Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention

no code implementations • NAACL (ACL) 2022 • Ayush K Chakravarthy, Jacob Labe Russin, Randall O’Reilly

Systematicity is thought to be a key inductive bias possessed by humans that is lacking in standard natural language processing systems such as those utilizing transformers.

Inductive Bias Systematic Generalization

BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation

no code implementations • CVPR 2024 • Yunhao Ge, Yihe Tang, Jiashu Xu, Cem Gokmen, Chengshu Li, Wensi Ai, Benjamin Jose Martinez, Arman Aydin, Mona Anvari, Ayush K Chakravarthy, Hong-Xing Yu, Josiah Wong, Sanjana Srivastava, Sharon Lee, Shengxin Zha, Laurent Itti, Yunzhu Li, Roberto Martín-Martín, Miao Liu, Pengchuan Zhang, Ruohan Zhang, Li Fei-Fei, Jiajun Wu

We introduce the BEHAVIOR Vision Suite (BVS), a set of tools and assets to generate fully customized synthetic data for systematic evaluation of computer vision models, based on the newly developed embodied AI benchmark, BEHAVIOR-1K.

Dataset Generation Scene Understanding