Science

Researchers have developed a novel framework that enhances graph neural networks’ ability to identify anomalous data at test time through iterative self-improvement.

A new approach leverages readily available AI models to overcome common limitations in automated mathematical problem-solving and achieve state-of-the-art results.

New algorithms enable AI systems to learn player preferences and make effective recommendations even in complex, competitive environments where strategies are unknown.

A new framework optimizes the discovery of meaningful sequential patterns within databases, drastically improving efficiency and relevance.

A new framework uses the power of large language models and contextual retrieval to automatically generate human-understandable topic labels for short-form text.

A new method leverages generative flow networks to create diverse and actionable counterfactual explanations, offering a deeper understanding of machine learning model decisions.

A new study examines the alarming tendency of large language models to generate historically inaccurate or biased content, potentially reshaping our understanding of the past.

A new approach uses continuous normalizing flows on spectral manifolds to identify safety-critical anomalies in autonomous driving systems, offering improved robustness and interpretability.

A new study demonstrates that machine learning can significantly improve the accuracy of predicting dielectric anisotropy in nematic liquid crystals, paving the way for more efficient materials design.

A new study analyzes a decade of social media data to reveal how discussions about hydrogen energy have evolved regionally and globally.