Introduction Armed conflict severely impacts health, with indirect deaths often exceeding direct casualties two to four times ...

Abstract: It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes ...

This is the source code for our CVPR (2022) paper: Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment based on Pytorch. This version is a demo of how to use GCL loss. The version ...

This package provides a simple interface for training and evaluating tuned lenses. A tuned lens allows us to peek at the iterative computations a transformer uses to compute the next token. The reason ...