Events for October 2025

How can AI, Natural Language Processing, machine learning, and computational approaches advance research and education in the humanities and interpretive social sciences? how can humanistic methodologies inform and challenge applications of AI? This working group aims to bring together graduate and advanced undergraduate students across the university who are interested in the intersections of computation, […]

This seminar will present findings from a large-scale evaluation of the American Heart Association's PREVENT model for predicting 10-year atherosclerotic cardiovascular disease (ASCVD) risk. Using electronic health records from over 550,000 adults in the Truveta data platform, we examined the model's fairness across demographic and social determinants of health (SDOH) subgroups and assessed whether adding […]

The informal discussion will take place from 11:15 am - 11:45 am in Gross Hall 103, followed by the colloquium talk at noon in French Sciences 2231 Q&A on research, career paths, and industry-academia transitions will be discussed with a Duke-connected industry Mathematician.

AI for Mathematics (AI4Math) is intellectually intriguing and crucial for AI-driven system design and verification. Much of the recent progress in this field has paralleled advances in natural language processing, especially by training large language models on curated mathematical text datasets. As a complementary yet less explored avenue, formal mathematical reasoning is grounded in formal […]

Tea/social begins at 1 pm followed by a talk and Q&A at 2 pm in Gross Hall 304B. Richard Allen will provide practical insights on math-bio-pharma pathways, discuss skills, roles and transitions into industry, and provide insight into current industry applications of mathematical biology.

Abstract: Synthetic data generation has become an increasingly powerful tool for overcoming the limitations of collecting and curating large real-world datasets for model training. Yet, fundamental questions remain about how synthetic data stores task-relevant information and how it can best be generated. In this talk, we bring together two complementary lines of work that aim […]

Modern edge devices, such as cameras, drones, and Internet-of-Things nodes, rely on deep learning to enable a wide range of intelligent applications. However, this deep learning inference is usually disaggregated: the model is stored on the cloud, while the inputs/outputs are obtained/required on the edge. To this end, we present a novel disaggregated computing architecture […]

How can AI, Natural Language Processing, machine learning, and computational approaches advance research and education in the humanities and interpretive social sciences? how can humanistic methodologies inform and challenge applications of AI? This working group aims to bring together graduate and advanced undergraduate students across the university who are interested in the intersections of computation, […]