Event
A model that understands the process, built for the domain.
- Wafer position and defect data compressed into a single vector — instant similar-case retrieval
- Pre-trained on Virtual Fab synthetic patterns — usable on day one without your data
- 3x RMSE improvement vs XGBoost · R² > 0.9 · 0.3 nm overlay prediction accuracy
Trusted investors and research partners.
ENSL Partners · Kakao Ventures · Newborn Ventures · TIPS Deep Tech.
Newsroom
Press and attention since year one
Starting from the hardest problems
A research team of process engineers and ML researchers, working together
Published papers.
Accepted at SPIE Advanced Lithography 2025·2026 and covered in industry press.
- Proactive yield maximization in photolithography via human-in-the-loop AI on an on-premise big data platformApr 10, 2026
- A hybrid machine learning framework for systematic optimization of overlay key positionsApr 10, 2026
- Domain knowledge-driven fusion machine learning for overlay prediction enhancementApr 08, 2026
Patent portfolio.
Patents covering semiconductor process, metrology, and RCA.
Tell us the challenge — we'll scope it with you.
You don't need detailed data ready. We reply within two business days with a tailored deployment scenario.