Conformal Prediction (CP) is a powerful framework for constructing prediction sets with
guaranteed coverage. However, recent studies have shown that integrating confidence …

TorchCP is a Python toolbox for conformal prediction research on deep learning models. It
contains various implementations for posthoc and training methods for classification and …

Many modern robotic systems are organized in terms of sequential modularized pipelines.
For example, the perception-planning-control loop is a common architecture for vision …