Talk Abstract

In a time where models with parameter counts in the billions that are trained on billions of samples (b^2) are becoming commonplace, many questions arise on how we should use these powerful models in downstream applications. In this talk, I will highlight three topics that are becoming increasingly important in this new age. First, I will explore how we can use large generative models to build fairer datasets that we can use to help ensure that models are less biased in their predictions, while also avoiding potential biases being introduced by using generated data. Second, I will delve into my lab’s recent work that aims to connect two disparate research directions that address label noise. By reformulating these methods in a new framework, we find that we can boost performance in even very noisy datasets that often arise in datasets in the wild. Third, to defend against some of the negative effect of large language models being used for misinformation, we will explore methods that aim to localize machine generated text in documents that is created via a mix of human and machine text, even in cases where current methods fail such as majority human-written documents.

Biography

Bryan Plummer is an Assistant Professor in the Department of Computer Science at Boston University and is a core faculty member of the Artificial Intelligence Research (AIR) Initiative in the Rafik B. Hariri Institute for Computing and Computational Science & Engineering. His research interests include multimodal reasoning, detecting manipulated and machine generated media, efficient neural networks, fair and explainable AI, and disentangled and structured representation learning. He has been an area chair for machine learning venues such as CVPR, ECCV, NeurIPS, and an action editor for ACL ARR. He was named a 2023 Hariri Institute Junior Faculty Fellow and has been published in top-venues in machine learning, computer vision, and natural language processing. Bryan received his PhD from the University of Illinois at Urbana-Champaign in 2018 advised by Svetlana Lazebnik where he received a 3M Foundation Fellowship and was an NSF GRFP honorable mention. He was a Postdoc and a Research Assistant Professor at Boston University before taking his current tenure-track position in 2020