AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Im-Promptu: In-Context Composition from Image Prompts

Bhishma Dedhia, Michael Chang, Jake Snell, Thomas L. Griffiths, Niraj Jha

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Abstract visual reasoning benchmarks · 0 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 object-centric slots with CET cross-attention instead of monolithic image vectorsIm-Promptu · 3D Shapes, BitMoji Faces, and CLEVr Objects composite tasksMSEImproved
Use object-centric slots with CET cross-attention instead of monolithic image vectorsIm-Promptu · 3D Shapes, BitMoji Faces, and CLEVr Objects composite tasksFIDImproved
Use the pixel-space rule D̂ = C + (B − A)Pixel baseline · 3D Shapes primitive extrapolationMSEHurt
Use the pixel-space rule D̂ = C + (B − A)Pixel baseline · BitMoji Faces primitive extrapolationMSEHurt
Use a monolithic vector representation rather than object-centric slotsIm-Promptu · 3D Shapes and BitMoji Faces primitive extrapolationMSEImproved
Use a monolithic vector representation rather than object-centric slotsIm-Promptu · CLEVr Objects primitive extrapolationFIDHurt
Use a monolithic vector representation rather than object-centric slotsIm-Promptu · 3D Shapes, BitMoji Faces, and CLEVr Objects composite tasksMSEHurt
Remove Slot Attention and represent images as discrete 4 × 4 patch latents (ablation)Im-Promptu Patch Learner · CLEVr ObjectsMSEImproved
Remove Slot Attention and represent images as discrete 4 × 4 patch latents (ablation)Im-Promptu Patch Learner · BitMoji FacesMSEHurt
Replace CET cross-attention with concatenated slot sequences and position embeddings (ablation)Im-Promptu Sequential Prompter · CLEVr Objectssample efficiencyHurt
Replace CET cross-attention with concatenated slot sequences and position embeddings (ablation)Im-Promptu Sequential Prompter · 3D Shapes, BitMoji Faces, and CLEVr ObjectsFIDNo clear effect
Add more context examplesPatch Learner and Sequential Prompter · Primitive task extrapolationMSEImproved

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