Balancing Multimodal Training Through Game-Theoretic Regularization

NeurIPSSpotlight2025

Authors
Konstantinos Kontras, Thomas Strypsteen, Christos Chatzichristos, Paul Pu Liang, Matthew B. Blaschko, Maarten De Vos
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Multimodal learning holds the promise for richer information extraction by capturing dependencies across data sources…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

multimodal

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive