Text-to-image synthesis has recently seen significant progress thanks to large pretrained
language models, large-scale training data, and the introduction of scalable model families …

Most existing geometry processing algorithms use meshes as the default shape
representation. Manipulating meshes, however, requires one to maintain high quality in the …

Neural fields have emerged as a new paradigm for representing signals, thanks to their
ability to do it compactly while being easy to optimize. In most applications, however, neural …

The standard approaches to neural network implementation yield powerful function
approximation capabilities but are limited in their abilities to learn meta representations and …

Despite the remarkable capabilities of deep neural networks in image recognition, the
dependence on activation functions remains a largely unexplored area and has yet to be …

Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural
networks and their generalization bounds. The study on NTK has been devoted to typical …

Deep neural networks have been the driving force behind the success in classification tasks,
eg, object and audio recognition. Impressive results and generalization have been achieved …

Learning representations of stochastic processes is an emerging problem in machine
learning with applications from meta-learning to physical object models to time series …

Abstract We introduce MIGS (Multi-Identity Gaussian Splatting), a novel method that learns a
single neural representation for multiple identities, using only monocular videos. Recent 3D …

In this work, we introduce a method that learns a single dynamic neural radiance field
(NeRF) from monocular talking face videos of multiple identities. NeRFs have shown …