AI Paper Atlas

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

PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures

Yuheng Shao, Lizhang Wang, Changhao Li, Peixian Chen, Qinyuan Liu

AAAI 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 6 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
replace single static prompt with static ensemble (ablation)PromptMoE · MVTec ADI-AUC: 91.7 -> 92.2Improved
replace static ensemble with single-layer VGMoP (ablation)PromptMoE · MVTec ADI-AUC: 92.2 -> 93.1Improved
replace static ensemble with single-layer VGMoP (ablation)PromptMoE · VisAI-AUC: 83.3 -> 84.1Improved
add multi-layer prompts and auxiliary losses to VGMoP (ablation)PromptMoE · VisAI-AUC: 84.1 -> 85.0Improved
add multi-layer prompts and auxiliary losses to VGMoP (ablation)PromptMoE · MVTec ADPRO: 83.3 -> 83.2No clear effect
add load-balancing loss (alpha 0 -> 0.01) (ablation)PromptMoE · MVTec ADI-AUC: 92.1 -> 93.8Improved
increase load-balancing weight from 0.01 to 0.1 (ablation)PromptMoE · MVTec ADI-AUC: 93.8 -> 92.9Hurt
add expert decoupling loss (ablation)PromptMoE · MVTec ADI-AUROCImproved

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