AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Natural Image Pretraining Improves Abstract Reasoning

Xiaoman Ding, Keya Hu, Katelyn Gan, Victor Yin, Kaiming He

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 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
initialize encoder from ImageNet MAE instead of random init (ablation)Nat-ARC (VARC pipeline) · ARC-1 eval (base, large, huge)pass@2Improved
add ImageNet MAE pretraining during offline training (ablation)Nat-ARC · ARC-1 train offline evalconvergence speed and accuracyImproved
scale encoder from base to large to huge without pretraining (ablation)Nat-ARC from scratch · ARC-1 evalpass@2Mixed
scale encoder size with ImageNet pretraining (ablation)Nat-ARC · ARC-1 evalpass@2Improved
ensemble two non-pretrained checkpoints vs single (ablation)Nat-ARC scratch · ARC-1 evalpass@2Improved
include ImageNet-pretrained checkpoints in ensemble vs scratch-only (ablation)Nat-ARC ensemble · ARC-1 evalpass@2Improved
two-ImageNet vs mixed scratch-ImageNet ensemble (ablation)Nat-ARC ensemble · ARC-1 evalpass@2No clear effect
add ARC-style grid MAE pretraining (ablation)Nat-ARC · ARC-1 evalpass@2Improved
scale ARC-style pretrained model from large to huge (ablation)Nat-ARC ARC-style pretrain · ARC-1 evalpass@2No clear effect
pool predictions from no-pretrain, ImageNet and ARC-style regimes (ablation)Nat-ARC ensemble · ARC-1 evalpass@2: 63.4 -> 70.2Improved
enable RoPE with ImageNet MAE init (base scale) (ablation)Nat-ARC base · ARC-1 offline evalaccuracyNo 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