Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion

Jan 1, 2021·

Alessandro Suglia

,

Qiaozi Gao

,

Jesse Thomason

,

Govind Thattai

,

Gaurav S. Sukhatme

· 0 min read

Type

Conference paper

Publication

EMNLP 2021 Workshop on Novel Ideas in Learning-to-Learn through Interaction

Last updated on Jan 1, 2021

← An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games Jan 1, 2021

CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning Jan 1, 2020 →