This paper pertains to an emerging machine learning paradigm: learning higher-order
functions, ie functions whose inputs are functions themselves, particularly when these inputs …

Neural functional networks (NFNs) have recently gained significant attention due to their
diverse applications, ranging from predicting network generalization and network editing to …

Abstract Multimodal Large Language Models (MLLMs) have demonstrated an excellent
understanding of images and 3D data. However, both modalities have shortcomings in …

A challenging problem in many modern machine learning tasks is to process weight-space
features, ie, to transform or extract information from the weights and gradients of a neural …

Neural fields (NeFs) have recently emerged as a versatile method for modeling signals of
various modalities including images shapes and scenes. Subsequently a number of works …

Many algorithms and observed phenomena in deep learning appear to be affected by
parameter symmetries--transformations of neural network parameters that do not change the …

Abstract Neural Radiance Fields (NeRFs) have emerged as a standard framework for
representing 3D scenes and objects introducing a novel data type for information exchange …

Conditional Neural Fields (CNFs) are increasingly being leveraged as continuous signal
representations, by associating each data-sample with a latent variable that conditions a …

Learning representations of well-trained neural network models holds the promise to
provide an understanding of the inner workings of those models. However, previous work …

The rapid growth of neural network models shared on the internet has made model weights
an important data modality. However, this information is underutilized as the weights are …