Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·19h ago
AI Research
arXiv CS.AI·Jun 9·5 min read
Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection
TL;DR
Semiconductor lithography inspection faces challenges in accurately detecting small pattern defects like bridges and contamination. A two-stage vision-language framework, utilizing Qwen3-VL fine-tuned with LoRA, was developed to enhance defect detection and prediction refinement.
✦ Why It Matters
Engineers can leverage this framework to enhance defect detection accuracy in semiconductor lithography processes.
Key Takeaways
- Utilize a two-stage framework for defect detection.
- Incorporate Low-Rank Adaptation for model fine-tuning.
- Train a refinement module on prediction failures.
- Enhance accuracy by learning from initial errors.
How It Works
The framework consists of two stages: the first stage uses Qwen3-VL, a vision-language model, to make initial predictions about defects in lithography images. The second stage focuses on refining these predictions by analyzing errors from the first stage and adjusting the model based on corrected labels.
This feedback loop allows the model to learn from its mistakes, leading to improved accuracy in defect detection.