Humans and animals excel at generalizing from limited data, a capability yet to be fully
replicated in artificial intelligence. This perspective investigates generalization in biological …

Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-
trained models directly in weight space: By adding the fine-tuned weights of different tasks …

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-
scale condensed graph as its substitution, has immediate benefits for various graph learning …

Dataset distillation compresses large datasets into smaller synthetic coresets which retain
performance with the aim of reducing the storage and computational burden of processing …

It has become standard to solve NLP tasks by fine-tuning pre-trained language models
(LMs), especially in low-data settings. There is minimal theoretical understanding of …

Neural-network architectures have been increasingly used to represent quantum many-body
wave functions. These networks require a large number of variational parameters and are …

Of theories for why large-scale machine learning models generalize despite being vastly
overparameterized, which of their assumptions are needed to capture the qualitative …

A seminal work [Jacot et al., 2018] demonstrated that training a neural network under
specific parameterization is equivalent to performing a particular kernel method as width …

Deep learning is a topic of considerable current interest. The availability of massive data
collections and powerful software resources has led to an impressive amount of results in …

Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but
its success hinges on obtaining large amounts of precise 3D annotations. Active learning …