Tag
PICasso is an AI-enabled framework for autonomous optimization of silicon photonic devices from natural-language specifications, demonstrating significant improvements in design satisfaction and loss reduction through LLMs and simulation feedback.
ARES proposes a framework for automatically constructing rubric-based RL data from pretraining documents, generating question-answer pairs and weighted rubrics to enable instance-level reward supervision for open-ended LLM responses, outperforming existing methods on multi-dimensional open-ended tasks.