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: underwater object detection and recognition are critical technologies in marine science and engineering, enabling advancements in environmental monitoring, resource exploration, and ...

In recent years, the detection for tiny objects in remote sensing images has become a hot research topic. Tiny objects contain a limited number of pixels and are easily confused with the background, ...

World's largest digital camera likely to discover interstellar objects, millions of asteroids The Vera C. Rubin Observatory in Chile is set to begin its biggest undertaking this fall, with the Legacy ...

The latest Apple-made artificial intelligence model, FastVLM, is now available for users to try out, offering a significantly faster video-captioning AI that can describe what the camera captures on ...

Real-world datasets follow an imbalanced distribution, which poses significant challenges in rare-category object detection. Recent studies tackle this problem by developing re-weighting and ...