AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Concrete Score Matching: Generalized Score Matching for Discrete Data

Chenlin Meng, Kristy Choi, Jiaming Song, Stefano Ermon

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Posterior sampling with diffusion guidance · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use CSM instead of Ratio MatchingMADE · NLTCSlog-likelihood: -6.15 -> -6.13Improved
Use CSM instead of Ratio MatchingMADE · Plantslog-likelihood: -15.44 -> -14.02Improved
Use CSM instead of Ratio MatchingMADE · Jesterlog-likelihood: -56.49 -> -54.91Improved
Use CSM instead of Ratio MatchingMADE · Amazon Diaperlog-likelihood: -10.69 -> -11.13Hurt
Use CSM instead of Ratio MatchingMADE · Amazon Feedinglog-likelihood: -12.09 -> -12.65Hurt
Use CSM instead of Discrete MarginalizationMADE · Amazon Giftslog-likelihood: -4.28 -> -4.22Improved
Use CSM instead of Ratio MatchingMADE · Amazon Medialog-likelihood: -10.22 -> -10.30Hurt
Use CSM instead of Ratio MatchingMADE · Amazon Toyslog-likelihood: -9.83 -> -9.30Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy