Machine learning, AI research, and applications.
Researchers developed a system to improve data collection by UAVs monitoring wildfires, which could help detect and respond to wildfires faster, reducing environmental damage.
A new AI system can better understand complex satellite images by first learning relevant information through text, before analyzing the visual data. This could improve how we use satellite imagery to study the environment and plan infrastructure.
Researchers developed a way to detect when a graph model is being used on data it wasn't trained on, helping ensure the reliability of graph AI systems in real-world applications.
Researchers developed a framework to better detect toxic content online by combining text and images, which could help make social media platforms safer for users.
Researchers developed a benchmark to evaluate AI systems that give financial advice, focusing on long-term utility rather than just imitating user behavior, which can be short-sighted in volatile markets.
Researchers developed a technique to align microscope images taken from opposite scan directions, which could improve the speed and accuracy of photoacoustic imaging used for medical diagnosis and research.
A new CLEF evaluation lab will test how well AI systems can extract information about people and places from old texts written in different languages. This could help historians and journalists better understand the connections between historical figures and locations.
A new framework called PETS helps AI models perform more consistently during testing, which could lead to more reliable and effective AI systems in real-world applications.
Researchers developed a new method to help self-driving cars continuously detect and avoid rare, risky situations, improving safety for autonomous vehicles.
Current speech language models can perform as well as combining speech recognition with language models, without explicit speech recognition. This means these speech models can produce accurate text output from audio inputs more efficiently.
Researchers found that translating culturally-sensitive phrases between languages is challenging, as meaning can be lost when words with similar definitions don't convey the same social context.
Researchers created a new Arabic language test called ALPS to check if AI language models truly understand complex linguistic and pragmatic aspects of the Arabic language, beyond just literal translations.
Researchers developed a way to make AI language models more efficient by decomposing attention weights, which could lead to faster and cheaper AI systems.
Researchers developed a new AI algorithm that can automatically discover and categorize unknown types of data, potentially enabling better organization and discovery of digital content. This could lead to improved search, recommendation, and content organization systems.
A new study finds that popular AI safety datasets used to train models may not accurately reflect real-world attacks, raising concerns about the reliability of AI safety systems.
Researchers developed a way to detect when a graph model is being used on data it wasn't trained on, helping ensure the reliability of graph AI systems in real-world applications.
Researchers developed a benchmark to evaluate AI systems that give financial advice, focusing on long-term utility rather than just imitating user behavior, which can be short-sighted in volatile markets.
A new CLEF evaluation lab will test how well AI systems can extract information about people and places from old texts written in different languages. This could help historians and journalists better understand the connections between historical figures and locations.
A new framework called PETS helps AI models perform more consistently during testing, which could lead to more reliable and effective AI systems in real-world applications.
Researchers developed a new method to help self-driving cars continuously detect and avoid rare, risky situations, improving safety for autonomous vehicles.
Current speech language models can perform as well as combining speech recognition with language models, without explicit speech recognition. This means these speech models can produce accurate text output from audio inputs more efficiently.
Researchers found that translating culturally-sensitive phrases between languages is challenging, as meaning can be lost when words with similar definitions don't convey the same social context.
Researchers created a new Arabic language test called ALPS to check if AI language models truly understand complex linguistic and pragmatic aspects of the Arabic language, beyond just literal translations.
Researchers developed a way to make AI language models more efficient by decomposing attention weights, which could lead to faster and cheaper AI systems.
Researchers developed a new AI algorithm that can automatically discover and categorize unknown types of data, potentially enabling better organization and discovery of digital content. This could lead to improved search, recommendation, and content organization systems.
A new study finds that popular AI safety datasets used to train models may not accurately reflect real-world attacks, raising concerns about the reliability of AI safety systems.
Researchers developed a way for AI devices to better understand each other by aligning their internal representations of language and concepts, which could improve communication and collaboration between intelligent systems.
Researchers developed a new kind of web agent that can interpret ambiguous user queries by analyzing their browsing history, which could make online searches more personalized and contextual.
Researchers developed new ways to make AI language models more useful for telecom companies, by improving the models' understanding of industry-specific knowledge and making their outputs more explainable.