Recent successful generative models are trained by fitting a neural netw...
Simulation-free methods for training continuous-time generative models
c...
Surface reconstruction has been seeing a lot of progress lately by utili...
Graph Neural Networks (GNN) are inherently limited in their expressive p...
Recent advances in text-to-image generation with diffusion models presen...
We propose Riemannian Flow Matching (RFM), a simple yet powerful framewo...
We introduce a new paradigm for generative modeling built on Continuous
...
We investigate the parameterization of deep neural networks that by desi...
Continuous Normalizing Flows (CNFs) are a class of generative models tha...
In recent years, algorithms and neural architectures based on the
Weisfe...
We are interested in learning generative models for complex geometries
d...
Neural volume rendering became increasingly popular recently due to its
...
Modeling distributions on Riemannian manifolds is a crucial component in...
Representing surfaces as zero level sets of neural networks recently eme...
Graph Neural Networks (GNNs) are known to have an expressive power bound...
Many problems in machine learning (ML) can be cast as learning functions...
Using deep neural networks that are either invariant or equivariant to
p...
The level sets of neural networks represent fundamental properties such ...
Recently, the Weisfeiler-Lehman (WL) graph isomorphism test was used to
...
Constraining linear layers in neural networks to respect symmetry
transf...
Developing deep learning techniques for geometric data is an active and
...
Invariant and equivariant networks have been successfully used for learn...
This paper introduces a 3D shape generative model based on deep neural
n...
This paper presents Point Convolutional Neural Networks (PCNN): a novel
...
We consider Riemann mappings from bounded Lipschitz domains in the plane...
We consider Riemann mappings from bounded Lipschitz domains in the plane...
Photometric Stereo methods seek to reconstruct the 3d shape of an object...
Correspondence problems are often modelled as quadratic optimization pro...
Finding correspondences in wide baseline setups is a challenging problem...
We present a constructive approach for approximating the conformal map
(...