AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

Runzhi Deng, Yundi Hu, Yiming Zhong, Zhao Wang, Xixi Liu, Hongsong Wang, Caifeng Shan, Fang Zhao

ECCV 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 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 online dual-stream verification to offline PVLA (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA MVTec (avg accuracy)accuracy: 88.98 -> 91.18Improved
add online dual-stream verification to offline PVLA (ablation)GLLS (Qwen2.5-VL-7B) · MMAD-QA MVTec (avg accuracy)accuracy: 77.04 -> 85.46Improved
add offline PVLA to online-only dual-stream (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA VisA (avg accuracy)accuracy: 79.96 -> 84.72Improved
add offline PVLA to base model (Qwen2.5-VL-7B) (ablation)Qwen2.5-VL-7B · MMAD-QA MVTec (avg accuracy)accuracy: 79.0 -> 77.0Hurt
add PVLA with Qwen3-VL-4B (ablation)Qwen3-VL-4B · MMAD-QA MVTec+VisA avgaccuracy: 71.8 -> 81.2Improved
PVLA versus text-guided only atlas (ablation)Qwen3-VL-8B · MMAD-QA MVTec+VisA avgaccuracy: 81.5 -> 84.4Improved
add Fine-Grained & Actions Stream to offline base (ablation)GLLS (Qwen3-VL-4B) · MMAD-QA MVTec+VisA avgaccuracy: 81.2 -> 82.7Improved
add Global & Logic stream on top of fine-grained stream (ablation)GLLS (Qwen2.5-VL-7B) · MMAD-QA MVTec+VisA avgaccuracy: 77.7 -> 81.5Improved
use MCTS search instead of sliding window (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA (Qwen3-VL-8B 1-shot search ablation) MVTecaccuracy: 89.4 -> 91.2Improved
use MCTS search instead of center crop (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA (Qwen3-VL-8B 1-shot search ablation) MVTecaccuracy: 84.2 -> 91.2Improved
raise evidence budget from 3 to 7 crops (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA (Qwen3-VL-8B 1-shot search ablation) MVTecaccuracy: 91.2 -> 90.1Hurt
raise evidence budget from 1 to 3 crops (ablation)GLLS (Qwen3-VL-8B) · MMAD-QA (Qwen3-VL-8B 1-shot search ablation) MVTecaccuracy: 88.5 -> 91.2Improved

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