|
I am a Research Scientist at Allen Institute for AI. I lead research on automating data-driven discovery for Asta, Ai2's agentic ecosystem for scientific research. I received my Ph.D. in Computer Science from UC San Diego, advised by Julian McAuley. I was fortunate to receive UCSD CSE Doctoral Award for Excellence in Research (2022), Adobe Research Fellowship (2022), Qualcomm Innovation Fellowship (2020), and
led UCSD (Team Bernard) in Amazon Alexa Prize, 2019. |
|
| Previously, I spent wonderful summers at Facebook AI Research, Microsoft Research, and Google AI Research. I worked as a technical editor for The Batch, a weekly newsletter by deeplearning.ai. I also co-authored a best-selling book on NLP with O'Reilly Media. |
|
My research goal is to develop communicative reasoners that can learn, adapt, and reason by interacting with the world and produce effective, explainable, and equitable outcomes. I apply my research to advance the frontier of science. I led the development of Asta DataVoyager, a data-driven discovery tool to accelerate science with generative AI. We are the first to introduce the trustworthy evaluation harness for AI agents solving autonomous scientific discovery tasks.Research highlights includes DataVoyager, Auto-discovery with Surprisal, DiscoveryBench, DiscoveryWorld, CodeScientist. I also design, train, and evaluate LLM agents at scale. See my full body of work in Publications. |
|
|
|
|
Practical Natural Language Processing
distills our collective wisdom on building real world applications such as data collection, working with noisy data and signals, incremental development of solutions, and issues involved in deploying the solutions as a part of a larger application - bridging a gap between current textbooks and online offerings.
|
|
|
|
Thanks to Jon Barron for this nice template! |
