arXiv:2606.08908v1 Announce Type: cross Abstract: Semiconductor lithography inspection requires reliable detection of small pattern defects such as bridge, burr, pinch, and contamination. In this study, we propose a two-stage vision-language framework that combines initial defect detection with prediction refinement. In the first stage, Qwen3-VL is fine-tuned with LoRA as a vision-language adapter to predict defect counts, defect categories, and normalized bounding boxes from lithography images. However, direct fine-tuning may still produce common test-time errors, including false positives, m
The increasing complexity and miniaturization in semiconductor manufacturing necessitate advanced AI for defect detection to maintain yield and quality.
Improved defect detection in lithography directly impacts the efficiency and cost-effectiveness of semiconductor production, a critical component of the global tech stack.
Vision-language models, specifically Qwen3-VL, are being adapted and refined to enhance precision in identifying and categorizing minute semiconductor defects, moving beyond traditional computer vision approaches.
- · Semiconductor manufacturers
- · AI model developers
- · Lithography equipment providers
- · Electronics industry
- · Companies reliant on older, less efficient defect detection methods
- · Manufacturers with high defect rates
Higher yields and reduced waste in semiconductor fabrication will result from more accurate defect detection.
The cost of leading-edge semiconductors could decrease, accelerating innovation in AI, high-performance computing, and other reliant sectors.
Nations and companies with advanced AI-driven lithography will gain a significant competitive advantage in the global technology race, further concentrating chip manufacturing expertise.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI