AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data

Dahyun Chung, Donghyun Shin, Yujin Sung, Seunggi Moon, Jinwoo Jeon, Byung-Jun Lee

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: CLIP training recipes and data curation · 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 embedding perturbation (Gaussian noise) (ablation)uCLIP · MSCOCO (translated)I2T R@10: 32.6 -> 53.2Improved
add embedding perturbation (Gaussian noise) (ablation)uCLIP · MSCOCO (translated)T2I R@10: 48.6 -> 53.3Improved
add pseudo-pair alignment loss Lpseudo (ablation)uCLIP · MSCOCO (translated)I2T R@10: 47.7 -> 53.2Improved
add pseudo-pair alignment loss Lpseudo (ablation)uCLIP · MSCOCO (translated)T2I R@10: 52.4 -> 53.3No clear effect
add text alignment loss Ltext (ablation)uCLIP · MSCOCO (translated)I2T R@10: 51.2 -> 53.2Improved
add intra-alignment loss Lintra (ablation)uCLIP · MSCOCO (translated)I2T R@10: 52.5 -> 53.2No clear effect
use MPNet-base instead of multilingual E5-base text encoder (ablation)uCLIP · MSCOCO (translated)I2T R@10: 32.2 -> 53.2Improved
use MPNet-base instead of MiniLM-L12 text encoder (ablation)uCLIP · MSCOCO (translated)I2T R@10: 48.9 -> 53.2Improved
apply uCLIP projector to SigLIP2 image encoder (ablation)uCLIP · MSCOCO (translated)I2T R@10: 44.7 -> 54.6Improved
uCLIP vs M-CLIP on text-to-image retrievaluCLIP · XM3600 (5 langs)T2I R@10: 77.5 -> 70.4Hurt
uCLIP vs M-CLIP on zero-shot classificationuCLIP · STL-10 (5 langs)F1: 94.3 -> 91.1Hurt
skip translation and use uCLIP instead of translate-then-CLIPuCLIP · inference latencyms/sample: 480.13 -> 23.56Improved

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