Tentative Program

1. 9:00–10:00 AM
   Arrival, breakfast & networking
2. 10:00–10:10 AM
   Opening remarksEvalScience
3. 10:10–11:30 AM

   Session 1

   Frameworks & Measures

   1. 10:10–10:30 AM
      

      Hanna WallachMicrosoft Research

   2. 10:30–10:50 AM
      

      Olawale SalaudeenUniversity of Illinois Urbana-Champaign

   3. 10:50–11:22 AM

      Lightning talks

      Short talks on accepted papers · See the list →

   11:22–11:30 AMDiscussion

4. 11:30 AM–12:30 PM

   Session 2A

   Benchmarks & Evaluation Infrastructure

   1. 11:30–11:50 AM
      

      Jason WestonMeta · NYU

   2. 11:50 AM–12:22 PM

      Lightning talks

      Short talks on accepted papers · See the list →

   12:22–12:30 PMDiscussion

5. 12:30–1:30 PM
   Lunch & networking
6. 1:30–1:50 PM

   Session 2B · continued

   Benchmarks & Evaluation Infrastructure

   1. 1:30–1:50 PM
      

      Yoav ArtziCornell University/Cornell Tech

      Evaluating Grounded Reasoning

7. 1:50–3:10 PM

   Session 3

   Real-World Systems

   1. 1:50–2:10 PM
      

      Peter HendersonPrinceton University

      Generalization, Jaggedness, and Setting Human Expectations of Model Performance

   2. 2:10–2:30 PM
      

      Nouha DziriCohere Labs

   3. 2:30–3:02 PM

      Lightning talks

      Short talks on accepted papers · See the list →

   3:02–3:10 PMDiscussion

8. 3:10–3:50 PM

   Fireside chat

   What Changes When We Evaluate Agents in the Real World?

   • Ofir PressMeta
   • Rachneet KaurJ.P. Morgan
   • Ida MomennejadMicrosoft Research
   • Saurabh JhaIBM Research
9. 3:50–4:30 PM
   Mentoring, coffee & networkingPoster setup 4:00–4:30 PM
10. 4:30–5:45 PM
    Poster session & reception64 posters in two sessions of 32 · See the poster list →
11. 5:45–6:00 PM
    Closing remarks

All times are Eastern Time. The program remains subject to change as speakers and presentations are confirmed.