AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

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 …

This article presents a comprehensive and practical guide for practitioners and end-users
working with Large Language Models (LLMs) in their downstream Natural Language …

With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential
to investigate ways to adapt these models to downstream datasets. A recently proposed …

The size of vision models has grown exponentially over the last few years, especially after
the emergence of Vision Transformer. This has motivated the development of parameter …

This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

Abstract Out-of-distribution (OOD) detection is vital to safety-critical machine learning
applications and has thus been extensively studied, with a plethora of methods developed in …

Underwater object detection is one of the most challenging research topics in computer
vision technology. The complex underwater environment makes underwater images suffer …

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with
only unlabeled test data streams. Most of the previous TTA methods have achieved great …