当前,像ChatGPT之类的LLM可谓是“风靡全球”。有读者留意到,几乎所有LLM都还是用最初的Multi-Head Scaled-Dot Attention,近年来大量的Efficient工作...| spaces.ac.cn
上一篇文章中,我们对原始的Sinusoidal位置编码做了较为详细的推导和理解,总的感觉是Sinusoidal位置编码是一种“想要成为相对位置编码的绝对位置编码”。一般来说,绝对位置编码具有实现...| spaces.ac.cn
2017年中,有两篇类似同时也是笔者非常欣赏的论文,分别是FaceBook的《Convolutional Sequence to Sequence Learning》和Google的《Atten...| spaces.ac.cn
A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs, and Transformers have specialized variants for capturing long dependencies, they still struggle to scale to very long sequences of $10000$ or more steps. A promising recent approach proposed modeling sequences by simulating the fundamental state space model (...| papers.cool
众所周知,尽管基于Attention机制的Transformer类模型有着良好的并行性能,但它的空间和时间复杂度都是$\mathcal{O}(n^2)$级别的,$n$是序列长度,所以当$n$比较...| spaces.ac.cn
事实上,除了写博客内容,在这几年里,笔者是花了相当一部分时间来做科学空间的“表面功夫”,为此还专门学了一点php、css和js。虽然不敢说精益求精,但总体来说网站的浏览体验应该比前几年要好得多。...| spaces.ac.cn