I am a Senior NLP Researcher at Tencent AI Lab, Seattle. My primary research interest lies in large language models (LLMs), multimodal foundation models, and how to leverage these models to build autonomous AI agents that can memorize, reason and learn. In particular, I work on topics such as tool-augmented LLMs, retrieval-augmented generation (RAG), reasoning and planning and model alignment.

I completed my Ph.D. at Language Technologies Institue at Carnegie Mellon University, where I was advised by Eric Nyberg. My thesis focuses on topics including question answering, information retrieval and commonsense reasoning. Specifically, I developed methods that can effectively leverage both explicit knowledge (e.g. text corpus, web tables, knowledge graphs) and implicit knowledge (e.g. model parameters learned from pretraining) for solving challenging reasoning tasks. During my PhD at CMU, I also work closely with Alessandro Oltramari and Jonathan Francis from Bosch Research, Filip Ilievski from University of Southern California, and Hao Cheng from Microsoft Research. Before coming to CMU, I obtained my B.S/M.S degree in computer science from Emory University, working with Jinho Choi.

Experience

• Tencent AI Lab, Bellevue, WA
  • September 2023 - present
  • Senior NLP Researcher
• Tencent AI Lab, Bellevue, WA
  • June 2023 - August 2023
  • Research Intern
• Microsoft Research, Redmond, WA
  • May 2021 - August 2021, May 2022 - August 2022
  • Research Intern at Deep Learning Group
  • Mentor: Hao Cheng
• Bosch Research and Technology Center, Pittsburgh, PA
  • May 2019 - August 2019, May 2020 - August 2020
  • Research Intern at Human-Machine Collaboration Team
  • Mentor: Alessandro Oltramari