Deep learning has become the method of choice to tackle real-world problems in different
domains, partly because of its ability to learn from data and achieve impressive performance …

Deep neural networks demonstrated their ability to provide remarkable performances on a
wide range of supervised learning tasks (eg, image classification) when trained on extensive …

Modern deep neural networks suffer from performance degradation when evaluated on
testing data under different distributions from training data. Domain generalization aims at …

Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

Abstract Domain adaptation (DA) aims to transfer the knowledge learned from source
domain to an unlabeled target domain. Some recent works tackle source-free domain …

A model must adapt itself to generalize to new and different data during testing. In this
setting of fully test-time adaptation the model has only the test data and its own parameters …

We propose a simple but effective source-free domain adaptation (SFDA) method. Treating
SFDA as an unsupervised clustering problem and following the intuition that local neighbors …

Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a
labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA …

We describe a simple method for unsupervised domain adaptation, whereby the
discrepancy between the source and target distributions is reduced by swapping the low …

In this paper, we investigate a challenging unsupervised domain adaptation setting---
unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data …