AIConfPaper
← Search

Michael Johnston

8 accepted papers

2025

Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering

Vishnu Sashank Dorbala, Prasoon Goyal, Robinson Piramuthu, Michael Johnston, Reza Ghanadan, Dinesh Manocha
IROS 2025

We present and tackle the problem of Embodied Question Answering (EQA) with Situational Queries (S-EQA) in a household environment. Unlike prior EQA work tackling simple queries that directly reference target objects and properties ("What is the color of the car?"), situational queries (such as "Is

Cited by 2Source ↗Scholar ↗
2024

"Don't Forget to Put the Milk Back!" Dataset for Enabling Embodied Agents to Detect Anomalous Situations

James F. Mullen Jr., Prasoon Goyal, Robinson Piramuthu, Michael Johnston, Dinesh Manocha, Reza Ghanadan
RA-L 2024

Home robots intend to make their users lives easier. Our work moves toward more helpful home robots by enabling them to inform their users of dangerous or unsanitary anomalies in the home. Some examples of these anomalies include the user leaving their milk out, forgetting to turn off the stove, or

Cited by 13Source ↗Scholar ↗
2024

Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning

Jiachen Li, Qiaozi Gao, Michael Johnston, Xiaofeng Gao, Xuehai He, Hangjie Shi +3
ICML 2024poster

Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models' tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the pr…

Cited by 11Source ↗PDF ↗Scholar ↗
2023

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

Qiaozi Gao, Govind Thattai, Suhaila Shakiah, Xiaofeng Gao, Shreyas Pansare, Vasu Sharma +19
NeurIPS 2023poster

We introduce Alexa Arena, a user-centric simulation platform to facilitate research in building assistive conversational embodied agents. Alexa Arena features multi-room layouts and an abundance of interactable objects. With user-friendly graphics and control mechanisms, the platform supports the de…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2023

GIVL: Improving Geographical Inclusivity of Vision-Language Models With Pre-Training Methods

Da Yin, Feng Gao, Govind Thattai, Michael Johnston, Kai-Wei Chang
CVPR 2023poster

A key goal for the advancement of AI is to develop technologies that serve the needs not just of one group but of all communities regardless of their geographical region. In fact, a significant proportion of knowledge is locally shared by people from certain regions but may not apply equally in othe…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2022

Intent Discovery for Enterprise Virtual Assistants: Applications of Utterance Embedding and Clustering to Intent Mining

Minhua Chen, Badrinath Jayakumar, Michael Johnston, S. Eman Mahmoodi, Daniel Pressel
NAACL 2022industry

A key challenge in the creation and refinement of virtual assistants is the ability to mine unlabeled utterance data to discover common intents. We develop an approach to this problem that combines large-scale pre-training and multi-task learning to derive a semantic embedding that can be leveraged…

Cited by 4Source ↗PDF ↗Scholar ↗
2022

Lightweight Transformers for Conversational AI

Daniel Pressel, Wenshuo Liu, Michael Johnston, Minhua Chen
NAACL 2022industry

To understand how training on conversational language impacts performance of pre-trained models on downstream dialogue tasks, we build compact Transformer-based Language Models from scratch on several large corpora of conversational data. We compare the performance and characteristics of these model…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗