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


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



8:00am Breakfast & Registration
9:00am Welcome & Overview
Anthony Corso
9:10am The Role of AI Safety in Human-robot Interaction
Dorsa Sadigh
9:40am Safe Perception and Localization Using AI
Grace Gao
10:10am Research Update from the Stanford Intelligent Systems Laboratory
Mykel Kochenderfer
10:40am Break
11:00am Trinity: On Trust, Resilience and Interpretability of AI
Susmit Jha, SRI International
11:30am Efficient Neural Network Analysis with Sum-of-infeasibilities
Clark Barrett
12:00pm Lunch
1:20pm Industry Panel Discussion: AI Safety in Practice
Moderator: Anthony Corso
2:00pm When Models Break: Systematic Understanding of AI Mistakes
James Zou
2:30pm How to Trust Machine Learning
Carlos Guestrin
3:00pm Break
3:30pm Knowing the Unknown Unknowns for Safe AI
Ransalu Senanayake
4:00pm Recent Advances in Assured Autonomy at NASA RSE
Ritchie Lee, NASA Ames Research Center
4:30pm Student Spotlight Talks
5:00pm Student Poster Session & Reception