358 citations · 727 across the 15 of their papers we have counts for
12 papers · 1 filter
Quantization-Free Autoregressive Action Transformer
Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach +1
Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. Howe…
JetFormer: An Autoregressive Generative Model of Raw Images and Text
Michael Tschannen, André Susano Pinto, Alexander Kolesnikov
Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these mod…
Weakly-Supervised Disentanglement Without Compromises
Francesco Locatello, Ben Poole, Gunnar Rätsch +3
Intelligent agents should be able to learn useful representations by observing changes in their environment. We model such observations as pairs of non-i.i.d. images sharing at lea…
Semantic Bottleneck Scene Generation
Samaneh Azadi, Michael Tschannen, Eric Tzeng +3
Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottl…
On Mutual Information Maximization for Representation Learning
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein +2
Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different…
Disentangling Factors of Variation Using Few Labels
Francesco Locatello, Michael Tschannen, Stefan Bauer +3
Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentangleme…