Summary
Yong-xiang Lin is a Senior AI Algorithms Software Engineer at NVIDIA Taiwan with a Ph.D. in Computer Science and a decade of experience building generative AI, computer vision, and multi-sensor decision systems. He specializes in curating, optimizing, and fine-tuning multimodal models (vision, text, audio) and has led MLLM fine-tuning projects that produced video+audio sports highlight systems using SOTA models like Qwen, NVILA, and Cosmos. His research background spans video diffusion models, multi-agent systems, and AI-guided camera control, bridging academic rigor with production-focused engineering. Comfortable with Azure and NVIDIA TAO tooling, he explores integrating audio foundation models into industrial pipelines to enhance training and deployment. Colleagues know him for pragmatic model choices and a “keep it simple” approach that accelerates collaboration between research and industry partners.
10 years of coding experience
博士, 資訊工程系, 博士, 資訊工程系 at 國立臺灣科技大學
德國阿亨工業大學
日語, Chinese, English