$\phi$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

ArXi:2602.22601v2 Announce Type: replace Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance across tasks. While recent continual learning studies have made progress in addressing catastrophic forgetting, the problem of fairness caused the imbalanced data remains largely underexplored.