Skip to main content Skip to secondary navigation

Annual Meeting: 2021 AI Safety Hosted by the Stanford Center for AI Safety

Main content start

September 14, 2021
Location: McCaw Hall, Arrillaga Alumni Center
 

Time Agenda Video
8:00 AM Breakfast & Registration  
9:00 AM

Welcome & Overview
Anthony Corso

Youtube
9:10 AM The Role of AI Safety in Human-Robot Interaction
Dorsa Sadigh
Youtube
9:40 AM Safe Perception and Localization Using AI
Grace Pao
Youtube
10:40 AM Break  
11:00 AM Trinity: On Trust, Resilience and Interpretability of AI
Susmit Jha, SRI International
Youtube
11:30 AM Efficient Neural Network Analysis with Sum-of-infeasibilities
Clark Barrett
Youtube
12:00 PM Lunch  
1:20 PM Industry Panel Discussion: AI Safety in Practice
Moderator: Anthony Corso
Youtube
2:00 PM When Models Break: Systematic Understanding of AI Mistakes
James Zou
Youtube
2:30 PM How to Trust Machine Learning
Carlos Guestrin
Youtube
3:00 PM Break  
3:30 PM Knowing the Unknown Unknowns for Safe AI
Ransalu Senanayake
Youtube
4:00 PM Recent Advances in Assured Autonomy at NASA RSE
Ritchie Lee, NASA Ames Research Center
Youtube
4:30 PM Student Spotlight Talks Youtube
5:00 PM Student Poster Session & Reception