Govind Thattai

LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering pdf

Gökhan Tür, Aishwarya N. Reganti, Weixin Liang, 2020, ArXiv.

Are We There Yet? Learning to Localize in Embodied Instruction Following pdf

Gökhan Tür, Qiaozi Gao, Govind Thattai, 2021, ArXiv.

Interactive Teaching for Conversational AI pdf

Dilek Z. Hakkani-Tür, Gokhan Tur, Aishwarya N. Reganti, 2020, ArXiv.

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges pdf

Gaurav S. Sukhatme, Zhiwei Jia, Govind Thattai, 2021, ArXiv.

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

Alessandro Suglia, Jesse Thomason, Govind Thattai, 2021, ArXiv.

Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts pdf

Aishwarya N. Reganti, Govind Thattai, Shane Storks, 2021, ArXiv.

Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning

Kaixiang Lin, Tongzhou Mu, Govind Thattai, 2022 .

Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation

Gokhan Tur, Qing Ping, Govind Thattai, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering

Aishwarya N. Reganti, Qing Ping, Govind Thattai, 2022, ArXiv.

Learning to Act with Affordance-Aware Multimodal Neural SLAM

Kaixiang Lin, Govind Thattai, Gaurav Sukhatme, 2022 .