Yuchao Wu

SAG achieves a remarkable 80.36% Recall@5 on the challenging MuSiQue dataset, outperforming traditional methods by over 11 points in multi-hop reasoning tasks.

LEAP achieves a 7.6x speedup in toggle propagation prediction while maintaining near-perfect accuracy, revolutionizing power analysis in VLSI design.

Community structures can transform hypergraph partitioning, allowing for superior solutions that escape local optima.

SAG achieves 80.0% Recall@5 on the challenging MuSiQue benchmark, showcasing a breakthrough in multi-hop reasoning without the burden of global graph maintenance.

LLMs can now be rigorously tested on their ability to automatically generate assertions that catch bugs in real-world hardware designs, thanks to a new benchmark that includes buggy RTL variants.