Task Agnostic Architecture for Algorithm Induction via Implicit Composition

no code implementations • 3 Apr 2024 • Sahil J. Sindhi, Ignas Budvytis

Third, the observation that the main missing component in developing a truly generalised network is an efficient approach for self-consistent input of previously learnt sub-steps of an algorithm and their (implicit) composition during the network's internal forward pass.

In-Context Learning Transformer