AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

WeightCLIP: Aligning Datasets and Models for Weight Space Learning

Aron Asefaw, Konstantinos Tzevelekakis, Damian Falk, Léo Meynent, Damian Borth

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 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
add dataset-model alignment loss (ablation)WeightCLIP · In-distribution retrievalR@1 (%): 10 -> 95Improved
add dataset-model alignment loss (ablation)WeightCLIP · Linear-mapper generation Ep. 0 (first three OOD datasets)accuracy (%): 14.5 -> 26.6Improved
align both model and dataset encoders instead of dataset encoder only (ablation)WeightCLIP · Linear-mapper generation Ep. 0accuracy (%): 23.9 -> 26.6Improved
align dataset encoder only (D2NWG) instead of no alignment (ablation)WeightCLIP · Linear-mapper generation Ep. 0accuracy (%): 14.5 -> 23.9Improved
replace nearest-neighbor selection with linear mapperWeightCLIP · ResNet18 OOD Ep. 0accuracy (%): 26.3 -> 30.9Improved
use memory-bank mapper instead of linear mapperWeightCLIP · ResNet18 OOD Ep. 0accuracy (%): 30.9 -> 31.5Improved
use latent-space refinement instead of weight-space fine-tuninggenerated ResNet18 models · 6 OOD datasets averageaccuracy (%): 38.8 -> 44.9Improved
add hyperspherical shell constraint to latent refinement (ablation)WeightCLIP · refinement averageaccuracy (%): 42.4 -> 44.9Improved
add hyperspherical shell constraint to unaligned latent refinement (ablation)WeightCLIP w/o align. · refinement averageaccuracy (%): 37.2 -> 40.7Improved
add alignment to shell-constrained latent refinement (ablation)WeightCLIP · refinement averageaccuracy (%): 40.7 -> 44.9Improved
increase dataset prompt size from 1 to 32 images (ablation)WeightCLIP · OOD generation after 1 epochaccuracy (%): 61.1 -> 64.3No clear effect
increase dataset prompt size from 32 to 100 images (ablation)WeightCLIP · OOD generation after 1 epochaccuracy (%): 64.3 -> 63.8No 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