Videos from NeurIPS 2025 Workshop on Biosecurity Safeguards for Generative AI

NeurIPS 2025 presentations are now online at https://slideslive.com/neurips-2025.

Last year I wrote about the papers coming out of the Biosecurity Safeguards for Generative AI workshop. I have links to all the papers in that post.

Now all the videos from that workshop are available at https://slideslive.com/neurips-2025/workshop-biosecurity-safeguards-for-generative-ai.

• Zaixi Zhang: Opening remarks

• Eric Xing: AI-Driven Digital Organism

• Megan Blewett: Could AI enable a super pandemic?

• Jian Ma: Learning cellular organization, interaction, and function across scales

• Sheng Lin-Gibson: From Code to Cure: Building Safe Models, Agents, AI-XR Co-scientist to Securely Accelerate Biomedical Innovation

• Russ B. Altman: Mitigation and governance options for AI biosecurity

• Sandy Yao, Girish Patangay: Responsible AI X Bio

• Peter Henderson: The Bubble of Risk: Alignment & Safety Under Adaptation

• Yoshua Bengio: Technical safeguards from epistemically cautious AI: Scientist AI

• Artem Elmuratov: "Biosecurity Safeguards for Generative AI" Workshop

• Contributed Spotlights A

• Contributed Spotlights B

Subscribe now