Reproduce “Streaming Virtual Metrology via Lightweight Adaptation under Temporal Distribution Shifts” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Doyun Choi, Cheonwoo Lee, Younghyun Han, Kiwook Han, Jinkook Park, Sungyoon Ryu, Younghoon Sohn, Jaemin Yoo
GRAPE predicts optical critical dimension from etch data under changing conditions. It freezes a Ridge-regression predictor and adds feature-level and environment-level corrections, updated after each wafer’s measurement arrives. On blind tests using the latest 60% of two anonymized datasets, it ranked first across six dataset-metric comparisons, with average rank 1.00; results are limited to optical critical dimension in etch processes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.