Search papers, labs, and topics across Lattice.
2
0
5
0
Domain-adapting LLMs for EDA requires explicit RAG scenario training to prevent performance degradation, and QA augmentation during corpus construction further boosts performance.
LLMs can rediscover known algorithms, but only after targeted unlearning and with the help of a generative verifier to avoid "thought collapse," revealing both the innovative potential and limitations of these models.
