研究人员推出了一种名为持续模型路由（CMR）的新框架，以应对在快速扩展的AI模型中心中管理和更新路由机制所带来的挑战。他们开发了CMRBench，一个包含2000多个模型的超大规模基准测试，以模拟真实的中心增长。所提出的CARvE方法利用对比嵌入，并结合了基于检查点的锚定和结构化重放，在准确性方面，无论是在模型、模型家族还是领域层面，都优于现有的检索、微调和适配器合并方法。 AI
影响 这项研究可能带来更高效、可扩展的AI模型中心管理，从而改进复杂系统中模型的选择和更新。
排序理由 该集群描述了一篇介绍用于AI模型路由的新颖框架和基准测试的研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.28577v1 Announce Type: new Abstract: AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental chall…
AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands …
AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands …