Survey paper defines "circuit foundation models" for VLSI design

A new survey paper introduces the concept of "circuit foundation models" (CFMs), which are AI models designed for VLSI circuit design and electronic design automation (EDA). These models are pre-trained on large amounts of unlabeled circuit data to learn intrinsic properties, and then fine-tuned for specific tasks like design evaluation or functional verification. The paper categorizes existing CFMs into encoder-based methods for predictive tasks and decoder-based methods using LLMs for generative tasks, covering over 130 works published primarily since 2022. AI

IMPACT Introduces a new paradigm for AI in hardware design, potentially accelerating VLSI development and EDA.

RANK_REASON The cluster contains an academic survey paper introducing a new concept in AI for VLSI circuit design. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Artificial intelligence
• Circuit Foundation Models
• Eda
• Large language models
• Zhiyao Xie

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →