Failures to Find Transferable Image Jailbreaks Between Vision-Language Models</td>
</tr>
| 10:50 am |
Contributing Talk 2: Towards Safe Multilingual Frontier AI |
| 11:00 am |
Poster session & Lunch |
| 12:00 pm |
Lunch break |
| Session 2 |
| 1:00 pm |
Invited talk 3 - Rida Qadri AI's Cultural Futures: Designing for a Culturally Rich World |
| 1:40 pm |
Invited talk 4 - Peter Henderson Aligning Machine Learning and Law for Responsible Real-World Deployments |
| 2:20 pm |
Invited talk 5 - Hannah Rose Kirk A Tale of Two RCTs: Building a rigorous evidence base on the societal impacts of frontier AI inside the UK Government. |
| 3:00 pm |
Break (20 min) |
| 3:20 pm |
Panel: Panelists: Yoshua Bengio, Margaret Mitchell, Jeff Clune, Moderator: Jakob Foerster |
| 4:20 pm |
Contributing Talk 3: Report Cards: Qualitative Evaluation of LLMs Using Natural Language Summaries |
| 4:30 pm |
Contributing Talk 4: An Adversarial Perspective on Machine Unlearning for AI Safety |
| 4:40 pm |
Contributing Talk 5: Targeted Manipulation and Deception Emerge in LLMs Trained on User Feedback |
| 4:50 pm |
Contributing Talk 6: On Demonstration Selection for Improving Fairness in Language Models |
| 5:00 pm |
Closing remarks (10 min) |
</table>