Shiyu Zhang

AlignGAE shatters the homophily bias barrier, achieving up to 18.7% better performance on heterophilous graphs compared to existing methods.

Get 5x faster language-guided segmentation without sacrificing accuracy by training models to distill verbose reasoning chains into concise summaries.

LLMs still fail to demonstrate expert-level proficiency, achieving only ~66% success on a new benchmark of real-world professional tasks spanning finance, healthcare, and law.