CORTEXA
← Browse
arxivcs.CV2026-07-04

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

Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal references and structured specifications in the inference context. It combines a Global & Logic Stream, where SAM 3 extracts partially checkable visual facts, with a Fine-Grained & Actions Stream, where MCTS selects local evidence crops under a fixed budget. Experiments on MMAD-QA and additional anomaly detection datasets show consistent gains over matched and general-purpose baselines, while keeping the final diagnostic decision traceable to explicit visual evidence throughout the inspection trace.

View free PDFSource page

Related papers

arxivcs.CV2026-07-01

Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap

Bingchen Huang, Zhiling Wang, Yifu Chen, Yuanchao Du

Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new imagery, each at the cost of a tool protocol, brittle code, or an expensive training pipeline. A fourt…

View free PDFSource page
arxivcs.CVcs.AI2026-06-30

Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning

Kaitao Chen, Weiqian Zhao, Jiamin Wu, Qihao Zheng, Shangquan Sun, Chunfeng Song, et al.

Vision-language models (VLMs) combining reinforcement learning (RL) ignite remarkable progress in multimodal reasoning, yet still struggle with medical images, which typically exhibit extremely sparse visual evidence to inform clinical decision-making. We recognize that pruning v…

View free PDFSource page
arxivcs.CV2026-07-03

OmniDS: Dual-Stream Context Fusion for Omnidirectional Depth from Fisheye Cameras

Chaesong Park, Jihyeon Hwang, Muyeol Sung, Jongwoo Lim

Omnidirectional depth estimation from multi-fisheye camera rigs is complicated by visibility conflicts: wide baselines cause different cameras to observe different portions, or even different faces, of the same object, so aggregating their features into a unified equirectangular…

View free PDFSource page
arxivcs.CV2026-07-16

SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection

Huong Ninh, Chien Thai, Mai Xuan Trang, Vu-Minh Le, Thanh Ha Le, Long Tran

Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, most are primarily designed for single-class settings and of…

View free PDFSource page
arxivcs.CV2026-07-03

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection

Wen Dong, Zhao Wang, Shuangqing Zhang, Kai Sun, Ben Li, Guo-Sen Xie, et al.

Multimodal Large Language Models (MLLMs) excel in diverse vision tasks, but full-parameter retraining is computationally expensive as real-world knowledge evolves. Existing continual learning methods often suffer from semantic entanglement in parameter spaces across tasks, impedi…

View free PDFSource page
arxivcs.CV2026-06-30

Domain Adaptive Object Detection via Dual-Stream Bilevel-Cycle Optimization

Yannan Chen, Wei Wang, Wenqiang Wang, Ruoyu Chen, Jiancheng Wang, Mingbo Yang, et al.

Cycle self-training (CST) breaks the shared classifier assumption of the standard self-training framework, which is effective for unsupervised domain adaptation and exploits unlabeled target data by training with target pseudo-labels. CST introduces a target classifier and employ…

View free PDFSource page