Alert button
Picture for Mario Lucic

Mario Lucic

Alert button

PaLI-X: On Scaling up a Multilingual Vision and Language Model

May 29, 2023
Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, AJ Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

Figure 1 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 2 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 3 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 4 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Viaarxiv icon

Audiovisual Masked Autoencoders

Dec 09, 2022
Mariana-Iuliana Georgescu, Eduardo Fonseca, Radu Tudor Ionescu, Mario Lucic, Cordelia Schmid, Anurag Arnab

Figure 1 for Audiovisual Masked Autoencoders
Figure 2 for Audiovisual Masked Autoencoders
Figure 3 for Audiovisual Masked Autoencoders
Figure 4 for Audiovisual Masked Autoencoders
Viaarxiv icon

RUST: Latent Neural Scene Representations from Unposed Imagery

Nov 25, 2022
Mehdi S. M. Sajjadi, Aravindh Mahendran, Thomas Kipf, Etienne Pot, Daniel Duckworth, Mario Lucic, Klaus Greff

Figure 1 for RUST: Latent Neural Scene Representations from Unposed Imagery
Figure 2 for RUST: Latent Neural Scene Representations from Unposed Imagery
Figure 3 for RUST: Latent Neural Scene Representations from Unposed Imagery
Figure 4 for RUST: Latent Neural Scene Representations from Unposed Imagery
Viaarxiv icon

VCT: A Video Compression Transformer

Jun 15, 2022
Fabian Mentzer, George Toderici, David Minnen, Sung-Jin Hwang, Sergi Caelles, Mario Lucic, Eirikur Agustsson

Figure 1 for VCT: A Video Compression Transformer
Figure 2 for VCT: A Video Compression Transformer
Figure 3 for VCT: A Video Compression Transformer
Figure 4 for VCT: A Video Compression Transformer
Viaarxiv icon

Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Nov 29, 2021
Mehdi S. M. Sajjadi, Henning Meyer, Etienne Pot, Urs Bergmann, Klaus Greff, Noha Radwan, Suhani Vora, Mario Lucic, Daniel Duckworth, Alexey Dosovitskiy, Jakob Uszkoreit, Thomas Funkhouser, Andrea Tagliasacchi

Figure 1 for Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Figure 2 for Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Figure 3 for Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Figure 4 for Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
Viaarxiv icon

PolyViT: Co-training Vision Transformers on Images, Videos and Audio

Nov 25, 2021
Valerii Likhosherstov, Anurag Arnab, Krzysztof Choromanski, Mario Lucic, Yi Tay, Adrian Weller, Mostafa Dehghani

Figure 1 for PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Figure 2 for PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Figure 3 for PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Figure 4 for PolyViT: Co-training Vision Transformers on Images, Videos and Audio
Viaarxiv icon

Revisiting the Calibration of Modern Neural Networks

Jun 15, 2021
Matthias Minderer, Josip Djolonga, Rob Romijnders, Frances Hubis, Xiaohua Zhai, Neil Houlsby, Dustin Tran, Mario Lucic

Figure 1 for Revisiting the Calibration of Modern Neural Networks
Figure 2 for Revisiting the Calibration of Modern Neural Networks
Figure 3 for Revisiting the Calibration of Modern Neural Networks
Figure 4 for Revisiting the Calibration of Modern Neural Networks
Viaarxiv icon

A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models

Jun 06, 2021
Ibrahim Alabdulmohsin, Mario Lucic

Figure 1 for A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
Figure 2 for A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
Figure 3 for A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
Figure 4 for A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
Viaarxiv icon

MLP-Mixer: An all-MLP Architecture for Vision

May 17, 2021
Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, Alexey Dosovitskiy

Figure 1 for MLP-Mixer: An all-MLP Architecture for Vision
Figure 2 for MLP-Mixer: An all-MLP Architecture for Vision
Figure 3 for MLP-Mixer: An all-MLP Architecture for Vision
Figure 4 for MLP-Mixer: An all-MLP Architecture for Vision
Viaarxiv icon