Lei Li

University of California Santa Barbara

Co-Director, UCSB NLP Group
Associate Professor, Computer Science Department

Research area: natural language processing, machine learning, data mining.


  • Machine translation, speech translation, multilingual NLP.
  • LLM, text generation, program synthesis, reasoning, privacy, watermark.
  • AI for drug design
  • Efficient ML


  • CGMH: A method for controllable text generation from specified keywords. [arxiv]
  • Analyzing anisotropic sentence embeddings from pre-trained language models. [arxiv]
  • Data-efficient methods for many-to-many neural machine translation. [mRASP, mRASP2]
  • Glancing Transformer (GLAT): non-autoregressive translation models are equally good as autoregressive Transformer. [arxiv]
  • VOLT: Learning vocabulary via optimal transport (ACL 2021 Best Paper). [arxiv]
  • SOLO: Fast and accurate object instance segmentation. [SOLO, SOLOv2]