Picture for Daniel Zoran

Daniel Zoran

Learning from One Continuous Video Stream

Add code
Dec 01, 2023
Viaarxiv icon

SODA: Bottleneck Diffusion Models for Representation Learning

Add code
Nov 29, 2023
Viaarxiv icon

Combining Behaviors with the Successor Features Keyboard

Add code
Oct 24, 2023
Viaarxiv icon

Laser: Latent Set Representations for 3D Generative Modeling

Add code
Jan 13, 2023
Viaarxiv icon

Solving Reasoning Tasks with a Slot Transformer

Add code
Oct 20, 2022
Figure 1 for Solving Reasoning Tasks with a Slot Transformer
Figure 2 for Solving Reasoning Tasks with a Slot Transformer
Figure 3 for Solving Reasoning Tasks with a Slot Transformer
Figure 4 for Solving Reasoning Tasks with a Slot Transformer
Viaarxiv icon

Object discovery and representation networks

Add code
Mar 16, 2022
Figure 1 for Object discovery and representation networks
Figure 2 for Object discovery and representation networks
Figure 3 for Object discovery and representation networks
Figure 4 for Object discovery and representation networks
Viaarxiv icon

Hierarchical Perceiver

Add code
Feb 22, 2022
Figure 1 for Hierarchical Perceiver
Figure 2 for Hierarchical Perceiver
Figure 3 for Hierarchical Perceiver
Figure 4 for Hierarchical Perceiver
Viaarxiv icon

Perceiver IO: A General Architecture for Structured Inputs & Outputs

Add code
Aug 02, 2021
Figure 1 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 2 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 3 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Figure 4 for Perceiver IO: A General Architecture for Structured Inputs & Outputs
Viaarxiv icon

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

Add code
Jun 07, 2021
Figure 1 for SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Figure 2 for SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Figure 3 for SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Figure 4 for SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Viaarxiv icon

NeRF-VAE: A Geometry Aware 3D Scene Generative Model

Add code
Apr 01, 2021
Figure 1 for NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Figure 2 for NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Figure 3 for NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Figure 4 for NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Viaarxiv icon