Distribution-Aware Expert Routing Enables Continual Adaptation of Video Multimodal LLMs
A new framework called Distribution-Aware Expert Routing (DAER) is introduced for adapting video multimodal large language models (Video-MLLMs) to sequentially evolving domains. DAER uses domain-isolated lightweight experts and a distribution-aware routing mechanism to reduce cross-domain interference and catastrophic forgetting, while keeping the pretrained backbone frozen. Experiments on a benchmark of ten diverse video question-answering datasets show that DAER consistently outperforms previous continual learning methods.
Why it matters: This approach advances the robustness and adaptability of video understanding systems in real-world scenarios where data domains change over time.
Full story at: arXiv Computer Vision ↗