AI Theory

Machine learning overlooks robustness to an unknowable future; this paper contrasts reinforcement learning with biological evolution, revealing that ML’s formalisms limit engagement with unknown unkno…

Machine learning models can enable secure computations previously impossible with cryptography, achieving privacy and efficiency in Trusted Capable Model Environments (TCMEs).

Game-theoretic LLMs: Agent Workflow for Negotiation Games enhances large language model (LLM) rationality in strategic decision-making through novel game-theoretic workflows.

A new lossy compression framework handles reconstruction distribution divergence by integrating a bottleneck, extending minimum entropy coupling and offering guaranteed performance.