AI Safety meetup | Station F

​🎉 Join us for the AI Safety Meetup at the iconic STATION F in Paris! 🎉

​This event brings together experts and innovators to discuss critical topics such as the robustness of multi-agent systems, model evaluation, and model poisoning.

​Speakers

• ​Hugo Hernandez (Co-founder of World Game) : Robustness of Multi-Agent Systems

• ​Pierre Peigné (CSO of PRISM Eval): PRISM Eval - Evaluating Model Robustness and Safety

• ​Thomas Winninger (Second-Year Student at Télécom SudParis): Model Poisoning

• ​Pierre Fernandez (Meta & INRIA Rennes): Watermarking

​Schedule

• ​18:30 - 18:50: Presentation by Pierre Fernandez

• ​18:50 - 19:10: Presentation by Pierre Peigné

• ​19:10 - 19:30: Presentation by Thomas Winninger

• ​19:30 - 19:50: Presentation by Hugo Hernandez

• ​19:50 - 21:00: Closing Remarks and Networking

​Limited seats are available, so don't miss this opportunity to be part of a critical discussion on AI safety.

​We look forward to welcoming you to an event that promises to be both informative and engaging, fostering a deeper understanding of the essential aspects of AI safety.