🏢 University of Massachusetts Amherst

SPRY: A memory-efficient federated learning algorithm for finetuning LLMs on resource-constrained devices, achieving high accuracy and speed.

One-shot label-only attack (OSLO) achieves high membership inference accuracy with only one query, surpassing existing methods by a large margin.

Learn graph representations efficiently by identifying the minimal data needed to uniquely define a graph’s structure, achieving robust performance with fewer resources.

Accelerate Bayesian inference in linear mixed-effects models by efficiently marginalizing random effects using fast linear algebra, enabling faster and more accurate posterior estimations.

GP-TopK: A novel contextual bandit algorithm uses Gaussian processes with a Kendall kernel for efficient & accurate top-k recommendations, even with limited feedback.

This paper presents novel, scalable algorithms for fair and efficient constrained resource allocation under uncertainty using robust and CVaR optimization.

ZoDiac: a novel image watermarking framework leveraging pre-trained stable diffusion models for robust, invisible watermarks resistant to state-of-the-art attacks.