3 papers - avg viability 7.7
A physics-informed Graph Neural Network framework that accelerates thermal warpage analysis for chiplet-based designs by over 200x compared to traditional FEM methods.
Deep learning model for actionable early-stage IR-drop estimation in VLSI design.
AnalogAgent automates analog circuit design using a multi-agent LLM system with self-evolving memory, significantly improving the performance of existing models.