Fan Yang

I work on computer vision and machine learning problems. I enjoy building the product that can scale, while doing applied research and occasionally publishing.

Most recently, I am involved in Google’s large multimodal generative model development, a.k.a., Gemini, with an focus on fine-tuning and its various downstream applications. Prior to that, I worked on Google’s MobileNetV4, designed and optimized vision models for various Google products, such as Photos, AR Core and Cloud, etc., created the first anomaly detection models behind Google Cloud Inspection AI, and built image search from the ground up for eBay’s first conversational chatbot.

I also spent great time as a research intern at NEC Labs and SRI International.

I obtained my Ph.D in Computer Science from the University of Maryland, College Park, advised by Prof. Larry S. Davis. I was also affiliated with the University of Maryland Institute for Advanced Computer Studies (UMIACS). Before that, I obtained my Master in Information Processing from Dalian University of Technology, advised by Prof. Huchuan Lu.