Lei Shu

Welcome,

my name is 舒蕾. I am a Research Scientist at

G

o

o

g

l

e

Deepmind

News

• Our new, Project Astra, launched at Google I/O 2025. I'm proud to lead modeling for Computer Control & Visual Overlay.
  Check out our demos:
  • Project Astra Action Intelligence
  • Project Astra x Education (Visual Tutor)
• I am no longer seeking a student researcher, as the position has been filled. Thank you to everyone who expressed interest. I am seeking a student researcher for Summer/Winter 2025 to collaborate on cutting-edge Agentic AI projects. If you are interested, please apply via Google Careers and send me an email once the recruiter confirms your inclusion in the candidate pool.

Publications

2024

• RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting
  Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, Canoee Liu, Simon Tong, Jindong Chen, Lei Meng
  AAAI 2024 [paper]
• Fusion-Eval: Integrating Assistant Evaluators with LLMs
  Lei Shu, Nevan Wichers, Liangchen Luo, Yun Zhu, Yinxiao Liu, Jindong Chen, Lei Meng
  EMNLP 2024 Industry [paper]
• Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic
  Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng
  EMNLP 2024 Main [paper]
• Improve Mathematical Reasoning in Language Models by Automated Process Supervision
  Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, Abhinav Rastogi
  arXiv:2406.06592 [preprint]
• Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection
  Yun Zhu, Jia-Chen Gu, Caitlin Sikora, Ho Ko, Yinxiao Liu, Chu-Cheng Lin, Lei Shu, Liangchen Luo, Lei Meng, Bang Liu, Jindong Chen
  arXiv:2405.16178 [preprint]

2023 and before (Selected Papers)

• Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
  Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang
  ACL 2022 [preprint] [bib] [code]
• Zero-Shot Out-of-Distribution Detection Based on the Pretrained Model CLIP
  Sepideh Esmaeilpour, Bing Liu, Eric Robertson, Lei Shu
  AAAI 2022 [paper] [bib]
• Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
  Zixuan Ke, Bing Liu, Nainzu Ma, Hu Xu, Lei Shu
  NeurIPS 2021 [code]
• BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
  Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
  NAACL 2019 [preprint][code][dataset]
• Unseen Class Discovery in Open-world Classification
  Lei Shu, Hu Xu, Bing Liu
  arXiv 2018 [preprint][bib]
• DOC: Deep Open Classification of Text Documents
  Lei Shu, Hu Xu, Bing Liu
  EMNLP 2017 [paper][bib][video][dataset][code]

Services and Awards

I actively serve as an Area Chair for ACL ARR (covering ACL, EMNLP, NAACL, EACL, and COLING) and as a reviewer for conferences including NeurIPS, ICML, ICLR, AAAI, IJCAI, WACV, and others.