Generative models· 2019
Generative Modeling by Estimating Gradients of the Data Distribution
On the reading lists
- #376 in the Top 500 (2026 edition)
- #24 in Generative models (2026 edition)
Why it matters
Established noise-conditional score networks and annealed Langevin sampling for high-quality generation.
Condensed from the expert lists' notes.
The record
- First released
- 2019 (from arXiv 1907.05600)
- Citations
- 6,113 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.394 · computed rank 376 · consensus 0.6, must-read 0, citations percentile 0.611 (2010s · generative-models), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.