|
Ruofeng Yang
|
About me
I am a third-year PhD student in computer science in John Hopcroft Center, Shanghai Jiao Tong University under the supervision of Prof. Shuai Li since Sept. 2022.
My research interest lies in diffusion models and reinforcement learning. Currently, I am focusing on the theoretical analysis of diffusion models (including Sampling complexity, Statistical complexity, and Optimization Perspective). I am also interested in the combination of diffusion model and reinforcement learning algorithm, such as using the
reinforcement learning method to fine-tune the diffusion and use diffusion models in the offline2online RL method
Research Interests
- Diffusion Models
- Deep Learning Theory
- Reinforcement Learning and RLHF
News
- One paper about iteration complexity of flow-based method is submitted to COLT 2025
- Three papers about (1) multi-view diffusion models, (2) consistency models, and (3) Optimization for few-shot diffusion models are submitted to ICML 2025
- One paper about improved iteration complexity of VESDE (reverse SDE and PFODE) is accepted by AISTATS 2025!
- Two papers about iteration complexity of diffusion models (including a training-free method) and few-shot diffusion models are accepted by NeurIPS 2024!
- One paper is accepted by NeurIPS 2023!
- One paper is accepted by ICLR 2023!
- One paper is accepted by AAAI 2023 (Oral)!
Tutorials
- A simple introduction to diffusion model (Application)
- A brief survey on some interesting directions about diffusion models (Theory) (Coming Soon)
Publications
|
The Polynomial Iteration Complexity for Variance Exploding Diffusion Models: Elucidating SDE and ODE Samplers (AISTATS 2025)
Ruofeng Yang, Bo Jiang, Shuai Li |
|
Few-shot Diffusion Models Escape the Curse of Dimensionality (NeurIPS 2024)
Ruofeng Yang, Bo Jiang, Cheng Chen, Ruinan Jin, Baoxiang Wang, Shuai Li [NeruIPS 2024] |
|
Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models (NeurIPS 2024)
Ruofeng Yang, Zhijie Wang, Bo Jiang, Shuai Li [NeruIPS 2024] |
|
Understanding Representation Learnability of Nonlinear Self-Supervised Learning (AAAI 2023 Oral)
Ruofeng Yang, Xiangyuan Li, Bo Jiang, Shuai Li [Code] [AAAI 2023] |
|
Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition (ICLR 2023)
Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Shuai Li [ICLR 2023] |
|
Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback (NeurIPS 2023)
Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Xuezhou Zhang, Shuai Li [NeruIPS 2023] |
In Submission
|
Contrastive guidance and feedback: A Suitable way to improve 3D Consistency of Multi-view Diffusion Model
Ruofeng Yang, Le Wan, Yaqing Zhang, Shuai Li [Openreview] |
|
The Discretization Complexity Analysis of Consistency Models under Variance Exploding Forward Process
Ruofeng Yang, Bo Jiang, Cheng Chen, Shuai Li [Openreview] |
Professional Services
Conference Reviewer for
- International Conference on Machine Learning (ICML) 2025
- International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
- International Conference on Learning Representations (ICLR) 2025
- Neural Information Processing Systems (NeurIPS) 2024
- Autonomous Agents and Multiagent Systems (AAMAS) 2022
Rewards
- Shanghai Jiao Tong University Outstanding Graduates 2022
- Outstanding Winner of Mathematical Contest in Modeling (top 0.1%) 2020
- Tung Scholarship (Hong Kong's Tung Foundation) 2020
- Yang You Scholarship 2019, 2021