UQLM provides a suite of response-level scorers for quantifying the uncertainty of Large Language Model (LLM) outputs. Each scorer returns a confidence score between 0 and 1, where higher scores ...
Abstract: Object detection refers to the identification of objects where the presence, location, and size are determined while putting on the corresponding class labels. Object detection is sensitive ...
Abstract: Small uncrewed autonmous vehicles (UAVs) equipped with deep learning models are increasingly used to detect small objects both on the ground and in aerial environments. Since small objects ...