NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
decision-making processes
4 papers
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity
Skill-Driven Neurosymbolic State Abstractions
Structural Causal Bandits under Markov Equivalence