Fan Bao   Ph.D. Candidate Room 1-509, FIT Building Dept. of Computer Science and Technology Tsinghua University Beijing, China, 100084. Email: bf19@mails.tsinghua.edu.cn Github: baofff [Google Scholar]

Biography

I am a third-year Ph.D. student of TSAIL Group in the Department of Computer Science and Technology, Tsinghua University, advised by Prof. Jun Zhu and Prof. Bo Zhang. Before that, I received my B.S. degree from the Department of Computer Science and Technology, Tsinghua University in July, 2019.

My research interest includes machine learning and deep learning. Recently, I am interested in deep generative models and its applications in multi-modality, computer vision and AI4Science.

Publications

• All are Worth Words: a ViT Backbone for Diffusion Models
  Fan Bao, Shen Nie, Kaiwen Xue, Yue Cao, Chongxuan Li, Hang Su, Jun Zhu
  Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  [arXiv] [code]
• Equivariant Energy-Guided SDE for Inverse Molecular Design
  Fan Bao*, Min Zhao*, Zhongkai Hao, Peiyao Li, Chongxuan Li, Jun Zhu
  International Conference on Learning Representations (ICLR), 2023
  [arXiv] [code]
• Why Are Conditional Generative Models Better Than Unconditional Ones?
  Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu
  Score-based Model workshop @ NeurIPS, 2022
  [arXiv]
• EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations
  Min Zhao, Fan Bao, Chongxuan Li, Jun Zhu
  Conference on Neural Information Processing Systems (NeurIPS), 2022
  [arXiv] [code]
• Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models
  Yong Zhong, Hongtao Liu, Xiaodong Liu, Fan Bao, Weiran Shen, Chongxuan Li
  International Conference on Learning Representations (ICLR), 2023
  [arXiv]
• DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
  Oral (Accept rate~1.7%)
  Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu
  Conference on Neural Information Processing Systems (NeurIPS), 2022
  [arXiv] [code]
• Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models
  Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu, Bo Zhang
  International Conference on Machine Learning (ICML), 2022
  [arXiv] [code]
• Maximum Likelihood Training for Score-based Diffusion ODEs by High Order Denoising Score Matching
  Cheng Lu, Kaiwen Zheng, Fan Bao, Chongxuan Li, Jianfei Chen, Jun Zhu
  International Conference on Machine Learning (ICML), 2022
  
• Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
  Outstanding Paper Award (Top 7/3391)
  Fan Bao, Chongxuan Li, Jun Zhu, Bo Zhang
  International Conference on Learning Representations (ICLR), 2022
  [arXiv] [code]
• Stability and Generalization of Bilevel Programming in Hyperparameter Optimization
  Fan Bao*, Guoqiang Wu*, Chongxuan Li*, Jun Zhu, Bo Zhang
  Conference on Neural Information Processing Systems (NeurIPS), 2021
  [arXiv] [code]
• Variational (Gradient) Estimate of the Score Function in Energy-based Latent Variable Models
  Fan Bao, Kun Xu, Chongxuan Li, Lanqing Hong, Jun Zhu, Bo Zhang
  International Conference on Machine Learning (ICML), 2021
  [arXiv] [code]
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
  Fan Bao*, Chongxuan Li*, Kun Xu, Hang Su, Jun Zhu, Bo Zhang
  Conference on Neural Information Processing Systems (NeurIPS), 2020
  [arXiv] [code]

Honors & Awards

ByteDance Scholarship, 2022.10

China National Scholarship, 2022.10

LongHu Scholarship, 2022.9

Yang Huiyan Scholarship, 2021.10

Services

Reviewer for:
NeurIPS 2021, 2022
ICML 2021, 2022
ICLR 2022, 2023
CVPR 2023

Invited Talks

Applications of Diffusion Models, ByteDance, 2022.5 [slide]

Teaching

2021 Spring, TA in Statistical Learning Theory and Applications, instructed by Prof. Jun Zhu
2021 Spring, TA in Deep Learning, instructed by Prof. Xiaolin Hu and Prof. Jun Zhu
2019 Fall, TA in Calculus, instructed by Prof. Jianlian Cui