Cameron Allen

Truthfulness Despite Weak Supervision: Evaluating and Training LLMs Using Peer Prediction

From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning

Memory as State Abstraction Over History

Generalizing Subgoals from Single Instances using Hypothesis-Preserving Ensembles

Skill-Driven Neurosymbolic State Abstractions

Truthfulness Without Supervision: Model Evaluation Using Peer Prediction

Learning Transferable Sub-goals by Hypothesizing Generalizing Features