Cheng Lu (路橙)  Ph.D. Candidate Room 1-509, FIT Building Dept. of Computer Science and Technology Tsinghua University Beijing, China, 100084. Email: lucheng.lc15@gmail.com Github: LuChengTHU [Google Scholar] [CV]

Biography

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

Currently, my research interest includes topics on theoretical understandings and scalable algorithms for deep generative models, including diffusion models, normalizing flows and energy-based models, and their applications in computer vision, 3D generation and offline reinforcement learning.

Selected Research

• ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
  Zhengyi Wang*, Cheng Lu*, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu
  [arXiv] [project]
  
  • State-of-the-art text-to-3D generation with solely 2D diffusion models.
• DPM-Solver and DPM-Solver++, training-free fast samplers for diffusion models.
  [code] [demo]
  
  • State-of-the-art training-free fast sampler for text-to-image diffusion models (such as Stable Diffusion).
  • Widely-applied in various of text-to-image libraries and applications, such as DreamStudio, StableBoost, Stable-Diffusion-WebUI, Diffusers, official Code of Stable Diffusion v2, official Code of Stable Diffusion v1, online demo of Stable Diffusion v2, online demo of Stable Diffusion v1.5, Apple's ML-Stable-Diffusion.
  Corresponding papers:
  • DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps.
    Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu
    
  • DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
    Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu
    

* indicates co-first authors.

Publications

• ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
  Spotlight
  Zhengyi Wang*, Cheng Lu*, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu
  Conference on Neural Information Processing Systems (NeurIPS), 2023
  [arXiv] [project]
  
• DPM-Solver-v3: Improved Diffusion ODE Solvers with Empirical Model Statistics
  Kaiwen Zheng*, Cheng Lu*, Jianfei Chen, Jun Zhu
  Conference on Neural Information Processing Systems (NeurIPS), 2023
  [arXiv]
• On Calibrating Diffusion Probabilistic Models
  Tianyu Pang, Cheng Lu, Chao Du, Min Lin, Shuicheng YAN, Zhijie Deng
  Conference on Neural Information Processing Systems (NeurIPS), 2023
  [arXiv] [code]
  
• Gaussian Mixture Solvers for Diffusion Models
  Hanzhong Allan Guo, Cheng Lu, Fan Bao, Tianyu Pang, Shuicheng YAN, Chao Du, Chongxuan Li
  Conference on Neural Information Processing Systems (NeurIPS), 2023
  [arXiv]
• Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs
  Kaiwen Zheng*, Cheng Lu*, Jianfei Chen, Jun Zhu
  International Conference on Machine Learning (ICML), 2023
  [arXiv]
• Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning
  Cheng Lu*, Huayu Chen*, Jianfei Chen, Hang Su, Chongxuan Li, Jun Zhu
  International Conference on Machine Learning (ICML), 2023
  [arXiv] [code]
• Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
  Huayu Chen, Cheng Lu, Chengyang Ying, Hang Su, Jun Zhu
  International Conference on Learning Representations (ICLR), 2023
  [arXiv] [code]
• 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]
• 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
  [arXiv] [code]
• Implicit Normalizing Flows
  Spotlight (Accept rate~5.5%)
  Cheng Lu, Jianfei Chen, Chongxuan Li, Qiuhao Wang, Jun Zhu.
  International Conference on Learning Representations (ICLR), 2021
  [arXiv] [code]
• VFlow: More Expressive Generative Flows with Variational Data Augmentation
  Jianfei Chen, Cheng Lu, Biqi Chenli, Jun Zhu, Tian Tian
  International Conference on Machine Learning (ICML), 2020
  [arXiv] [code]

* indicates co-first authors.

Preprints

• DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
  Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, Jun Zhu
  [arXiv] [code]
  

Honors & Awards

• China National Scholarship, 2023.10
• ByteDance Scholarship , 2023.10
• LongHu Scholarship, 2023.09
• Huawei-Tsinghua Outstanding Service Award, 2021.06
• '84' Future Innovation Scholarship, 2020.12
• Top Ten Compus Singers Competition, Tsinghua University, 2019.10
• Outstanding Graduates, Department of Computer Science and Technology, Tsinghua University, 2019.06
• The Mathematical Contest in Modeling, Meritorious Winner, 2018
• Chinese Mathematical Olympiad (CMO), Silver Medal, 2014

Services

Reviewer for:

• NeurIPS 2021, 2022 (Top Reviewer), 2022 workshop
• ICML 2021, 2022, 2023
• ICLR 2021
• CVPR 2023
• ICCV 2023

Contributor for:

• huggingface/diffusers, the most widely-used library for diffusion models.

Invited Talks

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps, ByteDance, 2022.11 [slide]

Teaching

2021 Spring, Head 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

Skills

Python, PyTorch, JAX, Vue.js

Personal

I'm a bass singer in Chorus of Tsinghua University with a vocal range of C2-E4 (where C2 is also known as "low C"). I won the top ten compus singers competition of Tsinghua University in 2019 by singing a famous song Autumn Leaves. I love singing!