655 citations · 2.7k across the 49 of their papers we have counts for
54 papers
Image-free Classifier Injection for Zero-Shot Classification
Anders Christensen, Massimiliano Mancini, A. Sophia Koepke +2
Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from…
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…
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…
Implicit Transfer Operator Learning: Multiple Time-Resolution Surrogates for Molecular Dynamics
Mathias Schreiner, Ole Winther, Simon Olsson
Computing properties of molecular systems rely on estimating expectations of the (unnormalized) Boltzmann distribution. Molecular dynamics (MD) is a broadly adopted technique to ap…
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…
ThoughtSource: A central hub for large language model reasoning data
Simon Ott, Konstantin Hebenstreit, Valentin Liévin +6
Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail…
Variational Open-Domain Question Answering
Valentin Liévin, Andreas Geert Motzfeldt, Ida Riis Jensen +1
Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference.…
NeuralNEB -- Neural Networks can find Reaction Paths Fast
Mathias Schreiner, Arghya Bhowmik, Tejs Vegge +2
Quantum mechanical methods like Density Functional Theory (DFT) are used with great success alongside efficient search algorithms for studying kinetics of reactive systems. However…
Can large language models reason about medical questions?
Valentin Liévin, Christoffer Egeberg Hother, Andreas Geert Motzfeldt +1
Although large language models (LLMs) often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert dom…
Few-Shot Diffusion Models
Giorgio Giannone, Didrik Nielsen, Ole Winther
Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties…
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Samuele Papa, Ole Winther, Andrea Dittadi
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging. In this paper, we systematic…
Image Super-Resolution With Deep Variational Autoencoders
Darius Chira, Ilian Haralampiev, Ole Winther +2
Image super-resolution (SR) techniques are used to generate a high-resolution image from a low-resolution image. Until now, deep generative models such as autoregressive models and…
SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
Giorgio Giannone, Ole Winther
A few-shot generative model should be able to generate data from a novel distribution by only observing a limited set of examples. In few-shot learning the model is trained on data…
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…
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
Andrea Dittadi, Frederik Träuble, Manuel Wüthrich +7
Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level…
Generalization and Robustness Implications in Object-Centric Learning
Andrea Dittadi, Samuele Papa, Michele De Vita +3
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed represe…
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…
Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
Valentin Liévin, Andrea Dittadi, Anders Christensen +1
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large (number o…
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:…
Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow
Didrik Nielsen, Ole Winther
Flow models have recently made great progress at modeling ordinal discrete data such as images and audio. Due to the continuous nature of flow models, dequantization is typically a…
LAVAE: Disentangling Location and Appearance
Andrea Dittadi, Ole Winther
We propose a probabilistic generative model for unsupervised learning of structured, interpretable, object-based representations of visual scenes. We use amortized variational infe…
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
Lars Maaløe, Marco Fraccaro, Valentin Liévin +1
With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their perfo…
Attend, Copy, Parse -- End-to-end information extraction from documents
Rasmus Berg Palm, Florian Laws, Ole Winther
Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally c…
A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images
Jacob Madsen, Pei Liu, Jens Kling +4
Recording atomic-resolution transmission electron microscopy (TEM) images is becoming increasingly routine. A new bottleneck is then analyzing this information, which often involve…