Large language models (LLMs) can generate credible but inaccurate responses, so researchers have developed uncertainty quantification methods to check the reliability of predictions. One popular ...

Thermometer, a new calibration technique tailored for large language models, can prevent LLMs from being overconfident or underconfident about their predictions. The technique aims to help users know ...

Hydrological models represent water movement in natural systems, and they are important for water resource planning and ...

Nvidia's KV Cache Transform Coding (KVTC) compresses LLM key-value cache by 20x without model changes, cutting GPU memory ...

In high-stakes settings like medical diagnostics, users often want to know what led a computer vision model to make a certain prediction, so they can determine whether to trust its output. Concept ...

2024 is going to be a huge year for the cross-section of generative AI/large foundational models and robotics. There’s a lot of excitement swirling around the potential for various applications, ...

FSU College of Engineering and Florida State University’s Resilient Infrastructure and Disaster Response Center examined ...

NEW YORK, NY--(Marketwire - Sep 26, 2012) - Errors in financial models that banks use on a daily basis could lead to tremendous financial and non-financial losses. It is crucial for banks to ...

Researchers at Google Cloud and UCLA have proposed a new reinforcement learning framework that significantly improves the ability of language models to learn very challenging multi-step reasoning ...