Researchers have developed a novel framework for calibrating Bosch etching simulators using a limited number of real-world measurements. This few-shot approach decouples simulator parameters from direct process variables, enabling the inference of recipe-specific simulator parameters. The system combines local exploration, LLM-guided candidate generation, and XGBoost-based surrogate screening to efficiently search the parameter space, achieving accurate predictions for etch depth and sidewall angle on held-out conditions. AI
IMPACT This framework could improve the accuracy and efficiency of semiconductor manufacturing processes by enabling better simulation calibration.
RANK_REASON The cluster contains a research paper detailing a new technical framework and experimental results. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
