Modality-free Graph In-context Alignment

ICLROral2026

Authors
Wei Zhuo, Siqiang Luo
Affiliation
Nanyang Technological University
Venue
ICLR 2026
Track
Oral

TL;DR

A pretraining framework that enables in-context learning on graph-structured data without modality assumptions.

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

in-context learning pretraining alignment graph

← All ICLR 2026 Oral papers · Browse the whole archive