2010, 2026 Dropout：均值不变，为何评估输出仍不同 黎 浩然/ 20 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
2010, 2026 Dropout: Why Preserving the Mean Does Not Match Evaluation 黎 浩然/ 20 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
2010, 2026 Xcode 27与CodeQL：构建成功为何扫描失败 黎 浩然/ 20 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
2010, 2026 Xcode 27 and CodeQL: Why a Successful Build Can Still Fail Scanning 黎 浩然/ 20 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 zero_grad：None与零梯度为何更新不同 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 zero_grad: Why None and Zero Gradients Update Differently 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 GitHub星标历史API：少返回为何不等于少扫描 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 GitHub Star History API: Smaller Responses Can Still Mean More Work 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 MSE广播：形状不同为何会把回归拉向均值 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More
1910, 2026 MSE Broadcasting: How a Shape Mismatch Changes Regression 黎 浩然/ 19 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 教程/TUTORIAL, 计算机/COMPUTER/ 0 comments Read More