To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models

ICLROral2026

Authors
Eran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Joshua M. Susskind, Etai Littwin
Affiliation
Apple
Venue
ICLR 2026
Track
Oral

TL;DR

State Space Models (SSMs) have become the leading alternative to Transformers for sequence modeling tasks. Their primary advantage is efficiency in long-context and long-form generation, enabled by fixed-size memory and linear scaling of computational complexity.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

state space model generalization transformer memory

← All ICLR 2026 Oral papers · Browse the whole archive