Search results
Yang Song is a leading expert in generative models, especially score-based diffusion models. He works on improving generative models for data understanding, generation and reasoning across diverse modalities.
- Blog
The personal website of Yang Song. Yang Song Toggle...
- Repositories
repositories. Most of my research has code open-sourced at...
- Publications
Yang Song*, Sahaj Garg*, Jiaxin Shi, and Stefano Ermon. In...
- cv
Organizer: NeurIPS 2022 Workshop on Score-Based Methods....
- Blog
Score-Based Generative Modeling through Stochastic Differential Equations. Y Song, J Sohl-Dickstein, DP Kingma, A Kumar, S Ermon, B Poole. International Conference on Learning Representations. , 2021. 4601. 2021. Generative modeling by estimating gradients of the data distribution. Y Song, S Ermon. Advances in Neural Information Processing ...
Yang Song, Stanford UniversityGenerating data with complex patterns, such as images, audio, and molecular structures, requires fitting very flexible statisti...
- 92 min
- 78.2K
- MITCBMM
Learn how to generate samples from data distributions by estimating their score functions, which are gradients of log probability density functions. Score-based models have advantages over existing generative models, such as GANs, in terms of sample quality, flexibility, and inverse problem solving.
To kick off our Youth Speaker Series, we are honored to have Dr. Yang Song joining us for a discussion around diffusion models for generative AI and their growing impact in pushing the...
- 81 min
- 5.6K
- Youth AI Lab
Yang Song is a Ph.D. candidate in Computer Science at Stanford University, advised by Stefano Ermon. He has interned at Google, Uber, and Microsoft Research, and won several awards and fellowships in AI/ML.
Monday, March 28, 2022, 3:30 pmAbstractGenerating data with complex patterns, such as images, audio, and molecular structures, requires fitting very flexible...
- 57 min
- 3.2K
- Paul G. Allen School
