Pang Wei Koh

I'm interested in making machine learning systems more useful, responsible, and reliable in the real world. For example:

• Access. How can we expand our access to foundation models, so that we can better understand, build upon, and adapt them? We develop new methods, architectures, and data for efficiently training and deploying fully open models.
• Reliability. How do we make our models more reliable and trustworthy? We design new approaches to evaluation and are working on the next generation of retrieval-based models that can reason directly over data.
• Impact. What can we do with AI that we could not do before, e.g., accelerate scientific discovery or provide universal access to medical advice?

I received my PhD in Computer Science from Stanford, advised by Percy Liang. Before that, I was the 3rd employee and Director of Partnerships at Coursera. I was also an undergraduate at Stanford, advised by Andrew Ng and Daphne Koller.

I'm part of the UW ML and NLP groups, and I'm also a visiting research scientist at AI2. If you're interested in joining our group, please read this. This cycle, I'm also looking for prospective students/postdocs interested in AI for science.

Current students

Scott Geng
(with Ranjay Krishna)

Jacqueline He
(with Luke Zettlemoyer)

Rulin Shao
(with Luke Zettlemoyer)

Rui Xin
(with Sewoong Oh)

Ian Magnusson
(with Noah Smith)

Zhiyuan Zeng
(with Hanna Hajishirzi)

Alumni

• Irena Gao (MS 2023, now PhD student at Stanford University)
• Kendrick Shen (MS 2022, now ML research engineer at Genesis Therapeutics)
• Henrik Marklund (MS 2021, now PhD student at Stanford University)
• Kai-Siang Ang (MS 2021, now ML engineer at Nuro)
• Erik Jones (MS 2020, now PhD student at UC Berkeley)
• Hubert Teo (MS 2019, now senior software engineer at Flock Freight)
• Thao Nguyen (BS 2019, now PhD student at the University of Washington)
• Yew-Siang Tang (BS 2019, now senior software engineer at You.com)

Publications

* = equal contribution.