–
Coffee and Check-In
–
Welcome and Introductions
–
Propositions as Parameters
Jason Eisner (Johns Hopkins University)
–
Break
–
LLM Generalization in Social Context
Diyi Yang (Stanford University)
–
Lunch (on your own)
–
In-Context Principle Learning from Mistakes
Uri Alon (Google DeepMind)
–
Break
–
LLM Metacognition: Understanding and leveraging "Thinking about Thinking"
Sanjeev Arora (Princeton University)
–
Break
–
Panel: Generalization in NLP
–
Reception
–
Coffee and Check-In
–
Out-of-Distribution Generalization as Reasoning: Are LLMs Competitive?
Les Valiant (Harvard University)
–
Break
–
When calibration goes awry: hallucination in language models
Adam Kalai (OpenAI)
–
Lunch (on your own)
–
Generalization in Diffusion Models Arises from Geometry-Adaptive Harmonic Representations
Zahra Kadkhodaie (New York University)
–
Break
–
How well does diffusion model generate? - A quantification that accounts for both training and sampling
Molei Tao (Georgia Tech), Yuqing Wang (Georgia Institute of Technology)
–
Break
–
Panel: New Theoretical Frameworks for Generalization
–
Coffee and Check-In
–
Robust Generalization in the Era of LLMs: Jailbreaking Attacks and Defenses
Hamed Hassani (University of Pennsylvania)
–
Break
–
The Pitfalls of Next-token Prediction
Vaishnavh Nagarajan (Google)
–
Lunch (on your own)
–
Predictability and Surprise in Language Model Benchmarks
Sanmi Koyejo (Stanford University)
–
Break
–
Human and machine inductive biases for compositional linguistic generalization
Najoung Kim (Boston University)
–
Break
–
Long context modeling and generalization: two perspectives
Amanda Bertsch (Carnegie Mellon University)
–
Coffee and Check-In
–
Generalization from the behavioral perspective
Max Raginsky (University of Illinois at Urbana-Champaign)
–
Break
–
Controlling distribution shifts in language models: a data-centric approach.
Tatsunori Hashimoto (Stanford University)
–
Lunch (on your own)
–
On the Curses of Future and History in Off-policy Evaluation in non-Markov Environments
Nan Jiang (University of Illinois Urbana-Champaign)
–
Break
–
Iterative preference learning methods for large language model post training
Wei Xiong (UIUC)
–
Break
–
Language Model Alignment: Theory & Algorithms
Ahmad Beirami (Google)
–
Coffee and Check-In
–
Unexpected Test Losses from Generalization Theory?
Frederic Koehler (University of Chicago)
–
Break
–
When do dependencies in your data help?
Ankur Moitra (Massachusetts Institute of Technology)
–
Lunch (on your own)
–
Know When You Know: Handling Adversarial Data by Abstaining
Surbhi Goel (University of Pennsylvania)
–
Break
–
Neural Networks meet Nonparametric Regression: Generalization by Weight Decay and Large Learning Rate
Yu-Xiang Wang (UC San Diego)
–
Break
–
Generalization in Robotic Behavior Cloning: Pitfalls and Promises
Max Simchowitz (Carnegie Mellon University)