Auto-Compressing Networks

NeurIPSOral2025

Authors
Vaggelis Dorovatas, Georgios Paraskevopoulos, Alexandros Potamianos
Affiliation
National Technical University of Athens
Venue
NeurIPS 2025
Track
Oral

TL;DR

Deep neural networks with short residual connections have demonstrated remarkable success across domains, but increasing depth often introduces computational redundancy without corresponding improvements in representation quality. We introduce Auto-Compressing Networks (ACNs), an architectural variant where additive long feedforward connections fro…

Opening excerpt from the authors’ abstract. source

Read the paper

← All NeurIPS 2025 Oral papers · Browse the whole archive