Building on our prior work on AI agents to think out loud in plain English, we are taking the next step. You will not only see Frogger think out loud using plan English, you will also be able to visually connect which parts of his language correspond to which parts of the game. For e.g, the statement "I am trying to avoid the red truck to the left" will be accompanied by a visual indication of the red truck. While language is instrumental in making black-boxed AI systems explainable to lay users, having a layer of visual correlation makes our approach even more powerful.
ClipLine, a social sharing mobile platform that helps users turn their favorite TV scenes into customized GIFs and instantly share them with their friends and the outside world. Voting up the best GIFs, re-clipping, and following other accounts will also be main features of ClipLine.
PhD Dissertation Defense: Jiachen Yang – Cooperation in Multi-Agent Reinforcement Learning
This seminar examines the collaborative use of personal informatics data.
Neha Kumar will serve a three-year term for the group, which is the premier international society for professionals and academics interested in human-computer interaction.
The two-year fellowship recognizes innovative and promising early-career professors in the Americas who are exploring breakthrough research in computer science or a related field.
The faculty will work at the new National Science Foundation AI Institutes.
GVU Resource Labs
Built for Success
A mobile computing "hackerspace."
Visit the App Lab website
Location: TSRB 333
GVU Prototyping Lab
From Concept to Creation
A rapid prototyping "makerspace."
Visit the Prototyping Lab website
Location: TSRB Basement
Testing Methods and Technology
An adaptable project testing space.
Visit the Usability Lab website
Location: TSRB 216