🏢 Ohio State University

This study introduces a novel Bayesian functional mixed model that reliably recovers the size and shape of fixed effects from noisy functional data with phase variability, outperforming current state-…

This paper presents novel, privacy-preserving algorithms achieving near-optimal rates for solving stochastic saddle point problems and variational inequalities in non-Euclidean geometries.

pcaGAN boosts posterior-sampling cGANs by using principal component regularization, achieving faster, more accurate results in various imaging tasks.

HippoRAG, a neurobiologically inspired framework, dramatically improves LLM long-term memory and multi-hop question answering by synergistically orchestrating LLMs, knowledge graphs, and the Personali…

Fine-tuning pre-trained models often degrades performance on unseen classes. This work reveals that the problem stems from logit scale discrepancies, not feature loss, and shows that post-processing c…

FEDNE: a novel approach enabling collaborative dimensionality reduction of distributed data in federated learning without data sharing, achieved via surrogate loss functions and data augmentation.

AI models retraining with model-annotated data incorporating human strategic responses can lead to unexpected outcomes, potentially reducing the proportion of agents with positive labels over time, wh…