most citedMitigating Modality Bias in Multi-modal Entity Alignment from a Causal Perspective

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization

Zefeng Zhang, Hengzhu Tang, Jiawei Sheng +6

Multimodal Large Language Models excel in various tasks, yet often struggle with modality bias, where the model tends to rely heavily on a single modality and overlook critical inf…