Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

ChatGPT is a recent chatbot service released by OpenAI and is receiving increasing
attention over the past few months. While evaluations of various aspects of ChatGPT have …

In this paper, we study dataset distillation (DD), from a novel perspective and introduce
a\emph {dataset factorization} approach, termed\emph {HaBa}, which is a plug-and-play …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

In-context learning (ICL) is a type of prompting where a transformer model operates on a
sequence of (input, output) examples and performs inference on-the-fly. In this work, we …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

We present a holistic approach to building a robust and useful natural language
classification system for real-world content moderation. The success of such a system relies …

Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global
server iteratively averages the model parameters of local users without accessing their data …