article

Unlabeled 3D objects present an opportunity to leverage pretrained vision language models (VLMs) on a range of annotation tasks – …

We introduce SODA, a self-supervised diffusion model, designed for representation learning. The model incorporates an image encoder, …

We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations. …

Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning …

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic …

The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence. Where those basic building …

We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders. …

This paper describes SCAN (Symbol-Concept Association Network), a new framework for learning recombinable concepts in the visual domain. We first use the previously published beta-VAE (Higgins et al., 2017a) architecture to learn a disentangled representation of the latent structure of the visual world, before training SCAN to extract abstract concepts grounded in such disentangled visual primitives through fast symbol association.