Jiawei Liu

LLMs can now effectively analyze deep learning frameworks for bugs without the need for costly runtime execution, revealing 31 previously undetected issues in PyTorch.

A unified runtime boundary and time-aware execution can boost LLM agent accuracy by over 2% in long-horizon tasks, revealing a critical leverage point for enhancing agent stability.

Handoff validity is crucial for ensuring that design artifacts maintain integrity and context across complex EDA workflows.

FSS-Net achieves an impressive 96.46% Dice score for carotid artery segmentation, showcasing remarkable robustness against noise and low contrast.