FedPivot: Bridging Heterogeneous Multimodal Pre-training via Federated Post-Alignment
The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-quality public data, while vast amounts of heterogeneous multimodal data remain inaccessible in privacy-sensitive silos. Federated Learning (FL) offers a promising solution to leverage these distributed resources w...