The Vienna Alignment Workshop brings together current and future research leaders interested in understanding and mitigating potential risks from advanced AI systems. Experts from academia, industry, government, and nonprofit sectors will debate and discuss key current issues in AI safety, including Guaranteed Safe AI & Robustness, Interpretability, and Governance & Evaluations.

As part of the Alignment Workshop Series, the Vienna Alignment Workshop is an invite-only event, with 150+ attendees carefully selected by our program committee. Each session will build on the progress and content from our highly-rated 2023 events in San Francisco and New Orleans (2023). The presentations and panels will highlight recent progress in the field, and be available online on our YouTube channel, creating a comprehensive and accessible repository of high-quality content, also shared via social media.

Following the workshop, the participant-led Monday Unconference will take place to support and foster connections and ideas made during the event.

All ICML attendees are also invited to join the Vienna Alignment Workshop Open Social on Sunday night, right after the event!