AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Trans-Dimensional Generative Modeling via Jump Diffusion Models

Andrew Campbell, William Harvey, Christian Dietrich Weilbach, Valentin De Bortoli, Tom Rainforth, Arnaud Doucet

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 1 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
Jointly generate molecular state values and dimension during conditional diffusion guidance rather than fixing dimension firstQM9 molecule generation · QM9 conditional molecule generationDimension Error: 0.511 ± 0.19 -> 0.134 ± 0.076Improved
Jointly generate molecular state values and dimension during conditional diffusion guidance rather than fixing dimension firstQM9 molecule generation · QM9 conditional molecule generation% Molecule Stable: 31.3 ± 6.3 -> 59.1 ± 11Improved
Jointly generate molecular state values and dimension during conditional diffusion guidance rather than fixing dimension firstQM9 molecule generation · QM9 conditional molecule generation% Valid: 65.2 ± 10.3 -> 74.8 ± 9.3Improved
Jointly generate video frames and video length during guided planning rather than sampling a fixed lengthRoboDesk video planning · RoboDesk planning, StationaryDimension prediction MAE: 14.16 ± 1.41 -> 9.70 ± 0.99Improved
Jointly generate video frames and video length during guided planning rather than sampling a fixed lengthRoboDesk video planning · RoboDesk planning, Slide DoorDimension prediction MAE: 13.39 ± 1.34 -> 11.47 ± 0.74Improved
Jointly generate video frames and video length during guided planning rather than sampling a fixed lengthRoboDesk video planning · RoboDesk planning, Push ObjectDimension prediction MAE: 17.06 ± 1.47 -> 15.43 ± 0.90Improved
Use a constant forward deletion rate throughout generation (ablation)TDDM · QM9 unconditional% Molecule Stable: 87.2 -> 79.1Hurt
Use a constant forward deletion rate throughout generation (ablation)TDDM · QM9 conditional molecule generationDimension Error: 0.134 ± 0.076 -> 0.226 ± 0.17Hurt
Set the forward rate to zero for t<0.9T instead of t<0.1T (ablation)TDDM · QM9 conditional molecule generationDimension Error: 0.134 ± 0.076 -> 0.390 ± 0.38Hurt
Set the forward rate to zero for t<0.9T instead of t<0.1T (ablation)TDDM · QM9 unconditional% Molecule Stable: 87.2 -> 82.6Hurt
Predict the backward jump rate directly instead of deriving it from the component-count prediction (ablation)TDDM · QM9 unconditional% Molecule Stable: 87.2 -> 66.9Hurt
Predict the backward jump rate directly instead of deriving it from the component-count prediction (ablation)TDDM · QM9 conditional molecule generationDimension Error: 0.134 ± 0.076 -> 0.219 ± 0.12Hurt

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