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.
- Publications
Yang Song*, Sahaj Garg*, Jiaxin Shi, and Stefano Ermon. In...
- Blog
46 min read · May 5, 2021. 2021. Sliced Score Matching: A...
- Recruitment
The personal website of Yang Song. ... Recruitment. December...
- cv
The personal website of Yang Song. ... Organizer: NeurIPS...
- Publications
Cited by. Year. 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. 3325. 2021. Generative modeling by estimating gradients of the data distribution.
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.
Yang Song is an associate professor of finance at the University of Washington and an editor of Management Science. He studies topics such as mutual funds, active management, information asymmetry, and liquidity premium.
Yang Song is a researcher and engineer working on generative models and AI safety. He has a PhD from Stanford and has published papers on Bayesian inference, kernel methods, and direct loss minimization.
- OpenAI
