This is Part II of the two-part comprehensive survey devoted to a computing framework most commonly known under the names Hyperdimensional Computing and Vector Symbolic …
The recent advent of large language models has reinvigorated debate over whether human cognitive capacities might emerge in such generic models given sufficient training data. Of …
A Ramesh, M Pavlov, G Goh, S Gray… - International …, 2021 - proceedings.mlr.press
Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures …
The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and increasing interest in both fields to …
Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to the input text prompt …
The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven …
A compositional understanding of the world in terms of objects and their geometry in 3D space is considered a cornerstone of human cognition. Facilitating the learning of such a …
Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built …
G Singh, YF Wu, S Ahn - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to …