[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-junfanz1--Awesome-AI-Review":3,"tool-junfanz1--Awesome-AI-Review":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":70,"readme_en":71,"readme_zh":72,"quickstart_zh":73,"use_case_zh":74,"hero_image_url":75,"owner_login":76,"owner_name":77,"owner_avatar_url":78,"owner_bio":79,"owner_company":80,"owner_location":81,"owner_email":82,"owner_twitter":83,"owner_website":84,"owner_url":85,"languages":86,"stars":87,"forks":88,"last_commit_at":89,"license":86,"difficulty_score":90,"env_os":91,"env_gpu":91,"env_ram":91,"env_deps":92,"category_tags":95,"github_topics":86,"view_count":23,"oss_zip_url":86,"oss_zip_packed_at":86,"status":16,"created_at":96,"updated_at":97,"faqs":98,"releases":99},2864,"junfanz1\u002FAwesome-AI-Review","Awesome-AI-Review","Awesome AI industry & research review","Awesome-AI-Review 是一个专注于人工智能行业前沿与学术研究的精选知识库。面对 AI 领域技术迭代极快、信息碎片化严重的挑战，它通过系统性地整理顶级会议（如 2025 NVIDIA GTC、Agentic AI Summit）、核心论文解读及实战项目，帮助从业者高效捕捉关键技术趋势。\n\n该资源库内容覆盖广泛且深入，不仅包含大语言模型（LLM）理论、RAG 检索增强生成、多智能体（Multi-Agent）架构等核心技术指南，还特别收录了 DeepSeek、Kimi 等新兴模型的深度解析。此外，它独具特色地融合了量化金融与高频交易领域的 AI 应用，提供了从系统设计面试到 C++ 衍生品定价的跨学科资料，填补了纯算法研究与工程落地之间的空白。\n\nAwesome-AI-Review 非常适合 AI 工程师、算法研究人员、量化分析师以及计算机专业的学生使用。对于希望快速掌握 2025 年最新技术动态（如 SGLang 推理优化、Agentic RL 方向）的开发者，或是准备相关领域面试的求职者，这里提供了一条清晰的学习路径。它不仅仅是一份文档列表，更是一座连接学术前沿与工业实践的","Awesome-AI-Review 是一个专注于人工智能行业前沿与学术研究的精选知识库。面对 AI 领域技术迭代极快、信息碎片化严重的挑战，它通过系统性地整理顶级会议（如 2025 NVIDIA GTC、Agentic AI Summit）、核心论文解读及实战项目，帮助从业者高效捕捉关键技术趋势。\n\n该资源库内容覆盖广泛且深入，不仅包含大语言模型（LLM）理论、RAG 检索增强生成、多智能体（Multi-Agent）架构等核心技术指南，还特别收录了 DeepSeek、Kimi 等新兴模型的深度解析。此外，它独具特色地融合了量化金融与高频交易领域的 AI 应用，提供了从系统设计面试到 C++ 衍生品定价的跨学科资料，填补了纯算法研究与工程落地之间的空白。\n\nAwesome-AI-Review 非常适合 AI 工程师、算法研究人员、量化分析师以及计算机专业的学生使用。对于希望快速掌握 2025 年最新技术动态（如 SGLang 推理优化、Agentic RL 方向）的开发者，或是准备相关领域面试的求职者，这里提供了一条清晰的学习路径。它不仅仅是一份文档列表，更是一座连接学术前沿与工业实践的桥梁，让用户能在纷繁复杂的信息中精准定位高价值内容，提升学习与研发效率。","\n\u003C!-- TOC -->\u003Ca name=\"ai-ml-cs-quant-readings-notes\">\u003C\u002Fa>\n\n\u003Cdiv align=\"left\">\n  \u003Cmarquee behavior=\"alternate\" scrollamount=\"3\">\n    \u003Cstrong>Views:\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_81eafa504aea.png\" alt=\"Profile Views\" \u002F>\n     • \n    \u003Cstrong>Followers:\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Ffollowers\u002Fjunfanz1?style=social\" alt=\"GitHub Followers\" \u002F>\n     • \n    \u003Cstrong>Stars:\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review?style=social\" alt=\"Repository Stars\" \u002F>\n  \u003C\u002Fmarquee>\n\u003C\u002Fdiv>\n\n\n# Awesome AI Engineer Review\n\nAwesome AI industry & research review.\n  - \u003Cmark>[__2025 NVIDIA GTC Conference − Technical & Industrial Insight__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Review\" alt=\"GitHub Stars\" \u002F>\n  - \u003Cmark>[__2025 Agentic AI Summit Berkeley − Technical & Industrial Insight__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FAgentic%20AI%20Summit\u002FAgentic%20AI%20Summit%20Berkeley%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub Stars\" \u002F>\n\n\u003C!-- TOC -->\u003Ca name=\"contents\">\u003C\u002Fa>\n## Contents\n\u003C!-- TOC start (generated with https:\u002F\u002Fgithub.com\u002Fderlin\u002Fbitdowntoc) -->\n\n- [1. NVIDIA GTC | AI Conference for Developers](#1-nvidia-gtc-ai-conference-for-developers)\n- [2. Agentic AI Summit](#2-agentic-ai-summit)\n- [3. LLM Essentials](#3-llm-essentials)\n   * [LLM Theory](#llm-theory)\n   * [LLM Applications](#llm-applications)\n   * [RAG](#rag)\n   * [Multi-Agent](#multi-agent)\n- [4. DeepSeek & Kimi ](#4-deepseek-kimi)\n   * [Research Implementation](#research-implementation)\n   * [DeepSeek Theory](#deepseek-theory)\n   * [DeepSeek Applications](#deepseek-applications)\n   * [Kimi K2](#kimi-k2)\n- [5. 2025 Paper Reading](#5-2025-paper-reading)\n   * [SGLang x NVIDIA: Dynamo for Inference Performance at Scale](#sglang-x-nvidia-dynamo-for-inference-performance-at-scale)\n   * [Jason Wei: 3 Ideas to Understand AI in 2025](#jason-wei-3-ideas-to-understand-ai-in-2025)\n   * [World Model: 5 Debates Between Eric Xing's PAN & Yann LeCun’s JEPA](#world-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa)\n   * [30 Takeaways from Shunyu Yao's Talk on Agentic AI](#30-takeaways-from-shunyu-yaos-talk-on-agentic-ai)\n   * [Building Web Agents](#building-web-agents)\n   * [Future of AI Agents = Agentic RL + Pretraining?](#future-of-ai-agents-agentic-rl-pretraining)\n   * [HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution](#hiva-self-organized-hierarchical-variable-agent-via-goal-driven-semantic-topological-evolution)\n- [6. LangGraph & Cursor AI Projects](#6-langgraph-cursor-ai-projects)\n- [7. System Design](#7-system-design)\n   * [ByteByteGo - GenAI\u002FML\u002FModern System Design Interview](#bytebytego-genaimlmodern-system-design-interview)\n   * [Educative - GenAI\u002FModern System Design Interview](#educative-genaimodern-system-design-interview)\n- [8. Computer Systems](#8-computer-systems)\n- [9. Big Data and AI in Finance, Econometrics and Statistics Conference, UChicago 2024](#9-big-data-and-ai-in-finance-econometrics-and-statistics-conference-uchicago-2024)\n- [10. C++ Design Patterns and Derivatives Pricing](#10-c-design-patterns-and-derivatives-pricing)\n- [11. High-Frequency Finance](#11-high-frequency-finance)\n- [12. Machine Learning for Algorithmic Trading](#12-machine-learning-for-algorithmic-trading)\n- [13. Stochastic Volatility Modeling](#13-stochastic-volatility-modeling)\n- [14. Quant Job Interview Questions](#14-quant-job-interview-questions)\n   * [Star History](#star-history)\n\n\u003C!-- TOC end -->\n\n---\n\n\u003C!-- TOC -->\u003Ca name=\"1-nvidia-gtc-ai-conference-for-developers\">\u003C\u002Fa>\n# 1. NVIDIA GTC | AI Conference for Developers\n\n> \u003Cmark>[__2025 NVIDIA GTC Conference − Technical & Industrial Insight__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub Stars\" \u002F>\n\n> [__GTC 2024 Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202024.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_f3896d493ac5.png\" width=\"80%\" height=\"80%\">\n\n\u003C!-- TOC -->\u003Ca name=\"2-agentic-ai-summit\">\u003C\u002Fa>\n# 2. Agentic AI Summit\n\n> \u003Cmark>[__2025 Agentic AI Summit Berkeley − Technical & Industrial Insight__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FAgentic%20AI%20Summit\u002FAgentic%20AI%20Summit%20Berkeley%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub Stars\" \u002F>\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_269bc9626558.png\" width=\"80%\" height=\"80%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"3-llm-essentials\">\u003C\u002Fa>\n# 3. LLM Essentials\n\n\u003C!-- TOC -->\u003Ca name=\"llm-theory\">\u003C\u002Fa>\n## LLM Theory\n\nDive into DeepSeek LLM, by Xiaojing Ding, 2025 \n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FDive%20into%20DeepSeek%20LLM.md)\n\nDeepSeek Large Model High-Performance Core Technology and Multimodal Fusion Development, by Xiaohua Wang, 2025 \n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FDeepSeek%20Large%20Model.md)\n\nEfficient Training in PyTorch, by Ailing Zhang, 2024\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FEfficient%20Training%20PyTorch.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_ab00e0921860.png\" width=\"34%\" height=\"34%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_8de628d774f8.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_6ff925d0f793.png\" width=\"32%\" height=\"32%\">\n\n---\n\nGenerative AI on AWS, by Chris Fregly, 2024\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FGenerative%20AI%20on%20AWS.md)\n\nLLM from Theory to Practice, by Qi Zhang, 2024\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FLLM%20from%20Theory%20to%20Practice.md)\n\nLangChain Scalable LLM Apps, by Teli Li, 2024\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FLangChain%20Scalable%20LLM%20Apps.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_266498c2136b.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_c2b2a6ffcd81.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_89a7a5033e43.png\" width=\"31%\" height=\"31%\">\n\n---\n\nFoundations of LLMs - by Yuren Mao, Zhejiang University, 2024\n\n> [Course Github](https:\u002F\u002Fgithub.com\u002FZJU-LLMs\u002FFoundations-of-LLMs) | [Course Video](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1PB6XYFET2) | [Textbook](https:\u002F\u002Fgithub.com\u002FZJU-LLMs\u002FFoundations-of-LLMs\u002Fblob\u002Fmain\u002F%E3%80%8A%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9F%BA%E7%A1%80%E3%80%8B%E6%95%99%E6%9D%90\u002F%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9F%BA%E7%A1%80%20%E5%AE%8C%E6%95%B4%E7%89%88.pdf) | [__PDF Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002F%E6%B5%99%E5%A4%A7%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AF%BE%E7%AC%94%E8%AE%B0.pdf)\n\n30 Essential Questions and Answers on Machine Learning and AI - by Sebastian Raschka, 2025\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002F30%20ML%20AI.md)\n\nUnveiling Large Model, by Liang Wen, 2025\n\n> [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FUnveiling%20Large%20Model.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_00575a887f12.png\" width=\"30%\" height=\"30%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_2715c66f81e0.png\" width=\"34%\" height=\"34%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_037bc7da1863.png\" width=\"34%\" height=\"34%\">\n\n---\n\n> [GeekBang: AI LLM Practice](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100770601) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20LLM%20Practice.md)\n\n> [GeekBang: AI LLM System](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Farticle\u002F852628) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20System.md)\n\n\u003C!-- TOC -->\u003Ca name=\"llm-applications\">\u003C\u002Fa>\n## LLM Applications\n\n> [GeekBang: AI LLM Project Implementation](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Farticle\u002F801454) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FLLM%20Project.md)\n\n> [GeekBang: LLM App Developmenmt](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100764201) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FLLM%20App.md)\n\n\u003C!-- TOC -->\u003Ca name=\"rag\">\u003C\u002Fa>\n## RAG\n\n> [Educative: Advanced RAG Techniques - Choosing the Right Approach](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002Fpg03nJFvpmPgN4W0Zuxy07pVPro3h2) | [__Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAdvanced%20RAG.md)\n\n> [GeekBang: RAG Development](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100804101?tab=catalog) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fedit\u002Fmain\u002FAI%20LLM\u002FRAG.md)\n\n\u003C!-- TOC -->\u003Ca name=\"multi-agent\">\u003C\u002Fa>\n## Multi-Agent\n\n> [Educative: Build AI Agents and Multi-Agent Systems with CrewAI](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002Fk5m3gACoj1xDYoOq7c0Kjk4y2AoGTn) | [__Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FCrewAI.md)\n\n> [GeekBang: AI Agents](https:\u002F\u002Ftime.geekbang.org\u002Fcourse\u002Fintro\u002F100775901?tab=catalog) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20Agent.md)\n\n\n\n\u003C!-- TOC -->\u003Ca name=\"4-deepseek-kimi\">\u003C\u002Fa>\n# 4. DeepSeek & Kimi \n\n\u003C!-- TOC -->\u003Ca name=\"research-implementation\">\u003C\u002Fa>\n## Research Implementation\n\n> [Github: Mixture-of-Experts (MoE) Implementation in PyTorch](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FMoE-Mixture-of-Experts)\n\n> [Github: MiniGPT-and-DeepSeek-MLA-Multi-Head-Latent-Attention](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FDeepSeek-MLA)\n\n\u003C!-- TOC -->\u003Ca name=\"deepseek-theory\">\u003C\u002Fa>\n## DeepSeek Theory\n\n> [Educative: Everything You Need to Know About DeepSeek](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FGZjlABCqZ1G2n7mWjuroy1MXK2GBIm) | [__Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Essentials.md)\n\n> [Zomi-Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F517221395\u002Fupload\u002Fvideo) | [Github](https:\u002F\u002Fgithub.com\u002Fchenzomi12\u002FAIFoundation\u002F) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Theory.md)\n\n\u003C!-- TOC -->\u003Ca name=\"deepseek-applications\">\u003C\u002Fa>\n## DeepSeek Applications\n\n> [GeekBang: DeepSeek HandsOn](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002F101000501) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20HandsOn.md)\n\n> [GeekBang: DeepSeek App Development](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100995901) | [__Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Developer%20Practice.md)\n\n\u003C!-- TOC -->\u003Ca name=\"kimi-k2\">\u003C\u002Fa>\n## Kimi K2\n\n> [Kimi K2](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FDeepSeek\u002FKimi%20K2.md) | [🚀 Understand Kimi K2 in 10 Minutes](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Funderstand-kimi-k2-10-minutes-jf-ai-vnsqc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"5-2025-paper-reading\">\u003C\u002Fa>\n# 5. 2025 Paper Reading\n\n## Frontier of Agentic AI: Agent Memory\n\n> [🚀 Frontier of Agentic AI: Agent Memory — Key Takeaways](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAwesome-AI-Engineer-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FFrontier%20of%20Agentic%20AI:%20Agent%20Memory.md) | [LinkedIn: 🚀 Frontier of Agentic AI: Agent Memory — Key Takeaways](https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Fjunfan-zhu_agent-memory-activity-7380113422757277696-oaAc?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8)\n\n\u003C!-- TOC -->\u003Ca name=\"sglang-x-nvidia-dynamo-for-inference-performance-at-scale\">\u003C\u002Fa>\n## SGLang x NVIDIA: Dynamo for Inference Performance at Scale\n\n> [🚀 Insights from SGLang x NVIDIA: Dynamo for Inference Performance at Scale](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAwesome-AI-Engineer-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FSGLang%20Dynamo.md) | [LinkedIn: 🚀 Insights from sgl-project x NVIDIA: #Dynamo for Inference Performance at Scale](https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Fjunfan-zhu_dynamo-sanfrancisco-ai-activity-7379780254493569024-pEBC?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8)\n\n\u003C!-- TOC -->\u003Ca name=\"jason-wei-3-ideas-to-understand-ai-in-2025\">\u003C\u002Fa>\n## Jason Wei: 3 Ideas to Understand AI in 2025\n\n> [Jason Wei: 3 Ideas to Understand AI in 2025](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FJason%20Wei%3A%203%20Ideas%20to%20Understand%20AI%20in%202025.md) | [LinkedIn: Jason Wei: 3 Ideas to Understand AI in 2025](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F06-jason-weis-3-ideas-understand-ai-2025-jf-ai-v7rgc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"world-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa\">\u003C\u002Fa>\n## World Model: 5 Debates Between Eric Xing's PAN & Yann LeCun’s JEPA\n\n> [World Models](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FWorld%20Models.md) | [LinkedIn: World Model: 5 Debates Between Eric Xing's PAN & Yann LeCun’s JEPA](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fworld-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa-jf-ai-8xigc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"30-takeaways-from-shunyu-yaos-talk-on-agentic-ai\">\u003C\u002Fa>\n## 30 Takeaways from Shunyu Yao's Talk on Agentic AI\n\n> [Shunyu Yao on Agentic AI](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FShunyu%20Yao%20Agentic%20AI.md) | [LinkedIn: 30 Takeaways from Shunyu Yao's Talk on Agentic AI](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F30-takeaways-from-shunyu-yaos-talk-agentic-ai-jf-ai-dqz6c)\n\n\u003C!-- TOC -->\u003Ca name=\"building-web-agents\">\u003C\u002Fa>\n## Building Web Agents\n\n> [Building Web Agents](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FBuilding%20Web%20Agents.md) | [LinkedIn: Building Web Agents](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fbuilding-web-agents-jf-ai-khjic)\n\n\u003C!-- TOC -->\u003Ca name=\"future-of-ai-agents-agentic-rl-pretraining\">\u003C\u002Fa>\n## Future of AI Agents = Agentic RL + Pretraining?\n\n> [Future of AI Agents = Agentic RL + Pretraining?](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FFuture%20of%20AI%20Agents%20%3D%20Agentic%20RL%20%2B%20Pretraining%3F.md) | [LinkedIn: Future of AI Agents = Agentic RL + Pretraining?](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Ffuture-ai-agents-agentic-rl-pretraining-jf-ai-p0nlc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"hiva-self-organized-hierarchical-variable-agent-via-goal-driven-semantic-topological-evolution\">\u003C\u002Fa>\n## HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution\n\n> [HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FHiVA:%20Self-organized%20Hierarchical%20Variable%20Agent%20via%20Goal-driven%20Semantic-Topological%20Evolution.md) | [LinkedIn: Co-Evolutionary Path Towards Organizational Intelligence: How Structure-as-Memory Network & Multi-Agent Emergence Could Unlock AGI?](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F07-co-evolutionary-path-towards-organizational-intelligence-how-kpqjc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"6-langgraph-cursor-ai-projects\">\u003C\u002Fa>\n# 6. LangGraph & Cursor AI Projects\n\n> [__Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FLangChain\u002FProjects.md)\n- [Ed Donner: LLM Engineering: Master AI, Large Language Models & Agents](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fllm-engineering-master-ai-and-large-language-models)\n- [Eden Marco: LangChain-Develop LLM powered applications with LangChain](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Flangchain\u002F)\n- [Eden Marco: LangGraph-Develop LLM powered AI agents with LangGraph](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Flanggraph)\n- [Eden Marco: Cursor Course: FullStack development with Cursor AI Copilot](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fcursor-ai-ide\u002F)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_6ed6e55e37d6.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_a7cc0031210c.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_31086c3ec9ea.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_cd9abf875c9a.png\" width=\"20%\" height=\"20%\">\n\n> GitHub Projects\n\n- [MCP-MultiServer-Interoperable-Agent2Agent-LangGraph-AI-System](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FMCP-Servers)\n- [Code-Interpreter-ReAct-LangChain-Agent](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCode-Interpreter-ReAct-LangChain-Agent)\n- [LLM-Documentation-Chatbot](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FLLM-Documentation-Chatbot)\n- [Cognito-LangGraph-RAG](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCognito-LangGraph-RAG)\n- [LangGraph-Reflection-Researcher](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FLangGraph-Reflection-Researcher)\n- [Cursor-FullStack-AI-App](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCursor-FullStack-AI-App)\n\n\n\n\n\u003C!-- TOC -->\u003Ca name=\"7-system-design\">\u003C\u002Fa>\n# 7. System Design\n\n\u003C!-- TOC -->\u003Ca name=\"bytebytego-genaimlmodern-system-design-interview\">\u003C\u002Fa>\n## ByteByteGo - GenAI\u002FML\u002FModern System Design Interview\n\nSystem Design Interview, An Insider's Guide, Second Edition - by Alex Xu, 2020\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FSystem-Design-Interview-insiders-Second\u002Fdp\u002FB08CMF2CQF) | [__PDF Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FSystem%20Design\u002FNotes%20on%20System%20Design.pdf)\n\nGenerative AI System Design Interview - by Ali Aminian, Hao Sheng, 2024\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-System-Design-Interview\u002Fdp\u002F1736049127) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FSystem%20Design\u002FGenAI%20System%20Design%20Interview.md)\n\nMachine Learning System Design Interview - by Ali Aminian, Alex Xu, 2023\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-System-Design-Interview\u002Fdp\u002F1736049127) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FSystem%20Design\u002FML%20System%20Design%20Interview.md)\n\n\u003Cdiv style=\"display: flex; justify-content: space-around;\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_4a4f4ee674ea.png\" width=\"28.6%\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_23060cd714af.png\" width=\"30%\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_72e44ae7b2c3.png\" width=\"30%\">\n\u003C\u002Fdiv>\n\n\u003C!-- TOC -->\u003Ca name=\"educative-genaimodern-system-design-interview\">\u003C\u002Fa>\n## Educative - GenAI\u002FModern System Design Interview\n\n> [Educative - Grokking System Design Interview](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FB86jYxWPP3JhA8lAZw0B2Mhr92YjJNmG5Ty) | [__PDF Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCS-Online-Course-Notes\u002Fblob\u002Fmain\u002FGrokking%20the%20System%20Design%20Interview\u002FGrokking%20the%20System%20Design%20Interview.pdf) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCS-Online-Course-Notes\u002Fblob\u002Fmain\u002FGrokking%20the%20System%20Design%20Interview\u002FGrokking%20the%20System%20Design%20Interview.md)\n\n> [Educative - Grokking the Modern System Design Interview](https:\u002F\u002Fwww.educative.io\u002Fcourses\u002Fgrokking-the-system-design-interview) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Overview\u002Fblob\u002Fmain\u002FSystem%20Design\u002FModern%20System%20Design.md)\n\n> [Educative - GenAI System Design](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FRgxzXQFQkKyYgKrGjTX1RQpE9J3vT6) | [__Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FSystem%20Design\u002FGenAI%20System%20Design.md)\n\n\u003C!-- TOC -->\u003Ca name=\"8-computer-systems\">\u003C\u002Fa>\n# 8. Computer Systems\n\n计算机底层的秘密，陆小风 - 2023，电子工业出版社\n\n> [Book Link](https:\u002F\u002Fbook.douban.com\u002Fsubject\u002F36370606\u002F) | [__PDF Notes-Chinese__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FComputer%20Systems\u002FNotes%20on%20Computer%20Systems%20-%20Chinese.pdf)\n  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_3a77babd4a79.png\" width=\"35%\" height=\"35%\">\n\n\u003C!-- TOC -->\u003Ca name=\"9-big-data-and-ai-in-finance-econometrics-and-statistics-conference-uchicago-2024\">\u003C\u002Fa>\n# 9. Big Data and AI in Finance, Econometrics and Statistics Conference, UChicago 2024\n\nBDAI Conference, 2024 Oct 3-5, UChicago\n\n> [Abstract PDF](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBDAI-2024%20Abstracts.pdf) | [Agenda PDF](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBDAI-2024%20Program.pdf) | [__High Level Overview Notes PDF__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBig_Data_Finance_Conference_High_Level_Overview.pdf) | [__Conference Review Notes PDF__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBig_Data_Finance_Conference_Notes.pdf) \n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_b76811a97050.png\" width=\"50%\" height=\"50%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"10-c-design-patterns-and-derivatives-pricing\">\u003C\u002Fa>\n# 10. C++ Design Patterns and Derivatives Pricing\n\nC++ Design Patterns and Derivatives Pricing (Mathematics, Finance and Risk, Series Number 2) 2nd Edition, by M. S. Joshi\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FPatterns-Derivatives-Pricing-Mathematics-Finance\u002Fdp\u002F0521721628) | [__PDF Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing.pdf) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_53a2e5b6ca48.png\" width=\"30%\" height=\"30%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"11-high-frequency-finance\">\u003C\u002Fa>\n# 11. High-Frequency Finance\n\nAn Introduction to High-Frequency Finance, by Ramazan Gençay, et al.\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FIntroduction-High-Frequency-Finance-Ramazan-Gen%C3%A7ay\u002Fdp\u002F0122796713) | [__PDF Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FAn%20Intro%20to%20High-Frequency%20Finance\u002FNotes%20on%20An%20Introduction%20to%20High-Frequency%20Finance.pdf) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FAn%20Intro%20to%20High-Frequency%20Finance\u002FAn%20Introduction%20to%20High-Frequency%20Financ.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_e21427ed7a4c.png\" width=\"30%\" height=\"30%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"12-machine-learning-for-algorithmic-trading\">\u003C\u002Fa>\n# 12. Machine Learning for Algorithmic Trading\n\nMachine Learning for Algorithmic Trading: Predictive models to extract signals from market and alternative data for systematic trading strategies with Python, 2nd Edition Paperback – by Stefan Jansen 2020 \n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-Algorithmic-Trading-alternative\u002Fdp\u002F1839217715) | [__PDF Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FML%20for%20Algorithmic%20Trading\u002FNotes%20on%20Machine%20Learning%20for%20Algorithmic%20Trading.pdf) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FML%20for%20Algorithmic%20Trading\u002FNotes%20on%20Machine%20Learning%20for%20Algorithmic%20Trading.md)\n\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_1993469acebc.png\" width=\"30%\" height=\"30%\">\n\n\u003C!-- TOC -->\u003Ca name=\"13-stochastic-volatility-modeling\">\u003C\u002Fa>\n# 13. Stochastic Volatility Modeling\n\nStochastic Volatility Modeling (Chapman and Hall\u002FCRC Financial Mathematics Series) 1st Edition, by Lorenzo Bergomi\n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FStochastic-Volatility-Modeling-Financial-Mathematics\u002Fdp\u002F1482244063) | [__PDF Char 1 Intro__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%201%20Introduction%20Notes.pdf) | [__Markdown Char 1 Intro__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%201%20Introduction%20Notes.md) | [__PDF Char 2 Local Vol__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%202%20Local%20Volatility%20Notes.pdf) | [__Markdown Char 2 Local Vol__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%202%20Local%20Volatility%20Notes.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_2dc98e9fdcbd.png\" width=\"30%\" height=\"30%\">\n\n\u003C!-- TOC -->\u003Ca name=\"14-quant-job-interview-questions\">\u003C\u002Fa>\n# 14. Quant Job Interview Questions\n\nQuant Job Interview Questions and Answers (Second Edition) – by Mark Joshi 2013 \n\n> [Book Link](https:\u002F\u002Fwww.amazon.com\u002FQuant-Interview-Questions-Answers-Second\u002Fdp\u002F0987122827) | [__Markdown Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FQuant%20Essentials%20Takeaways.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_4f9e9739d684.png\" width=\"30%\" height=\"30%\">\n\n- [__Cloud Platform Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FCloud.pdf) | [__Quant Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FQuant.pdf) | [__FX Exotic Derivatives Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FFX%20Exotic%20Derivatives.pdf) | [__Risk Methodologies Notes__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FRisk%20Methodologies.pdf)\n\n\n---\n\n\u003Cdiv align=\"left\">\n  \u003Cmarquee behavior=\"alternate\" scrollamount=\"3\">\n    \u003Cstrong>Connect with me:\u003C\u002Fstrong>\n     \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjunfanz1\">GitHub\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.overleaf.com\u002Fread\u002Fjcgfkzhyfvdv#57139d\">Resume\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fjunfan-zhu\u002F\">LinkedIn\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fx.com\u002Fjunfanzhu98\">X\u003C\u002Fa> •\n    \u003Ca href=\"mailto:junfanzhu98@gmail.com\">Email\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.instagram.com\u002Fjunfan_zhu\u002F\">Instagram\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.facebook.com\u002Fjunfan.zhu.961\u002F\">Facebook\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.douban.com\u002Fpeople\u002Fjunfanz\u002F\">Douban\u003C\u002Fa> •\n    \u003Ca href=\"junfanzhu98\">WeChat\u003C\u002Fa>\n  \u003C\u002Fmarquee>\n\u003C\u002Fdiv>\n\n\u003C!-- TOC -->\u003Ca name=\"star-history\">\u003C\u002Fa>\n## Star History\n\n[![Star History Chart](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_827877a55bcb.png)](https:\u002F\u002Fwww.star-history.com\u002F#junfanz1\u002FAI-LLM-ML-CS-Quant-Readings&Date)\n\n","\u003C!-- 目录 -->\u003Ca name=\"ai-ml-cs-quant-readings-notes\">\u003C\u002Fa>\n\n\u003Cdiv align=\"left\">\n  \u003Cmarquee behavior=\"alternate\" scrollamount=\"3\">\n    \u003Cstrong>浏览量：\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_81eafa504aea.png\" alt=\"个人主页浏览量\" \u002F>\n     • \n    \u003Cstrong>关注者：\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Ffollowers\u002Fjunfanz1?style=social\" alt=\"GitHub关注者\" \u002F>\n     • \n    \u003Cstrong>星标数：\u003C\u002Fstrong>\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review?style=social\" alt=\"仓库星标数\" \u002F>\n  \u003C\u002Fmarquee>\n\u003C\u002Fdiv>\n\n\n# 强大的AI工程师综述\n\n强大的AI行业与研究综述。\n  - \u003Cmark>[__2025年英伟达GTC大会——技术与产业洞察__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Review\" alt=\"GitHub星标数\" \u002F>\n  - \u003Cmark>[__2025年伯克利代理型AI峰会——技术与产业洞察__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FAgentic%20AI%20Summit\u002FAgentic%20AI%20Summit%20Berkeley%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub星标数\" \u002F>\n\n\u003C!-- 目录 -->\u003Ca name=\"contents\">\u003C\u002Fa>\n## 目录\n\u003C!-- 目录开始（由https:\u002F\u002Fgithub.com\u002Fderlin\u002Fbitdowntoc生成） -->\n\n- [1. 英伟达GTC | 面向开发者的AI大会](#1-nvidia-gtc-ai-conference-for-developers)\n- [2. 代理型AI峰会](#2-agentic-ai-summit)\n- [3. LLM基础](#3-llm-essentials)\n   * [LLM理论](#llm-theory)\n   * [LLM应用](#llm-applications)\n   * [RAG](#rag)\n   * [多智能体](#multi-agent)\n- [4. DeepSeek与Kimi](#4-deepseek-kimi)\n   * [研究实现](#research-implementation)\n   * [DeepSeek理论](#deepseek-theory)\n   * [DeepSeek应用](#deepseek-applications)\n   * [Kimi K2](#kimi-k2)\n- [5. 2025年论文阅读](#5-2025-paper-reading)\n   * [SGLang x 英伟达：用于大规模推理性能的Dynamo](#sglang-x-nvidia-dynamo-for-inference-performance-at-scale)\n   * [Jason Wei：理解2025年AI的三个思路](#jason-wei-3-ideas-to-understand-ai-in-2025)\n   * [世界模型：Eric Xing的PAN与Yann LeCun的JEPA之间的五个争论点](#world-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa)\n   * [Shunyu Yao关于代理型AI演讲的30个要点](#30-takeaways-from-shunyu-yaos-talk-on-agentic-ai)\n   * [构建Web智能体](#building-web-agents)\n   * [AI智能体的未来 = 代理型强化学习 + 预训练吗？](#future-of-ai-agents-agentic-rl-pretraining)\n   * [HiVA：通过目标驱动的语义拓扑进化自组织的分层可变智能体](#hiva-self-organized-hierarchical-variable-agent-via-goal-driven-semantic-topological-evolution)\n- [6. LangGraph与Cursor AI项目](#6-langgraph-cursor-ai-projects)\n- [7. 系统设计](#7-system-design)\n   * [ByteByteGo - GenAI\u002FML\u002F现代系统设计面试](#bytebytego-genaimlmodern-system-design-interview)\n   * [Educative - GenAI\u002F现代系统设计面试](#educative-genaimodern-system-design-interview)\n- [8. 计算机系统](#8-computer-systems)\n- [9. 芝加哥大学2024年金融、计量经济学和统计学中的大数据与AI会议](#9-big-data-and-ai-in-finance-econometrics-and-statistics-conference-uchicago-2024)\n- [10. C++设计模式与衍生品定价](#10-c-design-patterns-and-derivatives-pricing)\n- [11. 高频金融](#11-high-frequency-finance)\n- [12. 用于算法交易的机器学习](#12-machine-learning-for-algorithmic-trading)\n- [13. 随机波动率建模](#13-stochastic-volatility-modeling)\n- [14. 量化岗位面试题](#14-quant-job-interview-questions)\n   * [星标历史](#star-history)\n\n\u003C!-- 目录结束 -->\n\n---\n\n\u003C!-- 目录 -->\u003Ca name=\"1-nvidia-gtc-ai-conference-for-developers\">\u003C\u002Fa>\n# 1. 英伟达GTC | 面向开发者的AI大会\n\n> \u003Cmark>[__2025年英伟达GTC大会——技术与产业洞察__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub星标数\" \u002F>\n\n> [__GTC 2024笔记—中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FNVIDIA%20GTC\u002FGTC%202024.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_f3896d493ac5.png\" width=\"80%\" height=\"80%\">\n\n\u003C!-- 目录 -->\u003Ca name=\"2-agentic-ai-summit\">\u003C\u002Fa>\n# 2. 代理型AI峰会\n\n> \u003Cmark>[__2025年伯克利代理型AI峰会——技术与产业洞察__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FAgentic%20AI%20Summit\u002FAgentic%20AI%20Summit%20Berkeley%202025.md)\u003C\u002Fmark> \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fjunfanz1%2FAI-LLM-ML-CS-Quant-Overview\" alt=\"GitHub星标数\" \u002F>\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_269bc9626558.png\" width=\"80%\" height=\"80%\">\n\n\n\u003C!-- 目录 -->\u003Ca name=\"3-llm-essentials\">\u003C\u002Fa>\n# 3. LLM基础\n\n\u003C!-- 目录 -->\u003Ca name=\"llm-theory\">\u003C\u002Fa>\n\n## LLM 理论\n\n深入探索 DeepSeek LLM，作者：Xiaojing Ding，2025 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FDive%20into%20DeepSeek%20LLM.md)\n\nDeepSeek 大模型高性能核心技术与多模态融合发展，作者：Xiaohua Wang，2025 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FDeepSeek%20Large%20Model.md)\n\nPyTorch 中的高效训练，作者：Ailing Zhang，2024 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FEfficient%20Training%20PyTorch.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_ab00e0921860.png\" width=\"34%\" height=\"34%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_8de628d774f8.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_6ff925d0f793.png\" width=\"32%\" height=\"32%\">\n\n---\n\nAWS 上的生成式 AI，作者：Chris Fregly，2024 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FGenerative%20AI%20on%20AWS.md)\n\n从理论到实践的 LLM，作者：Qi Zhang，2024 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FLLM%20from%20Theory%20to%20Practice.md)\n\nLangChain 可扩展的 LLM 应用，作者：Teli Li，2024 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FLangChain%20Scalable%20LLM%20Apps.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_266498c2136b.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_c2b2a6ffcd81.png\" width=\"32%\" height=\"32%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_89a7a5033e43.png\" width=\"31%\" height=\"31%\">\n\n---\n\nLLM 基础——由浙江大学毛宇仁主讲，2024 年\n\n> [课程 GitHub](https:\u002F\u002Fgithub.com\u002FZJU-LLMs\u002FFoundations-of-LLMs) | [课程视频](https:\u002F\u002Fwww.bilibili.com\u002Fvideo\u002FBV1PB6XYFET2) | [教材](https:\u002F\u002Fgithub.com\u002FZJU-LLMs\u002FFoundations-of-LLMs\u002Fblob\u002Fmain\u002F%E3%80%8A%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9F%BA%E7%A1%80%E3%80%8B%E6%95%99%E6%9D%90\u002F%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%9F%BA%E7%A1%80%20%E5%AE%8C%E6%95%B4%E7%89%88.pdf) | [__PDF 笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002F%E6%B5%99%E5%A4%A7%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%AF%BE%E7%AC%94%E8%AE%B0.pdf)\n\n机器学习与人工智能的 30 个核心问答——塞巴斯蒂安·拉斯奇卡著，2025 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002F30%20ML%20AI.md)\n\n揭秘大模型，作者：Liang Wen，2025 年\n\n> [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FFoundations%20of%20LLMs\u002FUnveiling%20Large%20Model.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_00575a887f12.png\" width=\"30%\" height=\"30%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_2715c66f81e0.png\" width=\"34%\" height=\"34%\">\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_037bc7da1863.png\" width=\"34%\" height=\"34%\">\n\n---\n\n> [极客邦：AI LLM 实践](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100770601) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20LLM%20Practice.md)\n\n> [极客邦：AI LLM 系统](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Farticle\u002F852628) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20System.md)\n\n\u003C!-- TOC -->\u003Ca name=\"llm-applications\">\u003C\u002Fa>\n## LLM 应用\n\n> [极客邦：AI LLM 项目实施](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Farticle\u002F801454) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FLLM%20Project.md)\n\n> [极客邦：LLM 应用开发](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100764201) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FLLM%20App.md)\n\n\u003C!-- TOC -->\u003Ca name=\"rag\">\u003C\u002Fa>\n## RAG\n\n> [Educative：高级 RAG 技术——选择合适的方法](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002Fpg03nJFvpmPgN4W0Zuxy07pVPro3h2) | [__笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAdvanced%20RAG.md)\n\n> [极客邦：RAG 开发](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100804101?tab=catalog) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fedit\u002Fmain\u002FAI%20LLM\u002FRAG.md)\n\n\u003C!-- TOC -->\u003Ca name=\"multi-agent\">\u003C\u002Fa>\n## 多智能体\n\n> [Educative：使用 CrewAI 构建 AI 智能体和多智能体系统](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002Fk5m3gACoj1xDYoOq7c0Kjk4y2AoGTn) | [__笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FCrewAI.md)\n\n> [极客邦：AI 智能体](https:\u002F\u002Ftime.geekbang.org\u002Fcourse\u002Fintro\u002F100775901?tab=catalog) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FAI%20LLM\u002FAI%20Agent.md)\n\n\n\n\u003C!-- TOC -->\u003Ca name=\"4-deepseek-kimi\">\u003C\u002Fa>\n# 4. DeepSeek & Kimi \n\n\u003C!-- TOC -->\u003Ca name=\"research-implementation\">\u003C\u002Fa>\n## 研究实现\n\n> [GitHub：PyTorch 中混合专家（MoE）的实现](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FMoE-Mixture-of-Experts)\n\n> [GitHub：MiniGPT 和 DeepSeek MLA 多头潜在注意力](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FDeepSeek-MLA)\n\n\u003C!-- TOC -->\u003Ca name=\"deepseek-theory\">\u003C\u002Fa>\n## DeepSeek 理论\n\n> [Educative：关于 DeepSeek 的一切你需要知道](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FGZjlABCqZ1G2n7mWjuroy1MXK2GBIm) | [__笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Essentials.md)\n\n> [Zomi-Bilibili](https:\u002F\u002Fspace.bilibili.com\u002F517221395\u002Fupload\u002Fvideo) | [GitHub](https:\u002F\u002Fgithub.com\u002Fchenzomi12\u002FAIFoundation\u002F) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Theory.md)\n\n\u003C!-- TOC -->\u003Ca name=\"deepseek-applications\">\u003C\u002Fa>\n## DeepSeek 应用\n\n> [极客邦：DeepSeek 动手实践](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002F101000501) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20HandsOn.md)\n\n> [极客邦：DeepSeek 应用开发](https:\u002F\u002Ftime.geekbang.org\u002Fcolumn\u002Fintro\u002F100995901) | [__笔记-中文__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FDeepSeek\u002FDeepSeek%20Developer%20Practice.md)\n\n\u003C!-- TOC -->\u003Ca name=\"kimi-k2\">\u003C\u002Fa>\n## Kimi K2\n\n> [Kimi K2](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FDeepSeek\u002FKimi%20K2.md) | [🚀 10 分钟读懂 Kimi K2](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Funderstand-kimi-k2-10-minutes-jf-ai-vnsqc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"5-2025-paper-reading\">\u003C\u002Fa>\n# 5. 2025 年论文阅读\n\n## 智能体AI的前沿：智能体记忆\n\n> [🚀 智能体AI的前沿：智能体记忆 — 核心要点](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAwesome-AI-Engineer-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FFrontier%20of%20Agentic%20AI:%20Agent%20Memory.md) | [LinkedIn: 🚀 智能体AI的前沿：智能体记忆 — 核心要点](https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Fjunfan-zhu_agent-memory-activity-7380113422757277696-oaAc?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8)\n\n\u003C!-- TOC -->\u003Ca name=\"sglang-x-nvidia-dynamo-for-inference-performance-at-scale\">\u003C\u002Fa>\n## SGLang x NVIDIA：用于大规模推理性能的Dynamo\n\n> [🚀 SGLang x NVIDIA的洞见：用于大规模推理性能的Dynamo](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAwesome-AI-Engineer-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FSGLang%20Dynamo.md) | [LinkedIn: 🚀 sgl-project x NVIDIA的洞见：#Dynamo用于大规模推理性能](https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Fjunfan-zhu_dynamo-sanfrancisco-ai-activity-7379780254493569024-pEBC?utm_source=share&utm_medium=member_desktop&rcm=ACoAABxP-p0BpUNGDf347aKh_1uJAPzG4er0As8)\n\n\u003C!-- TOC -->\u003Ca name=\"jason-wei-3-ideas-to-understand-ai-in-2025\">\u003C\u002Fa>\n## Jason Wei：理解2025年AI的3个思路\n\n> [Jason Wei：理解2025年AI的3个思路](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FJason%20Wei%3A%203%20Ideas%20to%20Understand%20AI%20in%202025.md) | [LinkedIn：Jason Wei：理解2025年AI的3个思路](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F06-jason-weis-3-ideas-understand-ai-2025-jf-ai-v7rgc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"world-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa\">\u003C\u002Fa>\n## 世界模型：Eric Xing的PAN与Yann LeCun的JEPA之间的5场辩论\n\n> [世界模型](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FWorld%20Models.md) | [LinkedIn：世界模型：Eric Xing的PAN与Yann LeCun的JEPA之间的5场辩论](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fworld-model-5-debates-between-eric-xings-pan-yann-lecuns-jepa-jf-ai-8xigc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"30-takeaways-from-shunyu-yaos-talk-on-agentic-ai\">\u003C\u002Fa>\n## 来自Shunyu Yao关于智能体AI演讲的30条启示\n\n> [Shunyu Yao谈智能体AI](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FShunyu%20Yao%20Agentic%20AI.md) | [LinkedIn：来自Shunyu Yao关于智能体AI演讲的30条启示](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F30-takeaways-from-shunyu-yaos-talk-agentic-ai-jf-ai-dqz6c)\n\n\u003C!-- TOC -->\u003Ca name=\"building-web-agents\">\u003C\u002Fa>\n## 构建网络智能体\n\n> [构建网络智能体](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FBuilding%20Web%20Agents.md) | [LinkedIn：构建网络智能体](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Fbuilding-web-agents-jf-ai-khjic)\n\n\u003C!-- TOC -->\u003Ca name=\"future-of-ai-agents-agentic-rl-pretraining\">\u003C\u002Fa>\n## AI智能体的未来 = 智能体强化学习 + 预训练？\n\n> [AI智能体的未来 = 智能体强化学习 + 预训练？](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FFuture%20of%20AI%20Agents%20%3D%20Agentic%20RL%20%2B%20Pretraining%3F.md) | [LinkedIn：AI智能体的未来 = 智能体强化学习 + 预训练？](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002Ffuture-ai-agents-agentic-rl-pretraining-jf-ai-p0nlc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"hiva-self-organized-hierarchical-variable-agent-via-goal-driven-semantic-topological-evolution\">\u003C\u002Fa>\n## HiVA：通过目标驱动的语义拓扑进化实现自组织分层可变智能体\n\n> [HiVA：通过目标驱动的语义拓扑进化实现自组织分层可变智能体](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FPaper%20Reading\u002FHiVA:%20Self-organized%20Hierarchical%20Variable%20Agent%20via%20Goal-driven%20Semantic-Topological%20Evolution.md) | [LinkedIn：通往组织智能的协同进化之路：结构即记忆网络与多智能体涌现如何解锁AGI？](https:\u002F\u002Fwww.linkedin.com\u002Fpulse\u002F07-co-evolutionary-path-towards-organizational-intelligence-how-kpqjc\u002F)\n\n\u003C!-- TOC -->\u003Ca name=\"6-langgraph-cursor-ai-projects\">\u003C\u002Fa>\n# 6. LangGraph & Cursor AI项目\n\n> [__笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FLangChain\u002FProjects.md)\n- [Ed Donner：LLM工程：掌握AI、大型语言模型和智能体](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fllm-engineering-master-ai-and-large-language-models)\n- [Eden Marco：LangChain—使用LangChain开发LLM驱动的应用程序](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Flangchain\u002F)\n- [Eden Marco：LangGraph—使用LangGraph开发LLM驱动的AI智能体](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Flanggraph)\n- [Eden Marco：Cursor课程—使用Cursor AI Copilot进行全栈开发](https:\u002F\u002Fwww.udemy.com\u002Fcourse\u002Fcursor-ai-ide\u002F)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_6ed6e55e37d6.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_a7cc0031210c.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_31086c3ec9ea.png\" width=\"20%\" height=\"20%\">\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_cd9abf875c9a.png\" width=\"20%\" height=\"20%\">\n\n> GitHub项目\n\n- [MCP-多服务器互操作型Agent2Agent-LangGraph-AI系统](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FMCP-Servers)\n- [代码解释器-ReAct-LangChain智能体](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCode-Interpreter-ReAct-LangChain-Agent)\n- [LLM文档聊天机器人](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FLLM-Documentation-Chatbot)\n- [Cognito-LangGraph-RAG](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCognito-LangGraph-RAG)\n- [LangGraph反思研究员](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FLangGraph-Reflection-Researcher)\n- [Cursor全栈AI应用](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCursor-FullStack-AI-App)\n\n\n\n\n\u003C!-- TOC -->\u003Ca name=\"7-system-design\">\u003C\u002Fa>\n# 7. 系统设计\n\n\u003C!-- TOC -->\u003Ca name=\"bytebytego-genaimlmodern-system-design-interview\">\u003C\u002Fa>\n\n## ByteByteGo - 生成式AI\u002F机器学习\u002F现代系统设计面试\n\n系统设计面试：内部人士指南，第二版 - 作者：Alex Xu，2020年\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FSystem-Design-Interview-insiders-Second\u002Fdp\u002FB08CMF2CQF) | [__中文PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FSystem%20Design\u002FNotes%20on%20System%20Design.pdf)\n\n生成式AI系统设计面试 - 作者：Ali Aminian、Hao Sheng，2024年\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-System-Design-Interview\u002Fdp\u002F1736049127) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FSystem%20Design\u002FGenAI%20System%20Design%20Interview.md)\n\n机器学习系统设计面试 - 作者：Ali Aminian、Alex Xu，2023年\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-System-Design-Interview\u002Fdp\u002F1736049127) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review\u002Fblob\u002Fmain\u002FSystem%20Design\u002FML%20System%20Design%20Interview.md)\n\n\u003Cdiv style=\"display: flex; justify-content: space-around;\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_4a4f4ee674ea.png\" width=\"28.6%\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_23060cd714af.png\" width=\"30%\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_72e44ae7b2c3.png\" width=\"30%\">\n\u003C\u002Fdiv>\n\n\u003C!-- TOC -->\u003Ca name=\"educative-genaimodern-system-design-interview\">\u003C\u002Fa>\n## Educative - 生成式AI\u002F现代系统设计面试\n\n> [Educative - 掌握系统设计面试](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FB86jYxWPP3JhA8lAZw0B2Mhr92YjJNmG5Ty) | [__PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCS-Online-Course-Notes\u002Fblob\u002Fmain\u002FGrokking%20the%20System%20Design%20Interview\u002FGrokking%20the%20System%20Design%20Interview.pdf) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FCS-Online-Course-Notes\u002Fblob\u002Fmain\u002FGrokking%20the%20System%20Design%20Interview\u002FGrokking%20the%20System%20Design%20Interview.md)\n\n> [Educative - 掌握现代系统设计面试](https:\u002F\u002Fwww.educative.io\u002Fcourses\u002Fgrokking-the-system-design-interview) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Overview\u002Fblob\u002Fmain\u002FSystem%20Design\u002FModern%20System%20Design.md)\n\n> [Educative - 生成式AI系统设计](https:\u002F\u002Fwww.educative.io\u002Fverify-certificate\u002FRgxzXQFQkKyYgKrGjTX1RQpE9J3vT6) | [__笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FSystem%20Design\u002FGenAI%20System%20Design.md)\n\n\u003C!-- TOC -->\u003Ca name=\"8-computer-systems\">\u003C\u002Fa>\n# 8. 计算机系统\n\n计算机底层的秘密，陆小风 - 2023年，电子工业出版社\n\n> [图书链接](https:\u002F\u002Fbook.douban.com\u002Fsubject\u002F36370606\u002F) | [__中文PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FComputer%20Systems\u002FNotes%20on%20Computer%20Systems%20-%20Chinese.pdf)\n  \n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_3a77babd4a79.png\" width=\"35%\" height=\"35%\">\n\n\u003C!-- TOC -->\u003Ca name=\"9-big-data-and-ai-in-finance-econometrics-and-statistics-conference-uchicago-2024\">\u003C\u002Fa>\n# 9. 芝加哥大学2024年金融、计量经济学和统计学中的大数据与人工智能会议\n\nBDAI会议，2024年10月3日至5日，芝加哥大学\n\n> [摘要PDF](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBDAI-2024%20Abstracts.pdf) | [议程PDF](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBDAI-2024%20Program.pdf) | [__高级概述笔记PDF__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBig_Data_Finance_Conference_High_Level_Overview.pdf) | [__会议回顾笔记PDF__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FBig%20Data%20AI%20in%20Finance%2C%20Econometrics%2C%20Statistics%20Conference%202024\u002FBig_Data_Finance_Conference_Notes.pdf) \n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_b76811a97050.png\" width=\"50%\" height=\"50%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"10-c-design-patterns-and-derivatives-pricing\">\u003C\u002Fa>\n# 10. C++设计模式与衍生品定价\n\nC++设计模式与衍生品定价（数学、金融与风险，系列编号2）第2版，作者：M. S. Joshi\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FPatterns-Derivatives-Pricing-Mathematics-Finance\u002Fdp\u002F0521721628) | [__PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing.pdf) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing\u002FC%2B%2B%20Design%20Patterns%20Derivatives%20Pricing.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_53a2e5b6ca48.png\" width=\"30%\" height=\"30%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"11-high-frequency-finance\">\u003C\u002Fa>\n# 11. 高频金融\n\n高频金融导论，作者：Ramazan Gençay等。\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FIntroduction-High-Frequency-Finance-Ramazan-Gen%C3%A7ay\u002Fdp\u002F0122796713) | [__PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FAn%20Intro%20to%20High-Frequency%20Finance\u002FNotes%20on%20An%20Introduction%20to%20High-Frequency%20Finance.pdf) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FAn%20Intro%20to%20High-Frequency%20Finance\u002FAn%20Introduction%20to%20High-Frequency%20Financ.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_e21427ed7a4c.png\" width=\"30%\" height=\"30%\">\n\n\n\u003C!-- TOC -->\u003Ca name=\"12-machine-learning-for-algorithmic-trading\">\u003C\u002Fa>\n# 12. 用于算法交易的机器学习\n\n用于算法交易的机器学习：利用Python从市场和替代数据中提取信号以构建系统化交易策略的预测模型，第2版平装本 – 作者：Stefan Jansen，2020年\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FMachine-Learning-Algorithmic-Trading-alternative\u002Fdp\u002F1839217715) | [__PDF笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FML%20for%20Algorithmic%20Trading\u002FNotes%20on%20Machine%20Learning%20for%20Algorithmic%20Trading.pdf) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FML%20for%20Algorithmic%20Trading\u002FNotes%20on%20Machine%20Learning%20for%20Algorithmic%20Trading.md)\n\n\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_1993469acebc.png\" width=\"30%\" height=\"30%\">\n\n\u003C!-- TOC -->\u003Ca name=\"13-stochastic-volatility-modeling\">\u003C\u002Fa>\n\n# 13. 随机波动率建模\n\n随机波动率建模（查普曼和霍尔\u002FCRC金融数学系列）第一版，作者：洛伦佐·贝尔戈米\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FStochastic-Volatility-Modeling-Financial-Mathematics\u002Fdp\u002F1482244063) | [__PDF 第1章简介__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%201%20Introduction%20Notes.pdf) | [__Markdown 第1章简介__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%201%20Introduction%20Notes.md) | [__PDF 第2章局部波动率__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%202%20Local%20Volatility%20Notes.pdf) | [__Markdown 第2章局部波动率__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FStochastic%20Volatility%20Modeling\u002FStochastic%20Volatility%20Modeling%20-%20Char%202%20Local%20Volatility%20Notes.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_2dc98e9fdcbd.png\" width=\"30%\" height=\"30%\">\n\n\u003C!-- TOC -->\u003Ca name=\"14-quant-job-interview-questions\">\u003C\u002Fa>\n# 14. 量化岗位面试题\n\n量化岗位面试题及答案（第二版）——马克·乔希著，2013年\n\n> [图书链接](https:\u002F\u002Fwww.amazon.com\u002FQuant-Interview-Questions-Answers-Second\u002Fdp\u002F0987122827) | [__Markdown笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FQuant-Books-Notes\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FQuant%20Essentials%20Takeaways.md)\n\n\u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_4f9e9739d684.png\" width=\"30%\" height=\"30%\">\n\n- [__云平台笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FCloud.pdf) | [__量化笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FQuant.pdf) | [__外汇奇异衍生品笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FFX%20Exotic%20Derivatives.pdf) | [__风险方法论笔记__](https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-ML-CS-Quant-Readings\u002Fblob\u002Fmain\u002FQuant%20Job%20Interview%20Q%26A\u002FRisk%20Methodologies.pdf)\n\n\n---\n\n\u003Cdiv align=\"left\">\n  \u003Cmarquee behavior=\"alternate\" scrollamount=\"3\">\n    \u003Cstrong>与我联系：\u003C\u002Fstrong>\n     \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fjunfanz1\">GitHub\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.overleaf.com\u002Fread\u002Fjcgfkzhyfvdv#57139d\">简历\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fjunfan-zhu\u002F\">LinkedIn\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fx.com\u002Fjunfanzhu98\">X\u003C\u002Fa> •\n    \u003Ca href=\"mailto:junfanzhu98@gmail.com\">邮箱\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.instagram.com\u002Fjunfan_zhu\u002F\">Instagram\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.facebook.com\u002Fjunfan.zhu.961\u002F\">Facebook\u003C\u002Fa> •\n    \u003Ca href=\"https:\u002F\u002Fwww.douban.com\u002Fpeople\u002Fjunfanz\u002F\">豆瓣\u003C\u002Fa> •\n    \u003Ca href=\"junfanzhu98\">微信\u003C\u002Fa>\n  \u003C\u002Fmarquee>\n\u003C\u002Fdiv>\n\n\u003C!-- TOC -->\u003Ca name=\"star-history\">\u003C\u002Fa>\n## 星标历史\n\n[![星标历史图表](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_readme_827877a55bcb.png)](https:\u002F\u002Fwww.star-history.com\u002F#junfanz1\u002FAI-LLM-ML-CS-Quant-Readings&Date)","# Awesome-AI-Review 快速上手指南\n\nAwesome-AI-Review 并非一个需要安装运行的软件库，而是一个**精选的 AI 行业与技术学习资源索引仓库**。它汇集了 NVIDIA GTC、Agentic AI Summit、LLM 理论、DeepSeek\u002FKimi 实战、量化金融等前沿领域的会议笔记、论文解读和课程资料。\n\n本指南将帮助你快速克隆仓库并高效利用其中的中文学习笔记。\n\n## 1. 环境准备\n\n由于本项目主要为 Markdown 文档集合，对环境要求极低，仅需基础工具即可。\n\n*   **操作系统**: Windows \u002F macOS \u002F Linux\n*   **前置依赖**:\n    *   `Git`: 用于克隆代码仓库。\n    *   `Markdown 阅读器`: 推荐使用 **VS Code** (配合 Markdown All in One 插件) 或直接在 **GitHub 网页端** 浏览。\n*   **网络建议**:\n    *   鉴于仓库托管在 GitHub，国内访问可能较慢。建议使用 **Gitee 镜像** (如有) 或配置 **GitHub 加速代理**。\n    *   部分外部链接指向极客时间 (GeekBang)、Bilibili 或 Educative，请确保相关平台账号权限。\n\n## 2. 安装步骤（克隆仓库）\n\n打开终端（Terminal 或 CMD），执行以下命令将资源库下载到本地。\n\n### 标准克隆\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review.git\n```\n\n### 🚀 国内加速方案 (推荐)\n如果直接克隆速度慢，可以使用 Gitee 镜像源（需确认作者是否同步，若未同步可使用以下通用加速技巧或等待下载）：\n\n```bash\n# 方法 A: 使用 gitclone.com 加速 (如果可用)\ngit clone https:\u002F\u002Fgitclone.com\u002Fgithub.com\u002Fjunfanz1\u002FAI-LLM-ML-CS-Quant-Review.git\n\n# 方法 B: 进入目录查看内容\ncd AI-LLM-ML-CS-Quant-Review\n```\n\n> **提示**: 本项目核心内容为 `.md` 文件，克隆完成后无需运行 `pip install` 或编译操作。\n\n## 3. 基本使用\n\n本项目的使用方式是**按需阅读**。你可以根据当前的学习方向，直接在本地或 GitHub 上跳转至对应章节。\n\n### 场景一：浏览最新行业洞察 (NVIDIA GTC & Agentic AI)\n关注 2025 年最新的技术与产业趋势。\n\n*   **操作**: 打开根目录下的 `NVIDIA GTC\u002FGTC 2025.md` 或 `Agentic AI Summit\u002FAgentic AI Summit Berkeley 2025.md`。\n*   **内容**: 包含会议核心技术点整理和产业分析。\n\n### 场景二：系统学习 LLM 理论与应用\n适合希望从理论到落地全面掌握大模型的开发者。\n\n*   **操作**: 进入 `Foundations of LLMs\u002F` 目录。\n*   **推荐路径**:\n    1.  **理论基础**: 阅读 `Dive into DeepSeek LLM.md` 或 `浙大大模型课笔记.pdf`。\n    2.  **工程实践**: 阅读 `LangChain Scalable LLM Apps.md` 了解如何构建可扩展应用。\n    3.  **进阶技术**: 查看 `Advanced RAG.md` 和 `CrewAI.md` 学习检索增强生成与多智能体系统。\n\n### 场景三：DeepSeek 与 Kimi 专项研究\n针对国产热门大模型的深度解析与代码实现。\n\n*   **操作**: 进入 `DeepSeek\u002F` 目录。\n*   **核心资源**:\n    *   **理论**: `DeepSeek Theory.md` (含 MoE 架构解析)。\n    *   **实战**: `DeepSeek HandsOn.md` 和 `DeepSeek Developer Practice.md`。\n    *   **代码复现**: 参考仓库中关联的 `MoE-Mixture-of-Experts` 和 `DeepSeek-MLA` 子项目链接进行代码研习。\n\n### 场景四：量化金融与系统设计\n面向金融科技从业者的专项资料。\n\n*   **操作**: 查阅根目录中的 `Big Data and AI in Finance...` 章节及 `System Design` 部分。\n*   **内容**: 涵盖高频交易、随机波动率建模及 GenAI 系统设计面试题解。\n\n---\n\n**💡 使用小贴士**:\n*   所有标记为 `[__Notes-Chinese__]` 的链接均指向作者整理的**中文笔记**，优先阅读这些文件可获得最佳学习体验。\n*   若需搜索特定知识点，建议在本地使用 VS Code 打开整个文件夹，利用 `Ctrl+Shift+F` 进行全局关键词搜索。","某量化基金的高级算法工程师正筹备年度技术战略会议，急需整合 2025 年 NVIDIA GTC 大会关于推理优化的最新洞察，以及伯克利 Agentic AI 峰会中多智能体协作的前沿成果，以指导下一代高频交易系统的架构升级。\n\n### 没有 Awesome-AI-Review 时\n- **信息检索低效**：需要在 arXiv、YouTube 和各大博客间反复跳转，花费数天筛选关于 SGLang 与 NVIDIA Dynamo 性能优化的零散资料。\n- **核心观点遗漏**：难以从长达数小时的会议录像中快速提取如\"Shunyu Yao 关于代理式 AI 的 30 个关键结论”等高价值干货。\n- **知识体系割裂**：缺乏将 LLM 理论（如世界模型争论）与实际工程落地（如 LangGraph 项目）串联起来的系统性综述。\n- **前沿趋势误判**：容易错过 DeepSeek 或 Kimi K2 等新兴模型在金融场景的具体应用案例，导致技术选型滞后。\n\n### 使用 Awesome-AI-Review 后\n- **一站式获取精华**：直接查阅整理好的\"2025 NVIDIA GTC\"与“伯克利峰会”专题笔记，几分钟内掌握推理性能扩展的核心技术路径。\n- **深度洞察直达**：通过预设的论文解读章节，快速获取 Jason Wei 对 2025 AI 趋势的三大预判及 Eric Xing 与 Yann LeCun 的世界模型辩论要点。\n- **理论与实战闭环**：利用目录中从\"LLM 基础”到\"LangGraph 项目”的结构化指引，迅速构建从算法原理到系统设计的完整知识图谱。\n- **行业应用对标**：参考 DeepSeek 在量化领域的实施细节及高频金融相关的面试题与建模策略，精准校准团队的技术演进方向。\n\nAwesome-AI-Review 将原本需要数周的行业调研工作压缩至数小时，让技术人员能直接从巨人的肩膀上启动创新。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fjunfanz1_Awesome-AI-Review_f3896d49.png","junfanz1","Junfan Zhu","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fjunfanz1_b6066560.jpg","AI Engineer (open), RL, Agent | Stanford GSB | Georgia Tech CS | UChicago Math, ex-Quant | WeChat: junfanzhu98 | LinkedIn: junfan-zhu | IG: junfan_zhu","University of Chicago","Santa Clara, California","junfanz@gatech.edu","junfanzhu98","https:\u002F\u002Fjunfanz1.github.io\u002F","https:\u002F\u002Fgithub.com\u002Fjunfanz1",null,554,107,"2026-04-03T00:35:09",1,"",{"notes":93,"python":91,"dependencies":94},"该项目（Awesome-AI-Review）并非一个可执行的 AI 软件工具，而是一个汇集人工智能、大语言模型（LLM）、量化金融等领域技术文章、会议笔记（如 NVIDIA GTC, Agentic AI Summit）、论文解读和学习资源索引的仓库。因此，它本身没有特定的操作系统、GPU、内存或 Python 版本等运行环境需求。用户只需具备浏览器即可访问其中的文档链接，或克隆仓库阅读 Markdown 文件。部分链接指向的外部教程或代码实现（如 PyTorch MoE 实现）可能有各自独立的环境要求，需参考对应子项目的说明。",[],[26,13,15,54],"2026-03-27T02:49:30.150509","2026-04-06T07:15:03.014788",[],[]]