Location: Room 524B
| Session 1 | |
| 9:20 am | Opening Remarks |
| 9:30 am | Selected Talk 1: Michelle Ding and Jo Kavishe Testing LLMs in a sandbox isn’t responsible. Focusing on community use and needs is. |
| 10:00 am | Invited Talk 1: Yulia Tsvetkov (University of Washington, Associate Professor) Safety and Ethics of Agentic LLMs in Health Domains |
| 10:45 am | Selected Talk 2: Ali Falahati We Are Losing the War for Real Data, It is Time to Mark the Originals |
| 11:15 am | Poster Session |
| 1:00 pm | Lunch break |
| Session 2 | |
| 2:30 pm | Invited Talk 2: David Duvenaud (University of Toronto, Associate Professor) Alignment is Not Enough: Anticipating Post-AGI Power-Seeking by Institutions and States |
| 3:15 pm | Sponsor Talk: Dishank Bansal (AISI) Measuring Sandbagging: Could LLMs be strategically underperforming on our evals? |
| 4:00 pm | Invited Talk 3: Golnoosh Farnadi (McGill University, Assistant Professor) |
| 4:45 pm | Closing remarks (15 min) |