Yan Chen

This paper identifies and characterizes 'guidance injection,' a stealthy attack vector that embeds adversarial operational narratives into autonomous coding agents' bootstrap guidance, demonstrating high success rates and evasion capabilities.

The paper introduces CardioLens, a rigorous evaluation testbed for multi-sequence Cardiac MRI, which reveals that current Multimodal Large Language Models (MLLMs) exhibit a significant 'clinical reality gap' and perform poorly when simulating real-world cardiac interpretation workflows.

The paper introduces PassNet, a large-scale ecosystem for generating compiler passes using LLMs, demonstrating that LLMs can significantly accelerate graph compilation for long-tail workloads, suggesting that consistency is the primary bottleneck.