Publications (51)
Noisy subspace clustering via matching pursuits
Michael Tschannen, Helmut Bölcskei
High-Fidelity Generative Image Compression
Fabian Mentzer, George Toderici, Michael Tschannen +1
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Francesco Locatello, Rajiv Khanna, Michael Tschannen +1
Representation learning from videos in-the-wild: An object-centric approach
Rob Romijnders, Aravindh Mahendran, Michael Tschannen +4
StrassenNets: Deep Learning with a Multiplication Budget
Michael Tschannen, Aran Khanna, Anima Anandkumar
GIVT: Generative Infinite-Vocabulary Transformers
Michael Tschannen, Cian Eastwood, Fabian Mentzer
M2T: Masking Transformers Twice for Faster Decoding
Fabian Mentzer, Eirikur Agustsson, Michael Tschannen
Self-Supervised Learning of Video-Induced Visual Invariances
Michael Tschannen, Josip Djolonga, Marvin Ritter +5
Nonparametric Nearest Neighbor Random Process Clustering
Michael Tschannen, Helmut Bölcskei
Semantic Bottleneck Scene Generation
Samaneh Azadi, Michael Tschannen, Eric Tzeng +3
PaLI-X: On Scaling up a Multilingual Vision and Language Model
Xi Chen, Josip Djolonga, Piotr Padlewski +40
Weakly-Supervised Disentanglement Without Compromises
Francesco Locatello, Ben Poole, Gunnar Rätsch +3
High-Fidelity Image Generation With Fewer Labels
Mario Lucic, Michael Tschannen, Marvin Ritter +3
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees
Francesco Locatello, Michael Tschannen, Gunnar Rätsch +1
Learning Better Lossless Compression Using Lossy Compression
Fabian Mentzer, Luc Van Gool, Michael Tschannen
Deep Structured Features for Semantic Segmentation
Michael Tschannen, Lukas Cavigelli, Fabian Mentzer +2
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
Eirikur Agustsson, Fabian Mentzer, Michael Tschannen +4
Recent Advances in Autoencoder-Based Representation Learning
Michael Tschannen, Olivier Bachem, Mario Lucic
Discrete Deep Feature Extraction: A Theory and New Architectures
Thomas Wiatowski, Michael Tschannen, Aleksandar StaniÄ +2
Deep Generative Models for Distribution-Preserving Lossy Compression
Michael Tschannen, Eirikur Agustsson, Mario Lucic
Robust nonparametric nearest neighbor random process clustering
Michael Tschannen, Helmut Bölcskei
Disentangling Factors of Variation Using Few Labels
Francesco Locatello, Michael Tschannen, Stefan Bauer +3
JetFormer: An Autoregressive Generative Model of Raw Images and Text
Michael Tschannen, André Susano Pinto, Alexander Kolesnikov
Image Captioners Are Scalable Vision Learners Too
Michael Tschannen, Manoj Kumar, Andreas Steiner +3
PaliGemma: A versatile 3B VLM for transfer
Lucas Beyer, Andreas Steiner, André Susano Pinto +32
PaliGemma 2: A Family of Versatile VLMs for Transfer
Andreas Steiner, André Susano Pinto, Michael Tschannen +15
Conditional Probability Models for Deep Image Compression
Fabian Mentzer, Eirikur Agustsson, Michael Tschannen +2
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
Towards Image Understanding from Deep Compression without Decoding
Robert Torfason, Fabian Mentzer, Eirikur Agustsson +3
On Robustness and Transferability of Convolutional Neural Networks
Josip Djolonga, Jessica Yung, Michael Tschannen +11
On Mutual Information Maximization for Representation Learning
Michael Tschannen, Josip Djolonga, Paul K. Rubenstein +2
Finite Scalar Quantization: VQ-VAE Made Simple
Fabian Mentzer, David Minnen, Eirikur Agustsson +1
CLIPPO: Image-and-Language Understanding from Pixels Only
Michael Tschannen, Basil Mustafa, Neil Houlsby
Scaling Vision Transformers to 22 Billion Parameters
Mostafa Dehghani, Josip Djolonga, Basil Mustafa +39
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Michael Tschannen, Alexey Gritsenko, Xiao Wang +11
Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers
Aleksandar StaniÄ, Sergi Caelles, Michael Tschannen
FlexiViT: One Model for All Patch Sizes
Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov +7
Neural Face Video Compression using Multiple Views
Anna Volokitin, Stefan Brugger, Ali Benlalah +3
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
Subspace clustering of dimensionality-reduced data
Reinhard Heckel, Michael Tschannen, Helmut Bölcskei
LocCa: Visual Pretraining with Location-aware Captioners
Bo Wan, Michael Tschannen, Yongqin Xian +7
Automatic Shortcut Removal for Self-Supervised Representation Learning
Matthias Minderer, Olivier Bachem, Neil Houlsby +1
Generative Adversarial Networks for Extreme Learned Image Compression
Eirikur Agustsson, Michael Tschannen, Fabian Mentzer +2
Dimensionality-reduced subspace clustering
Reinhard Heckel, Michael Tschannen, Helmut Bölcskei
Pursuits in Structured Non-Convex Matrix Factorizations
Rajiv Khanna, Michael Tschannen, Martin Jaggi
Quantization-Free Autoregressive Action Transformer
Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach +1
Convolutional Recurrent Neural Networks for Electrocardiogram Classification
Martin Zihlmann, Dmytro Perekrestenko, Michael Tschannen
Born Again Neural Networks
Tommaso Furlanello, Zachary C. Lipton, Michael Tschannen +2
Practical Full Resolution Learned Lossless Image Compression
Fabian Mentzer, Eirikur Agustsson, Michael Tschannen +2
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov +14
Jet: A Modern Transformer-Based Normalizing Flow
Alexander Kolesnikov, André Susano Pinto, Michael Tschannen