Visual symbolic mechanisms: Emergent symbol processing in Vision Language Models

ICLROral2026

Authors: Rim Assouel, Declan Iain Campbell, Yoshua Bengio, Taylor Whittington Webb
Venue: ICLR 2026
Track: Oral

TL;DR

We describe a set of symbolic-like mechanisms that VLMs use to bind to visual entities in context…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

language model

← All ICLR 2026 Oral papers · Browse the whole archive