Tag
The paper provides a formal mathematical framework defining 'any-task inference' (zero-shot capable) foundation models, decomposing them via a universal task reduction into encoder, model, and decoder components and stratifying error into design and realized-model terms, illustrated with five real-world examples.
This paper proposes a formal framework for agent memory, defining memory as a basis, knowledge as its span, and optimality as capacity-constrained expected coverage, while framing continual memory as a sequential MDP and demonstrating the framework on Homer's Odyssey.
This paper presents a formal definition and meta-model for a machine theory of mind, aiming to provide a structured framework for reasoning about others' mental states in artificial intelligence systems.