PhD Proposal by Arjun Chandrasekaran

Primary tabs

Title: Towards natural human-AI interactions in vision and language


Date: Thursday, November 29 2018

Time: 10:00AM - 11:30AM (ET)

Location: CCB 360B


Arjun Chandrasekaran

Ph.D. Student in Computer Science

School of Interactive Computing 

Georgia Institute of Technology




Dr. Devi Parikh (Advisor, School of Interactive Computing, Georgia Institute of Technology)

Dr. Dhruv Batra (School of Interactive Computing, Georgia Institute of Technology)

Dr. Sonia Chernova (School of Interactive Computing, Georgia Institute of Technology)

Dr. Mohit Bansal (Computer Science Dept., University of North Carolina at Chapel Hill)



Inter-human interaction is a rich form of communication. Human interactions typically leverage a good theory of mind, involve pragmatics, story-telling, humor, sarcasm, empathy, sympathy, etc. Current human-AI interactions, however, lack many of these features that characterize inter-human interactions. Towards the goal of developing AI that can interact with humans naturally (similar to other humans), in this dissertation, I take steps towards studying aspects of humor, story-telling, and theory of (AI's) mind. 

Specifically, I 

1. Build computational models for humor manifested in static images, and contextual, multi-modal humor. 

2. Introduce a picture-sequencing task where a computational model learns the correct temporal order of events in a story. 

3. Evaluate different factors that influence the extent to which a lay person can predict the behavior of an AI, i.e., a person's theory of the AI's mind. 


In proposed work, I will evaluate the extent to which interpretable AI approaches improve the overall performance of a human-AI team in a goal-driven, cooperative task.



  • Workflow Status:
  • Created By:
    Tatianna Richardson
  • Created:
  • Modified By:
    Tatianna Richardson
  • Modified:


Target Audience

    No target audience selected.