The LLM took an entirely different route, using a formula that was well known in related parts of math, but which no one had thought to apply to this type of question.
大多数人认为数学突破需要全新的理论或方法，但作者认为AI只是将已知公式应用到新领域就能取得突破，这挑战了人们对数学创新本质的理解，暗示创新有时来自于跨领域应用而非全新创造。
The LLM took an entirely different route, using a formula that was well known in related parts of math, but which no one had thought to apply to this type of question.
大多数人认为数学突破需要全新的理论或方法，但AI的解决方案使用了已知公式只是应用到了新领域，这表明创新可能更多来自于跨领域应用而非全新发明，挑战了我们对数学创新本质的理解。
基于 Pre-RoPE 空间的三角函数分析全新 KV Cache 压缩方法
令人惊讶的是：研究人员竟能通过三角函数分析来优化KV Cache压缩，这种跨学科的方法展示了AI创新的多样性。将数学理论与工程实践结合，创造出如此显著的性能提升，体现了基础研究对技术进步的重要推动作用。