AI Dynamics

Global AI News Aggregator

About

Requential Coding Compresses Models With Self-Generated Training Samples

"Requential Coding: Pushing the Limits of Model Compression with Self-Generated Training Data" This paper, Requential Coding, compresses models by coding what they learn, not their weights. So a student trains on samples it generates itself. A teacher then only points out which

→ View original post on X — @askalphaxiv