expert-distillation

该论文提出 SCOPED（Skill-Decoupled On-Policy Expert Distillation），通过训练能力专属专家并以奖励引导反思提取技能，在在线蒸馏中将程序性知识内化到统一的视觉-语言模型中，从而避免跨能力梯度干扰，并在八个多模态基准上超越骨干模型和混合能力 RL。

The paper introduces Continuous Audio Thinking (CoAT), a framework that equips large audio language models with a continuous latent workspace to organize acoustic information before generating textual responses, improving performance on audio reasoning, understanding, and transcription tasks without additional decoding cost.