研究人员开发了一种名为KV-Cache嫁接的新颖技术，可以在不改变权重的情况下增强小型语言模型。该方法允许将已验证的知识以字节精确的方式恢复到推理上下文中，从而在能力和效率方面取得显著改进。例如，Gemma-4-12B模型在AIME 2025基准测试上的性能在嫁接了已验证的解决方案库后，从80.0%提高到93.3%。这种方法还大大减少了token使用量和能耗，使得上下文窗口高达280万token，而无需额外的内存成本。 AI
影响 这项技术可以显著降低小型语言模型的计算成本并增加其有效上下文窗口，从而使先进的AI更易于访问和更高效。
排序理由 该集群描述了一篇详细介绍改进语言模型新技术的最新研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.14431v1 Announce Type: cross Abstract: We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later r…
We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context.…
We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context.…