Bingbing Wen

I am a PhD student at University of Washington. I’m fortunate to be advised by Prof. Bill Howe and Prof. Lucy Lu Wang. I also work closely with Prof. Yulia Tsvetkov. I’m a member of UW RAISE Center and The AI Clinic.

My research focuses on three key areas: Data Efficiency through Curation and Optimization - optimizing data mixtures and designing fine-grained preference signals that go beyond correctness; Model Efficiency via Modular and Adaptive Architectures - exploring mixture-of-LoRA experts, routing mechanisms and reinforcement learning approaches to enhance collaboration among multiple specialized models; and Evaluation for Efficient Reliability - designing abstention and confidence-based evaluation frameworks that help models decide when not to compute unnecessary outputs.

During my PhD, I had the opportunity to conduct research internships at Apple, Microsoft Cloud AI, and OPPO Research, where I explored challenges in building large-scale AI systems. I also collaborate closely with the Allen Institute for AI.

I actively mentor undergraduate and master students in developing and carrying out research projects–feel free to reach out if you’re interested in my research or PhD application.