passionate to solve computer vision problems such as object recognition and detection problems and image and video processing problems by leveraging image processing, computer vision, and machine learning techniques since I was pursuing my master degree at Fu-Jen Catholic University. My Ph.D. thesis is relevant to research and develop a portable computer vision tool to assist programmers for prototyping computer vision software effectively. Regardless of my thesis, I am also passionate about applications of Generative Models (GANs and Diffusion Models), Efficient Deep Neural Networks (Compression, Pruning, Quantization, and Distillation), and applications of Multimodal Learning.Lovely learning new techniques and solving complex problems in machine learning and computer vision via research collaboration and working projects together.Current side projects: Vision Language Models and Multimodal Large Language Models (MLLMs).Links:1. Google Scholar: https://scholar.google.com/citations?user=O5utQngAAAAJ&hl2. Github: https://github.com/LiYunJamesPhDLooking for full-time roles:1. Deep learning, AI, or machine learning, or computer vision engineer2. Applied scientist in machine learning, deep learning, or computer vision3. Research engineer in machine learning, deep learning, or computer vision4. Research scientist in machine learning, deep learning, or computer vision