32 citations · 80 across the 4 of their papers we have counts for
7 papers
Right for the Right Latent Factors: Debiasing Generative Models via Disentanglement
Xiaoting Shao, Karl Stelzner, Kristian Kersting
A key assumption of most statistical machine learning methods is that they have access to independent samples from the distribution of data they encounter at test time. As such, th…
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
Karl Stelzner, Kristian Kersting, Adam R. Kosiorek
We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a differen…
Structured Object-Aware Physics Prediction for Video Modeling and Planning
Jannik Kossen, Karl Stelzner, Marcel Hussing +2
When humans observe a physical system, they can easily locate objects, understand their interactions, and anticipate future behavior, even in settings with complicated and previous…
Random Sum-Product Forests with Residual Links
Fabrizio Ventola, Karl Stelzner, Alejandro Molina +1
Tractable yet expressive density estimators are a key building block of probabilistic machine learning. While sum-product networks (SPNs) offer attractive inference capabilities, o…
Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
Xiaoting Shao, Alejandro Molina, Antonio Vergari +4
Probabilistic graphical models are a central tool in AI; however, they are generally not as expressive as deep neural models, and inference is notoriously hard and slow. In contras…
SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks
Alejandro Molina, Antonio Vergari, Karl Stelzner +5
We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called…