Join the Center for AI Safety’s (CAIS) for a bi-weekly Reading and Learning (RAL) event. These meetings serve as a platform to dissect and explore recent publications from the Machine Learning community. Our discussions encompass an array of publications, including papers emerging from CAIS, as well as ones curated from outside institutions. We invite individuals external to CAIS to present their work, fostering a dynamic exchange of ideas and perspectives. To minimize the pressure when preparing the upcoming talk, we won’t ask speakers to prepare slides beforehand (but you are more than welcome to do so).
Subscribe to all RAL events using this link.
RAL Outline
- Part I: Presentation and Short Questions (40 min)
- Part II: Long Questions and Discussion (20 min)
Become a Speaker
We welcome people from universities and the industry to present their work at RAL. We are interested in topics ranging from general AI safety to adversarial robustness, privacy, fairness, interpretability, language models, vision models, multimodality, etc. If you are interested in sharing your work with CAIS and other people, please fill out the following Google Form.
Past Presentations
Universal and Transferable Adversarial Attacks on Aligned Language Models by Andy Zou
AI Deception: A Survey of Examples, Risks, and Potential Solutions by Aidan O’Gara
Contact
If you have any questions, feel free to contact us at long@safe.ai