NSF REU Program

The College of Information at the University of North Texas (UNT) will conduct a 10-week summer research program funded by the National Science Foundation (NSF) for 10 undergraduates from May 19 to July 25, 2025 titled "Beyond Language: Training to Create and Share Vector Embeddings across Applications". The goal of this REU is to teach students how to build modern Artificial Intelligence (AI) systems capable of communicating their acquired knowledge across domains. Knowledge is about much more than what can be described in language, and we aim to train students to handle this new way of communication. We welcome rising sophomores, juniors and seniors from accredited undergraduate institutions who are U.S. citizens or permanent residents to apply for this NSF REU program to conduct research with faculty members at UNT. Underrepresented groups are strongly encouraged to apply, as well as those from academic institutions with limited research opportunities.

---

Students participating in this interdisciplinary undergraduate research experience will be trained in techniques that will allow them to more efficiently communicate the knowledge acquired by self-supervised deep learning models. The 10 participating students will create vector representations of common terms or items that appear across various applications, utilize those embeddings to improve prediction models, and properly validate and document the benefit of this approach. For the first 5 weeks, students will be exposed to different embedding strategies and machine learning applications utilizing them, then transition to demonstrations and trouble-shooting of their individual research efforts in the last 5 weeks. Early in the program they will identify an embedding, application domain, and external advisor to work with among a number of presented options. Students will also participate in a long-standing, unique AI/CS summer research program integrating current UNT students and external REU students to facilitate collaboration across departments and collaboration among a range of students and faculty mentors.

We are grateful to the NSF and the College of Information, the Department of Information Science, the Department of Computer Science and Engineering, and many offices at UNT for providing support to this program.