activity
20112023
most citedA Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning

116 citations · 289 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2023

Addressing caveats of neural persistence with deep graph persistence

Leander Girrbach, Anders Christensen, Ole Winther +2

Neural Persistence is a prominent measure for quantifying neural network complexity, proposed in the emerging field of topological data analysis in deep learning. In this work, how…

cs.LG202311 cited

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

Giorgio Giannone, Akash Srivastava, Ole Winther +1

Generative models have had a profound impact on vision and language, paving the way for a new era of multimodal generative applications. While these successes have inspired researc…

cs.LG2023

Unifying Molecular and Textual Representations via Multi-task Language Modelling

Dimitrios Christofidellis, Giorgio Giannone, Jannis Born +3

The recent advances in neural language models have also been successfully applied to the field of chemistry, offering generative solutions for classical problems in molecular desig…

cs.LG2021

Calibrated Uncertainty for Molecular Property Prediction using Ensembles of Message Passing Neural Networks

Jonas Busk, Peter Bjørn Jørgensen, Arghya Bhowmik +3

Data-driven methods based on machine learning have the potential to accelerate computational analysis of atomic structures. In this context, reliable uncertainty estimates are impo…

cs.LG2020

On the Transfer of Disentangled Representations in Realistic Settings

Andrea Dittadi, Frederik Träuble, Francesco Locatello +5

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disent…

cs.LG2020

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

Didrik Nielsen, Priyank Jaini, Emiel Hoogeboom +2

Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. However, they both impose constraints on the models:…