Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

ICLROral2026

Authors: Junlin Han, Shengbang Tong, David Fan, Yufan Ren, Koustuv Sinha, Philip Torr, Filippos Kokkinos
Affiliation: University of Oxford
Venue: ICLR 2026
Track: Oral

TL;DR

Explore and understand the visual priors within LLMs and thus build better MLLMs.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

pre-training llm

← All ICLR 2026 Oral papers · Browse the whole archive