System Description
System descriptions encompass the design, implementation, and evaluation of computational systems addressing diverse challenges. Current research focuses on improving system efficiency and accuracy through techniques like hybrid neural networks for optimal control, fine-tuned BERT models for question answering, and various large language model (LLM) applications for tasks ranging from automatic scoring to creative idea generation. These advancements are significant for improving automation in various fields, from energy management and disaster response to healthcare and education, and for advancing our understanding of AI capabilities and limitations.
Papers
T*$\varepsilon$ -- Bounded-Suboptimal Efficient Motion Planning for Minimum-Time Planar Curvature-Constrained Systems
Doron Pinsky, Petr Váňa, Jan Faigl, Oren Salzman
MLPro: A System for Hosting Crowdsourced Machine Learning Challenges for Open-Ended Research Problems
Peter Washington, Aayush Nandkeolyar, Sam Yang