AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Any-to-Any Generation via Composable Diffusion

Zineng Tang, Ziyi Yang, Chenguang Zhu, Michael Zeng, Mohit Bansal

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Diffusion audio synthesis · 29 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 CoDi instead of Versatile Diffusion for text-to-image synthesisCoDi · COCO-caption validationFID: 11.10 -> 11.26Hurt
Use CoDi instead of Make-A-Video for text-to-video generationCoDi · MSR-VTTCLIPSIM: 0.3049 -> 0.2890Hurt
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testFD: 23.31 -> 22.90Improved
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testIS: 8.13 -> 8.77Improved
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testKL: 1.59 -> 1.40Improved
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testFAD: 1.96 -> 1.80Improved
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testOVL: 65.91 -> 66.87Improved
Use CoDi instead of AudioLDM-L-Full for audio generationCoDi · AudioCaps testREL: 65.97 -> 67.60Improved
Use CoDi instead of OFA for image captioningCoDi · COCO image captioningCIDEr: 154.9 -> 149.9Hurt
Use CoDi instead of AL-MixGen for audio captioningCoDi · AudioCaps audio captioningSPIDEr: 0.466 -> 0.480Improved
Use CoDi instead of AL-MixGen for audio captioningCoDi · AudioCaps audio captioningCIDEr: 0.755 -> 0.789Improved
Use CoDi instead of AL-MixGen for audio captioningCoDi · AudioCaps audio captioningSPICE: 0.177 -> 0.182Improved

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