Statistical Learning
GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients
Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications.
Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation
In this paper, we present MixV al, an innovative model selection method that operates solely with unlabeled target data during inference.
Tracr: Compiled Transformers as a Laboratory for Interpretability David Lindner
We show how to "compile" human-readable programs into standard decoder-only transformer models.
