从零复现GPT核心机制，基于PyTorch实现简洁自回归语言模型，AI学习者必读的底层论文教程。
arXiv:2605.17398v1 Announce Type: cross Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive langu…
揭示Transformer残差流不仅是优化通道，更是模型表示核心——两轴视角（序列位置×层深度）重构设计空间，自注意力与残差路径协同新理解。
arXiv:2603.16039v2 Announce Type: replace-cross Abstract: Recent work has made clear that the residual pathway is not mere optimization plumbing; it i…
无需训练的自适应注意力抑制方法，精准移除图像中指定对象并修复背景。
arXiv:2605.15921v1 Announce Type: new Abstract: Object removal aims to eliminate specified objects from images while plausibly inpainting the affected…