Search results
Yang Song is a leading expert in generative models, especially score-based diffusion models. He works on improving generative models for diverse modalities, applications, and scientific discovery.
- Blog
Sliced Score Matching: A Scalable Approach to Density and...
- Publications
Yang Song*, Sahaj Garg*, Jiaxin Shi, and Stefano Ermon. In...
- Repositories
repositories. Most of my research has code open-sourced at...
- cv
The personal website of Yang Song. ... Organizer: NeurIPS...
- Blog
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.
Sep 4, 2018 · Sliced Score Matching: A Scalable Approach to Density and Score Estimation. An overview for our UAI 2019 paper on Sliced Score Matching. We show how to use random projections to scale up score matching—a classic method to learn unnormalized probabilisic models—to high-dimensional data.
Pixeldefend: Leveraging generative models to understand and defend against adversarial examples. Y Song, T Kim, S Nowozin, S Ermon, N Kushman. International Conference on Learning Representations. , 2018. 898. 2018. Diffusion models: A comprehensive survey of methods and applications.
Articles 1–20. Google Research - Machine Intelligence - Cited by 16,139 - Information Retrieval - Machine Learning - Recommender Systems - Deep Learning - Search Engines.
Yang Song. J Huang, V Rathod, C Sun, M Zhu, A Korattikara, A Fathi, I Fischer, ... Proceedings of the IEEE conference on computer vision and pattern …. Proceedings of the IEEE/CVF conference on computer vision and pattern …. G Van Horn, O Mac Aodha, Y Song, Y Cui, C Sun, A Shepard, H Adam, ...
1. 2022. Development and validation of a deep-learning model to predict 10-year atherosclerotic cardiovascular disease risk from retinal images using the UK Biobank and EyePACS 10K datasets. E...