Schedule
The session will cover invited talks, contributed talks and posters. The tentative schedule in Pacific Time (GMT-7) can be found below. All events take place at Meeting Room 205-207.
| Time | Session | Details |
|---|---|---|
| 8:30 - 8:45 | Welcome Session | Opening remarks and announcement of the best papers by Andreas Krause |
| 8:45-8:55 | Best Paper Award Language Modeling Track | E3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs |
| 8:55-9:05 | Best Paper Award AI for Science Track | A Diffusion Model to Shrink Proteins While Maintaining their Function |
| 9:05-9:15 | Best Paper Award Theory Track | Provably Learning from Language Feedback |
| 9:15-9:25 | Best Paper Award Robotics Track | Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames |
| 9:30-10:00 | Invited Talk | Alison Gopnik |
| 10:00-10:30 | Invited Talk | Sergey Levine: Exploration with Prior Knowledge |
| 10:30-11:00 | Invited Talk | Jeff Clune: Open-Ended and AI-Generating Algorithms in the Era of Foundation Models |
| 11:00-11:45 | Panel Discussion | Led by Andrew Wagenmaker and Parnian Kassraie. Panelists: Jeff Clune, Masatoshi Uehara, Ji Won Park, Aviral Kumar, Kevin Jamieson, Andreas Krause |
| 11:45-14:15 | Poster session and lunch | - |
| 14:15-14:45 | Invited talk | Natasha Jaques: Exploration in Human-AI Cooperation |
| 14:45-15:15 | Invited talk | Dylan Foster: Theoretical Foundations for Exploration with Language Models |
| 15:15-15:45 | Invited talk | Wenhao Yu: Laying the Bricks for Scalable Robot Learning |
| 15:45-16:00 | Coffee break | Sponsored |
| 16:00-16:30 | Invited talk | Masatoshi Uehara: Reward-Guided Generation in Diffusion Models: Toward Programmable Protein Design |
| 16:30-17:00 | Invited talk | Ji Won Park: Targeting the Multivariate Tails in AI-driven Molecular Optimization |
| 17:00-17:15 | Closing remarks | Given by Kevin Jamieson |