URAP

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Check back for status     Weekly Hours: 12 or more hours     Location: On Campus

Conformal prediction (CP) is a model-agnostic and distribution-free method for quantifying uncertainty in black-box machine learning (ML) models. CP can be used to construct prediction sets/intervals that covers the true labels with a pre-determined probability as long as the training and testing data are exchangeable...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Check back for status     Weekly Hours: 12 or more hours     Location: On Campus

Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions to assist in diagnostic and treatment tasks. However, VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. This challenge is particularly pronounced in the medical domain, where we...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Check back for status     Weekly Hours: 12 or more hours     Location: On Campus

Large language models (LLMs) pre-trained on large corpora of text have demonstrated incredible capabilities across with zero- or few-shot performance in new tasks that differ from their pre-training objectives. In this projects, we will study the zero-shot performance of LLMs for various clinical tasks using real...

Ahmed Alaa - Professor, Electrical Engineering and Computer Science

Status: Full- no new appr needed     Weekly Hours: 12 or more hours     Location: On Campus

Institutional constraints and concerns over patient privacy impedes sharing of clinical data among researchers. High-fidelity synthetic data that mimics the real data distribution without revealing real data for individual patients can help empower and democratize research applying machine learning models to clinical problems. In this project, we will use...