This Project Grant award for $175,000 was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070). The project, titled "Formalizing Human-Interpretable Machine Learning," aims to develop approaches for training artificial intelligence systems, such as self-driving cars, to make their decision-making processes more transparent and interpretable to people. The research will involve pairing...
This $207,737 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund research to develop a new class of machine learning models called "Programmatic Foundation Models" that can efficiently analyze large-scale satellite, aerial, and ground imagery. The goal is to create interpretable, robust AI models that can understand global and local phenomena from images, providing insights...
This $680,733 federal Project Grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program aims to systematically explore the interpretability of deep learning models from representation, modeling, and prediction perspectives. The project, titled "COLLABORATIVE RESEARCH: TOWARDS EFFECTIVE INTERPRETATION OF DEEP LEARNING: PREDICTION, REPRESENTATION, MODELING AND UTILIZATION," seeks to develop a series of...
This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program (CFDA 47.070) provides $600,000 to The Pennsylvania State University from October 1, 2022 to September 30, 2025. The university will develop interpretable machine learning methods based on deep neural networks from a source coding perspective. Researchers will draw an analogy between explaining complex prediction models and transmitting signals with limited channel capacity. The...
This $400,000 Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) Federal Grant Program. The project aims to develop a systematic framework for visualizing, understanding, and rewriting the learned computations of multimodal generative AI models, in order to increase the accountable and safe use of these advanced AI systems and mitigate potential harms. The key research thrusts involve: 1) new...
This $400,000 project grant awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program supports research to develop a systematic framework for visualizing, understanding, and rewriting the learned computations of multimodal generative AI models. The key objectives are to: 1) create new methodologies to visualize the internal mechanisms and hierarchical structures of pre-trained multimodal generative models, 2) explore model...
The National Science Foundation (NSF) awarded a $600,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of South Carolina. The grant, with a period of performance from October 1, 2024 to September 30, 2027, focuses on enhancing security and mitigating harm in AI-generated vision language models. Key technical objectives include: 1) Developing a prompting framework for detecting harmful content provenance in AI-generated vision...
This $1,192,951 federal Project Grant award from the National Science Foundation's STEM Education program (CFDA 47.076) will fund a 3-year program to provide 15 high school teachers and 60 high school students, primarily from underrepresented and rural communities in Mississippi, with innovative learning experiences in machine learning and computer vision. The project aims to develop the AI/ML competencies of these students and prepare them for potential careers in artificial intelligence and...
The National Science Foundation (NSF) awarded a $329,183 Project Grant to the College of William & Mary under the Computer and Information Science and Engineering (CFDA 47.070) program. The grant, awarded on October 1, 2023, will fund the development of a framework and methodology to enable researchers and software engineers to better interpret the behavior of AI-powered developer tools that leverage neural language models for source code. The project aims to generate global and local...
This Project Grant from the National Science Foundation's $524,474 Computer and Information Science and Engineering program will support the development of artificial intelligence systems capable of understanding general real-world tasks and providing step-by-step visual and language guidance to solve complex problems. Over a three-year period from June 2022 to May 2025, researchers at the University of Minnesota will create a new dataset annotating diverse everyday tasks and solutions,...