adaptive-computation topic

(NeurIPS-2019 MicroNet Challenge - 3rd Winner) Open source code for "SIPA: A simple framework for efficient networks"

Lee-Gihun

A curated reading list of research in Adaptive Computation, Dynamic Compute & Mixture of Experts (MoE).

koayon

Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount of time on any token

lucidrains

Exploration into the proposed "Self Reasoning Tokens" by Felipe Bonetto

lucidrains