Eight early-career professors win NSF development awards

Researchers studying artificial intelligence training data, better predictions of extreme weather events and treatment of swelling linked to breast cancer are among the eight Cornell assistant professors who recently received National Science Foundation Faculty Early Career Development Awards.

Each will receive a minimum of $400,000 over five years from the program, which supports early-career faculty "who have the potential to serve as academic role models in research and education and to lead advances in the mission of their department or organization," according to the NSF. Each funded project must include an educational component.

Recent recipients from Cornell:

Abe Davis, Department of Computer Science (Cornell Bowers CIS), will use his award to develop mobile AI applications to help regular users capture information that aid decision-making in various fields. Much of the recent progress in AI has come from training on large publicly available datasets, but many real-world problems require learning from specific data that must be captured manually. This project will combine novel interaction design with adaptive tracking and registration strategies to build systems that help users capture precise field data. These systems will include tools that make it easy for experts to define target distributions of important information, which can then be used to guide the collection of photos, audio recordings, and other types of field data by non-expert users. The project will also integrate research with education and outreach to high school students and teachers from underrepresented communities.

Kevin Ellis, Department of Computer Science, (Cornell Bowers CIS), will use his award to develop new AI methods for learning symbolic knowledge - information that can be passed from one person to another, such as rules of a game or a recipe - represented as computer code, combining ideas from statistics, large language models and program synthesis. The scientific impact of this research will be AI systems that learn more abstract forms of knowledge, from fewer examples, and which are more understandable to humans because the systems will describe what they know in languages we can understand. This research will involve student researchers, especially those from underrepresented groups, and will inform new graduate and undergraduate classes, including Cornell's new 150-student undergraduate AI class.

Nikhil Garg, from the Jacobs Institute at Cornell Tech, and the School of Operations Research and Information Engineering (Cornell Engineering), will use his award to improve public interest decision-making. He will develop statistical methods to engineer more efficient, transparent public interest systems that account for missing information and heterogeneous behavior. The research will contribute methods for general Bayesian inference, optimization, machine learning and data-driven decision-making, applied to auditing and engineering systems in public interest settings such as education, health and government broadly. This knowledge will help allocate resources where they are most needed. The project will also educate data scientists and researchers for the public interest by providing continuing education and publicly available resources for municipal technology workers and open data hobbyists.

Andrew Hein, computational biology (College of Agriculture and Life Sciences), will use his award in an attempt to answer a question that has eluded scientists for decades: How and why do biological collectives - groups of interacting biological individuals, from cells that make up biological tissue to social groups of higher animals - coordinate seamlessly in some situations, yet exhibit catastrophic dysfunction in others? Hein's project will seek to answer this question by combining elegant experiments with mathematical and computational models that seek to identify the factors contributing to this variation. This research has the potential to help solve problems ranging from the control of distributed robots and sensor networks to health interventions aimed at promoting wound healing. Education and broader impact activities will focus on strengthening mathematical and AI literacy among life-science students at undergraduate and graduate levels, and sharing scientific knowledge beyond academia.

Peter Hitchcock, Department of Earth and Atmospheric Sciences (College of Agriculture and Life Sciences), will use his funding to improve the prediction and attribution of extreme weather events of exceptional severity. Weather events often have several contributing factors, including warming, related to climate change; the project will develop new methods to understand how these come together to create extremes. Hitchcock will study events that evolve over the subseasonal timescale (longer than one week but shorter than an entire season) and that are influenced in some way by the stratosphere, focusing primarily on cold air outbreaks, in which winds from the north cause extreme cold over the middle-latitude continents. The project pursues these attribution questions using observations as well as simulations from models at varying levels of complexity. Educational activities include development of a modular course intended to introduce statistical thinking to undergraduates.

Esak Lee, Nancy and Peter Meinig Family Investigator in the Life Sciences and assistant professor of biomedical engineering (Cornell Engineering), will use his award to study the regulation of the lymphatic structure and function in breast cancer, and to discover novel approaches to treating breast cancer-related lymphedema - swelling caused by poor lymphatic drainage - through the establishment of a unique cell culture platform dedicated to studying lymphatic drainage in breast cancer. Lee seeks to investigate the mechanisms of secondary lymphedema - not caused by genetic defects, as is primary lymphedema - identifying potential therapeutic targets and treatment strategies. This project aims to contribute to the development of new therapies benefitting more than 150 million lymphedema patients and enhancing health outcomes in the U.S. Educational initiatives will involve Cornell and local high school students, including those from underrepresented groups.

Wen Sun, Department of Computer Science (Ann S. Bowers College of Computing and Information Science), will use his award to develop new reinforcement learning (RL) algorithms that can learn efficiently, from as few training data points as possible, and reliably, to avoid catastrophic failures with high probability. The development of such RL algorithms can expand the applications of RL systems from simulation to real-world applications where data is expensive to collect and safety is critical. In autonomous driving, the developed technologies can make self-driving cars adapt to new road conditions safely by making fewer mistakes. The main research goal of this project is to enable real-world RL by advancing RL techniques, theoretically and empirically. The critical innovation in the project is to develop safe and efficient RL algorithms by leveraging specific problem structures and rich human feedback.

Jingjie Yeo, mechanical and aerospace engineering (Cornell Engineering), will use his award to advance computational modeling and simulations that offer new insights into the nanoscale mechanics of healthy and diseased mucus in the human gut. The mechanistic insights from this project will help to accelerate the design of mucoadhesive materials for drug delivery or antimicrobials for the human gut. Aside from contributing to the design of mucoadhesive therapeutics and antimicrobials, the research will serve as a foundation for the development of new engineered living materials that use biofilm for specific engineering objectives. The award will also support several educational initiatives, including Station1, a nonprofit higher education institution where Yeo is a co-instructor, and the Sibley School's Future Leaders in Aerospace and Mechanical Engineering (FLAME) program.

Public link

Please use the above public link if you want to share this noodl on another website.