1
ChatGPT vs Gemini vs Claude: How They Differ
三大AI模型ChatGPT、Gemini、Claude核心差异一图看懂，从自注意力机制到各自架构特点。
In this article, we will look at the various architectural forks the teams building these models encountered and the decisions they took.
2
Plain Transformers are Surprisingly Powerful Link Predictors
普通Transformer在链接预测任务上表现惊人，挑战了图神经网络在该领域的传统认知。
arXiv:2602.01553v2 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture…
3
MiniGPT: Rebuilding GPT from First Principles
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…
4
Residual Stream Duality in Modern Transformer Architectures
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…
5
AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
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…