Alert button
Picture for Sjoerd van Steenkiste

Sjoerd van Steenkiste

Alert button

DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback

Nov 29, 2023
Jiao Sun, Deqing Fu, Yushi Hu, Su Wang, Royi Rassin, Da-Cheng Juan, Dana Alon, Charles Herrmann, Sjoerd van Steenkiste, Ranjay Krishna, Cyrus Rashtchian

Viaarxiv icon

A Systematic Comparison of Syllogistic Reasoning in Humans and Language Models

Nov 01, 2023
Tiwalayo Eisape, MH Tessler, Ishita Dasgupta, Fei Sha, Sjoerd van Steenkiste, Tal Linzen

Viaarxiv icon

The Impact of Depth and Width on Transformer Language Model Generalization

Oct 30, 2023
Jackson Petty, Sjoerd van Steenkiste, Ishita Dasgupta, Fei Sha, Dan Garrette, Tal Linzen

Viaarxiv icon

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos

Oct 09, 2023
Maximilian Seitzer, Sjoerd van Steenkiste, Thomas Kipf, Klaus Greff, Mehdi S. M. Sajjadi

Viaarxiv icon

DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$

Jun 13, 2023
Allan Jabri, Sjoerd van Steenkiste, Emiel Hoogeboom, Mehdi S. M. Sajjadi, Thomas Kipf

Figure 1 for DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
Figure 2 for DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
Figure 3 for DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
Figure 4 for DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
Viaarxiv icon

Sensitivity of Slot-Based Object-Centric Models to their Number of Slots

May 30, 2023
Roland S. Zimmermann, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Thomas Kipf, Klaus Greff

Figure 1 for Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Figure 2 for Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Figure 3 for Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Figure 4 for Sensitivity of Slot-Based Object-Centric Models to their Number of Slots
Viaarxiv icon

Scaling Vision Transformers to 22 Billion Parameters

Feb 10, 2023
Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey Gritsenko, Vighnesh Birodkar, Cristina Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetić, Dustin Tran, Thomas Kipf, Mario Lučić, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby

Figure 1 for Scaling Vision Transformers to 22 Billion Parameters
Figure 2 for Scaling Vision Transformers to 22 Billion Parameters
Figure 3 for Scaling Vision Transformers to 22 Billion Parameters
Figure 4 for Scaling Vision Transformers to 22 Billion Parameters
Viaarxiv icon

Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames

Feb 09, 2023
Ondrej Biza, Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Gamaleldin F. Elsayed, Aravindh Mahendran, Thomas Kipf

Figure 1 for Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Figure 2 for Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Figure 3 for Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Figure 4 for Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
Viaarxiv icon

Exploring through Random Curiosity with General Value Functions

Nov 18, 2022
Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber

Figure 1 for Exploring through Random Curiosity with General Value Functions
Figure 2 for Exploring through Random Curiosity with General Value Functions
Figure 3 for Exploring through Random Curiosity with General Value Functions
Figure 4 for Exploring through Random Curiosity with General Value Functions
Viaarxiv icon

SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos

Jun 15, 2022
Gamaleldin F. Elsayed, Aravindh Mahendran, Sjoerd van Steenkiste, Klaus Greff, Michael C. Mozer, Thomas Kipf

Figure 1 for SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
Figure 2 for SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
Figure 3 for SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
Figure 4 for SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
Viaarxiv icon