Publications
-
Concepts for autonomous navigation of underground mine face haulage equipment using depth cameras
Abstract This paper describes the development of a software pipeline for autonomous navigation of underground mine haulage equipment. The approach uses depth-sensing cameras mounted on the haulage vehicle to capture…
-
Medical Procedure Tracking using Abductive Planning – A PARADIGM Shift
Abstract This paper presents PARACHUTE, a Prolog-based frame-work for abductive trace completion and projection for real-time medical procedure tracking and guidance, developed as part of the AI-powered AMIRA system in…
-
GeoSURGE: Geo-localization using semantic fusion with hierarchy of geographic embeddings
Abstract Worldwide visual geo-localization aims to determine the geographic location of an image anywhere on Earth using only its visual content. Despite recent progress, learning expressive representations of geographic space…
-
Bridging the Divide: Connecting Word Recognition and Language Comprehension in Early Literacy
This brief focuses on how reading foundational skills instruction in K–2 classrooms can more intentionally connect word recognition and language comprehension through two particular bridging processes - reading fluency and…
-
Partnering with Faith Communities to Expand Early Care and Education Access for Children in Foster Care
This brief presents findings about Arkansas faith-based ECE programs’ participation in state quality rating and child care subsidy systems.
-
DUDA: Distilled unsupervised domain adaptation for lightweight semantic segmentation
Abstract Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally identical teacher…
-
Technical report: Psychometric properties of self-directed learning survey measures in broad access institution contexts
Abstract The Postsecondary Teaching with Technology Collaborative (the Collaborative) conducted secondary analyses of survey datasets to advance the conceptualization and measurement of self-directed learning (SDL) in higher education. Drawing on…
-
Lessons Learned Estimating Impacts of Extreme Weather on District-Level Achievement
Abstract The study highlights limitations of using integrated district-level education and county-level weather event data to estimate effects of weather events on student achievement. Limitations included imprecise geographic linkage between…
-
Evaluation of the Career Connect Pathway Project. Final Report.
Abstract The Career Connected Pathways (CCP) project was designed to increase the number of high school students who graduate prepared to pursue high-wage, high-demand careers in computer science and cybersecurity. Launched…
-
Interpolative Decoding: Exploring the Spectrum of Personality Traits in LLMs
Abstract Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human…
-
Collaborative Innovations: Bridging Gaps and Promoting AI Literacy Through Engagement and Dissemination in Education
Abstract SRI researchers reviewed existing studies to understand how AI literacy is taught across grade levels and what components are emphasized in each grade band. Our findings show AI literacy…
-
Opening the Classroom Door: Can AI Improve Understanding of Pre-K Experiences
Abstract High-quality early childhood classrooms provide children with a nurturing environment to develop their physical, social, and academic capabilities. All day the classroom is in motion: children move from whole-group…