Guanpeng Li

PaRID combines parallel-aware code transformation with LLM-tuned performance modeling, guided by eight generalizable findings from an offline characterization study, to enable fast soft error detection in parallel applications.

V-Mem achieves a groundbreaking LLM-judge score of 0.82 in multimodal memory retrieval, outperforming existing systems by leveraging modality-specific routing and LLM-generated anchors.

Error propagation in LLMs reveals critical vulnerabilities that could undermine their reliability in high-stakes applications.