AI Paper Atlas

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

Make it SING: Analyzing Semantic Invariants in Classifiers

Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded visual concept learning · 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 non-linear 3-layer MLP translator instead of linear (ablation)translator to CLIP space · Translator validationmean cosine similarity: 0.8946 -> 0.9049No clear effect
use non-linear 4-layer MLP translator instead of linear (ablation)translator to CLIP space · Translator validationvalidation MSE: 0.091355 -> 0.084346No clear effect
use cosine-only loss instead of MSE for translator (ablation)translator · Translator trainingcosine similarity and MSEHurt
use EVA02 instead of CLIP as target space (ablation)model-level IS/AS ratio · 5-model comparisonIS/AS ratio orderingNo clear effect
pretrain with self-supervised DINO ViT rather than supervised/weakly supervised CNNsclassifier · text-gradient null perturbation|AS| toward target: 12.04 -> 5.0 (ResNet50 vs DinoViT)Improved
compare ResNext101 with DinoViT on null leakageclassifier · ImageNet 1000 classesIS/AS ratioHurt

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