02/05基于 AutoGen 的数智助手问答架构设计深入探讨基于 AutoGen 框架的多智能体对话系统架构设计，包括意图理解、任务规划及 Deepseek R1 融合方案。# LLM# deep-learning
08/03江苏移动数智助手 Text2SQL 大模型微调实践随着人工智能技术的迅猛发展，企业在数据处理和分析方面的需求也日益增长。为了更高效地从海量数据中提取有用信息，我们在数智助手中进行了Text2SQL微调实践。# LLM# deep-learning
12/09Introducing Intel LLM-on-Ray: A New Era for Large Language ModelsPretrain, finetune and serve LLMs on Intel platforms with Ray distributed framework.# LLM# Intel
11/06高精度图像分割技术回顾回顾高精度图像分割算法发展：从 BASNet 到 U2Net，再到 DIS。探讨 Residual Refine Module 及多尺度融合技术。# deep-learning
03/14强化学习基础（1）强化学习入门：介绍 Agent、Environment、Policy 等基本概念，以及 DQN、Policy Network 和 Actor-Critic 方法。# deep-learning
01/20Let's build GPT: from scratch, in code, spelled out (1)a shocking turn of events a leaf has fallen from a treat in the local park Witnesses report that the leaf which was previously attached to a branch of# LLM# deep-learning
12/13Learn Makefiles (2)Getting Advanced: Targets, Automatic Variables and Wildcards, Fancy Rules# C++
11/21Vtune UsageInstructions Retired per Cycle, or IPC shows average number of retired instructions per cycle. Modern superscalar processors issue up to four instruct# Intel# HPC