研究人员开发了新的“学习延迟”（L2D）系统方法，该系统决定是进行预测还是咨询专家。最新的进展通过允许系统不仅选择专家，还为该专家提供额外的、特定于上下文的信息，从而解决了现有框架中的局限性。新方法还将L2D扩展到同时利用多个专家，使系统能够查询成本效益最高的k个实体或根据输入难度调整专家数量。 AI
影响 学习延迟方面的这些进步可以通过优化专家咨询和实现协作智能，从而带来更高效、更准确的AI系统。
排序理由 该集群包含多篇详细介绍机器学习新研究的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2603.14324v3 Announce Type: replace Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert is fixed at decision time. Many modern systems violate this assumption: after selectin…
arXiv:2604.09414v3 Announce Type: replace Abstract: A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains classifier and router jointly by treating the $K$…
arXiv:2504.12988v5 Announce Type: replace-cross Abstract: Existing Learning-to-Defer (L2D) frameworks are limited to single-expert deferral, forcing each query to rely on only one expert and preventing the use of collective expertise. We introduce the first framework for Top-$k$ …