Search Results for author:
Found 10 papers, 5 papers with code
D-Flow: Differentiating through Flows for Controlled Generation
Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in general.
Multisample Flow Matching: Straightening Flows with Minibatch Couplings
Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples.
Flow Matching for Generative Modeling
These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization.
Ranked #5 on
Density Estimation
on CIFAR-10
Matching Normalizing Flows and Probability Paths on Manifolds
Continuous Normalizing Flows (CNFs) are a class of generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE).
Frame Averaging for Invariant and Equivariant Network Design
For example, Euclidean motion invariant/equivariant graph or point cloud neural networks.
Global Attention Improves Graph Networks Generalization
This paper advocates incorporating a Low-Rank Global Attention (LRGA) module, a computation and memory efficient variant of the dot-product attention (Vaswani et al., 2017), to Graph Neural Networks (GNNs) for improving their generalization power.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Provably Powerful Graph Networks
It was shown that the popular message passing GNN cannot distinguish between graphs that are indistinguishable by the 1-WL test (Morris et al. 2018; Xu et al. 2019).
Ranked #6 on
Graph Classification
on COLLAB
Surface Networks via General Covers
Specifically, for the use case of learning spherical signals, our representation provides a low distortion alternative to several popular spherical parameterizations used in deep learning.
Invariant and Equivariant Graph Networks
In this paper we provide a characterization of all permutation invariant and equivariant linear layers for (hyper-)graph data, and show that their dimension, in case of edge-value graph data, is 2 and 15, respectively.
Multi-chart Generative Surface Modeling
The new tensor data representation is used as input to Generative Adversarial Networks for the task of 3D shape generation.
