Papers by Samuel Gershman

1 papers
Language-Mediated, Object-Centric Representation Learning (2021.findings-acl)

Copied to clipboard

Challenge: Recent work has studied the problem of unsupervised object representation learning, though without language.
Approach: They propose language-mediated, Objectcentric Representation Learning (LORL) a paradigm for learning disentangled, objectcentric scene representations from vision and language.
Outcome: The proposed paradigm improves performance of unsupervised object discovery algorithms on two datasets using language.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations