AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Geometric Neural Diffusion Processes

Emile Mathieu, Vincent Dutordoir, Michael John Hutchinson, Valentin De Bortoli, Yee Whye Teh, Richard E Turner

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Diffusion theory and learned samplers · 2 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
Enforce translation invariance in the score networkGeomNDP · 1D stationary scalar fields, generalisationtest log-likelihoodImproved
Model outputs on the sphere rather than in Euclidean coordinatesGeomNDP · Cyclone extrapolationMSE (km): 769± 48 -> 496± 14Improved
Use non-white limiting kernels instead of white noise (ablation)GeomNDP · 1D synthetic regression datasetstest log-likelihoodHurt
Use the preconditioned score K∇ log p_t parameterisation (ablation)GeomNDP · 1D synthetic regression datasetstest log-likelihoodImproved
Perform multiple Langevin dynamics steps during conditional sampling (ablation)GeomNDP conditional sampler · SE conditional samplingKL divergenceImproved
Change the noising scheme for context values (ablation)GeomNDP conditional sampler · SE conditional samplingKL divergenceNo clear effect

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