I am a Research scientist at Meta AI, primarily working on efficient NLP models for language generation and QA. Before joining Meta, I was at Microsoft Research NLP group, working on text generation and pre-training.

I received Ph.D. degree and M.S. degree (Statistical Science) from Duke University in 2018, advised by Professor Lawrence Carin. Before that, I received B.Sc. degree in Physics from Nanjing University, Department for Intensive Instruction (DII), Kuang Yaming Honors school in 2011.

I have served as an Area Chair (or equivalent) for NeurIPS (2021), ACL (2021) and AAAI (2019-2021). I have served as one of the organization committee members in ACL (2020). I received NeurIPS top reviewer awards (2019).

Please send me an email with your latest CV if you are a senior PhD student working on NLG and looking for an internship

My recent research focuses on below topics:

  • Efficient NLP models.

  • Open-domain question answering.

  • Controllable text geneneration.

  • Safe & Responsible NLP.

  • Non-autoregressive generation.

  • NLP Pretraining.