Applications
Zero-Shot Multi-Class Wafer Map Classification with Rule-Ordered Prompts for Large Multimodal Models
arXiv:2610.35080v1 Announce Type: new Abstract: Wafer-map defect classification often requires labeled data and retraining when production conditions change. We present a training-free six-class frame
arXiv:2610.35080v1 Announce Type: new Abstract: Wafer-map defect classification often requires labeled data and retraining when production conditions change. We present a training-free six-class framework that combines connected-component highlighting with morphology-, location-, and exclusion-aware prompts for a frozen large multimodal model. On Mixed-WM38 (6,866 maps), multi-region prompting achieves 92.9% macro and 93.8% overall accuracy. On WM811K (9,000 maps), it achieves 79.1% and 81.3%, respectively. Eight alternative rule orders achieve 90.1-91.9% overall accuracy, compared with 93.8% for the selected order.
Related
- PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection
- Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
- CART: Compatible Routing for Multimodal Continual Instruction Tuning
- CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
Source: arXiv cs.AI | 2026-10-27