🏢 University of Illinois Urbana-Champaign

FedGTST significantly improves federated transfer learning by tuning cross-client statistics, achieving superior global transferability with minimal communication overhead.

DISCO: a novel discrete-state continuous-time diffusion model for flexible and efficient graph generation, outperforming state-of-the-art methods.

LLMs struggle to reliably generate valid data science code due to a lack of true understanding of numerical constraints in APIs, despite seemingly mastering common patterns through extensive training.

A novel graph-theoretic framework bridges OOD detection & generalization, offering theoretical error bounds and competitive empirical performance.

2D-OOB: a novel framework for jointly attributing data values to individual features, enabling fine-grained outlier detection and improved model performance.