Researchers propose using a $q$Gaussian distribution derived from Tsallis entropy maximization as an alternative to Gaussian models in statistical spa...
Researchers have developed an adaptive surrogate modeling method for problems with high-dimensional spatio-temporal outputs. This approach uses dimens...
Researchers have developed a new framework called Co-RL that enables unsupervised reasoning in reinforcement learning. Unlike traditional self-rewardi...
Researchers have developed a new method for reconstructing CT scans from just two X-ray images. The approach, called LiftXR, first generates a 3D layo...
Researchers have developed a nonadaptive learning method for robust nonlinear output regulation in control systems. This approach combines an input-dr...
Researchers analyzed the effectiveness of 'curriculum learning' in large language models by examining how different schedules for training data affect...
Researchers have surveyed the Model Context Protocol (MCP) ecosystem, finding that AI agents are increasingly modifying external state. This shift in ...
Researchers have proposed a new method for forecasting irregular time series data, which is commonly used in healthcare and meteorological observation...
Researchers have proposed a new evaluation metric for irregular time-series forecasting called Continuous-time Squared Error (CSE). They argue that th...
NeuroAbs is a new framework for accelerating property checking in hardware design verification. It uses machine learning to analyze and simplify compl...
Researchers have proposed a new method called ADAPT to improve the robustness of vision-language models. They found that existing methods can actually...
Researchers propose a method called Online Residual Policy Adaptation (ORPA) for improving the performance of robotic manipulation policies in real-ti...