[Gauss Labs @ SPIE AL 2025] Introducing our new paper on Virtual Metrology

[Paper 13426-84] High-performing Virtual Metrology with Group-Wise Feature Transformation and Advanced Data Aggregation Techniques

Gauss Labs published three papers at SPIE Advanced Lithography + Patterning 2025, a global conference for solving challenges in optical and EUV lithography, patterning technologies, metrology, and process integration for semiconductor manufacturing and adjacent applications.

In this video, Tau, our Applied Scientist, introduces our new paper on virtual metrology, "A Grid Mapping-based U-Net Algorithm for Photolithography Overlay Virtual Metrology". We proposed our new data engineering technique for virtual metrology and experimental results with real data. We proposed an effective method to process the big data from diverse sources and to enhance the predictive performance in complex manufacturing datasets.

To learn more, please visit: www.spiedigitallibrary.org/conference-proceedings-…

If you are interested in finding out more about the other two papers we published, check out:

[Paper 13426-101] SiliconBASE: Multi-task Baseline Model for Semiconductor Metrology and Inspection Applications (   • [Gauss Labs @ SPIE AL 2025] Introducing ou...  )
[PAPER 13426-17] A Grid Mapping-based U-Net Algorithm for Photolithography Overlay Virtual Metrology (   • [Gauss Labs @ SPIE AL 2025] Introducing ou...  )

For more information, please visit our website at gausslabs.ai!