Sequences of Logits and The Low Rank Structure of Language Models

Noah Golowich
May 14, 2026

From Generative Models to Control: Representation-based Reinforcement Learning in Physical Systems

Na Li
May 13, 2026

Latent Representations for Control Design with Provable Stability and Safety Guarantees

Stephen Tu
May 13, 2026

Large Language Models and Computation

Dale Schuurmans
May 13, 2026

Learning and control in the presence of observer effects

Sarah Dean
May 13, 2026

Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success

Daniel Russo
May 12, 2026

Some fundamental limitations of learning for dynamics and control

Necmiye Ozay
May 12, 2026

Learning Pipelines for Adaptive Control

Florian Dorfler
May 12, 2026

The Power of Universal Sequence Preconditioning

Annie Marsden
May 12, 2026