Yu Bao (鲍宇)

Logo

View My GitHub Profile

About Me

This is Yu Bao (鲍宇). My name in Chinese Pinyin has two interesting extensions, one means rainstorm (🌧) and the other means abalone (🐟). I prefer the former one, as it looks very powerful. Actually, my name comes from “Staying together through thick and thin (fēng yǔ tóng zhōu)” because I also have an older brother named Feng Bao.

I am currently a research scientist at ByteDance Research since Apr. 2022. Before that, I did my Ph. D. in the Natural Language Processing Group@Nanjing University, where I was co-advised by Prof. Shujian Huang and Prof. Jiajun Chen. I also interned twice at ByteDance AI Lab, and my mentors were Prof. Zhou Hao and Prof. Lei Li. I obtained a bachelor’s degree from the School of Science of Northeast Forestry University in 2015.

All of my research interests focus on deep generative models. During my Ph. D. studies and internships at ByteDance AI Lab, I worked on structure and sequence modeling in deep generative models, focusing on machine translation and natural language generation. Now, as a member of ByteDance Research, my focus has turned to AI for Science, especially structure-based drug design.

[Email] [CV]

Selected Publications/Preprints

[Full Publications] [*: equal contributions] [†: interns/students I mentored]

  1. Shimao Zhang†, Yu Bao, Shujian Huang, EDT: Improving Large Language Models by Entropy-based Dynamic Temperature Sampling, Preprint 2024.
  2. Xiangxin Zhou*†, Xiwei Cheng*†, Yuwei Yang, Yu Bao, Liang Wang, Quanquan Gu, DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization, ICLR 2024.
  3. Jiaqi Guan*†, Xiangxin Zhou*†, Yuwei Yang, Yu Bao, Jian Peng, Jianzhu Ma, Qiang Liu, Liang Wang, Quanquan Gu, DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design, ICML 2023.
  4. Min Liu†, Yu Bao, Chengqi Zhao, Shujian Huang, Selective Knowledge Distillation for Non-Autoregressive Neural Machine Translation, AAAI 2023.
  5. Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei Li, latent-GLAT: Glancing at Latent Variables for Parallel Text Generation, ACL 2022.
  6. Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei Li, Glancing Transformer for Non-Autoregressive Neural Machine Translation, ACL 2021.
  7. Yu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen, Non-Autoregressive Translation by Learning Target Categorical Codes, NAACL-HLT 2021.
  8. Jiahuan Li*, Yu Bao*, Shujian Huang, Xinyu Dai, Jiajun Chen, Explicit Semantic Decomposition for Definition Generation, ACL 2020.
  9. Yu Bao, Hao Zhou, Jiangtao Feng, Mingxuan Wang, Shujian Huang, Jiajun Chen, Lei Li, PNAT: Non-Autoregressive Transformer by Position Learning, Preprint 2019.
  10. Yu Bao*, Hao Zhou*, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xinyu Dai, Jiajun Chen, Generating Sentences from Disentangled Syntactic and Semantic Spaces, ACL 2019.

Professional Services

Area Chair of

Journal Reviewer of

PC Member/Reviewer of