Researchers have developed a statistical shape model for the heart that can be used to complete missing structures in cardiac computed-tomography (CT)...
Researchers have proposed a new approach to accelerate Mixed-Integer Linear Programming (MILP) solving. They observed that solutions found early in th...
Researchers propose a new framework called SCPaT for multivariate time series forecasting. The framework uses semantic structured partitioning to deco...
Researchers have developed ReguSim, a controlled environment for testing the ability of large language models (LLMs) to follow rules in financial mark...
Large language model (LLM) agents acquire task-specific capabilities by loading reusable skill documents into a bounded context window. However, curre...
Researchers have created a new benchmark called ExPhy to help evaluate AI models' ability to learn and predict physical properties in multi-object tra...
Researchers have identified a problem in preference optimization for generative models, known as manifold drift. This occurs when updates to the model...
Researchers have proposed a new model called CMPL (Contrastive Mixed Prompt Learning) to address the challenge of incomplete multimodal sentiment anal...
Researchers have proposed a three-dimensional typology for understanding the concept of agency in advanced artificial intelligence (AI) systems. The f...
Researchers have developed a 'safety net' system to ensure the reliability of AI-powered aviation systems. The system combines neural networks with lo...
Researchers have found that restricting what a shared language model can see in its environment improves its ability to generalize and solve complex t...
Researchers have developed DECOWAM, a new model for legged mobile robots that can predict how their movements affect future observations. This is achi...