PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization 事件

PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization arXiv:2606.03444v1 Announce Type: new Abstract: Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation. To address these feature conflicts, we introduce \textbf{PRISM}, a novel dual-stream Mixture-of-Experts (MoE) framework that synergizes VFMs via modular specia