Search Results for author:
Found 18 papers, 12 papers with code
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-body systems, is a foundational problem in science.
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly.
On the Stability of Iterative Retraining of Generative Models on their own Data
In this paper, we develop a framework to rigorously study the impact of training generative models on mixed datasets -- from classical training on real data to self-consuming generative models trained on purely synthetic data.
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
The past few years have seen impressive progress in the development of deep generative models capable of producing high-dimensional, complex, and photo-realistic data.
Riemannian Diffusion Models
In this work, we generalize continuous-time diffusion models to arbitrary Riemannian manifolds and derive a variational framework for likelihood estimation.
Equivariant Finite Normalizing Flows
Generative modeling seeks to uncover the underlying factors that give rise to observed data that can often be modeled as the natural symmetries that manifest themselves through invariances and equivariances to certain transformation laws.
Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding
Dialogue systems powered by large pre-trained language models (LM) exhibit an innate ability to deliver fluent and natural-looking responses.
Online Adversarial Attacks
Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream.
Structure Aware Negative Sampling in Knowledge Graphs
Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns.
Adversarial Example Games
We introduce Adversarial Example Games (AEG), a framework that models the crafting of adversarial examples as a min-max game between a generator of attacks and a classifier.
Latent Variable Modelling with Hyperbolic Normalizing Flows
One effective solution is the use of normalizing flows \cut{defined on Euclidean spaces} to construct flexible posterior distributions.
Meta-Graph: Few Shot Link Prediction via Meta Learning
We consider the task of few shot link prediction on graphs.
Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
Deep Reinforcement Learning (DRL) algorithms for continuous action spaces are known to be brittle toward hyperparameters as well as \cut{being}sample inefficient.
A Cross-Domain Transferable Neural Coherence Model
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example.
Compositional Fairness Constraints for Graph Embeddings
Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems.
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization
Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them.
Adversarial Contrastive Estimation
Learning by contrasting positive and negative samples is a general strategy adopted by many methods.
