Unknown Futures of Generalization

Program

Modern Paradigms in Generalization

Location

Calvin Lab Auditorium

Date

Monday, Dec. 2 – Friday, Dec. 6, 2024

Back to calendar

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

Talk By

Florent Krzakala (EPFL Lausanne)

10:15 – 10:45 a.m.

Break

10:45 – 11:30 a.m.

Strong Generalization from Small Brains and No Training Data

Bruno Olshausen (UC Berkeley)

11:30 – 11:45 a.m.

Break

11:45 a.m. – 12:30 p.m.

How machine learning is influencing protein engineering

Jennifer Listgarten (UC Berkeley)

12:30 – 2:15 p.m.

Lunch (on your own)

2:15 – 3 p.m.

Frame-shifting and Conceptual Blending: What do large language models have to say?

Seana Coulson (UC San Diego)

3 – 3:30 p.m.

Break

3:30 – 4:30 p.m.

Richard M. Karp Distinguished Lecture | Po-Ling Loh

Po-Ling Loh (University of Cambridge)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

Temporal Context in Brains and AI

Terry Sejnowski (UC San Diego)

10:15 – 10:45 a.m.

Break

10:45 – 11:30 a.m.

Polymathic AI: Advancing Science through Multidisciplinary AI

Shirley Ho (Flatiron Institute/ NYU)

11:30 – 11:45 a.m.

Break

11:45 a.m. – 12:30 p.m.

Generalization in the representations and computations of frontier language models.

Joshua Batson (Anthropic)

12:30 – 2:15 p.m.

Lunch (on your own)

2:15 – 3:45 p.m.

Panel on the future of scientific research and education

Konrad Kording (University of Pennsylvania),
Florent Krzakala (École polytechnique fédérale de Lausanne),
Shirley Ho (Flatiron Institute/ NYU),
Joshua Batson (Anthropic),
Adam Klivans (UT Austin),
Fanny Yang (ETH Zurich),
Russell Impagliazzo (UC San Diego)

4 – 4:45 p.m.

Welcome Reception

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

First-Person Fairness in Chatbots

Adam Tauman Kalai (Open AI)

10:15 – 10:45 a.m.

Break

10:45 – 11:30 a.m.

Off-the-shelf Algorithmic Stability

Rebecca Willett (University of Chicago)

11:30 – 11:45 a.m.

Break

11:45 a.m. – 12:30 p.m.

Learning Theory of Transformers: Generalization and Optimization of In-Context Learning

Taiji Suzuki (University of Tokyo)

12:30 – 2:15 p.m.

Lunch (on your own)

2:15 – 3 p.m.

The Curious Incident of Developing Artificial General Intelligence

Jimmy Ba (xAI)

3 – 3:45 p.m.

Fireside Chat

Peter Bickel (UC Berkeley)

3:45 – 4 p.m.

Break

4 – 4:45 p.m.

On Memorization of Large Language Models in Logical Reasoning

Chiyuan Zhang (Google Research)

8:30 – 9 a.m.

Coffee and Check-In

9 – 10:10 a.m.

Convex Analysis at Infinity: An Introduction to Astral Space and Fireside Chat

Robert Schapire (Microsoft Research)

9 – 10:10 a.m.

Convex Analysis at Infinity: An Introduction to Astral Space and Fireside Chat

Robert Schapire (Microsoft Research)

10:10 – 10:30 a.m.

Break

10:30 a.m. – 12 p.m.

Debate: Sparks versus Embers

Sebastien Bubeck (Open AI),
Tom McCoy (Yale University),
Anil Ananthaswamy (Simons Institute),
Pavel Izmailov (Anthropic),
Ankur Moitra (MIT)

12 – 2:15 p.m.

Lunch (on your own)

2:15 – 3 p.m.

A New Paradigm for Learning with Distribution Shift

Adam Klivans (University of Texas at Austin)

3 – 3:45 p.m.

Understanding the abilities of AI systems: Memorization, generalization, and points in between

Tom McCoy (Yale University)

3:45 – 4 p.m.

Break

4 – 4:45 p.m.

Weak-to-Strong Generalization

Pavel Izmailov (Anthropic)

9 – 9:30 a.m.

Coffee and Check-In

9:30 – 10:15 a.m.

Generalization insights from actual cognition

Konrad Kording (University of Pennsylvania)

10:15 – 10:45 a.m.

Break

10:45 – 11:30 a.m.

Generalization via analogy in young children and Large Models.

Alison Gopnik (UC Berkeley)

11:30 – 11:45 a.m.

Break

11:45 a.m. – 12:30 p.m.

The Wisdom of the Body Revisited

Ben Recht (UC Berkeley)

12:30 – 2 p.m.

MPG Potluck