@Jolyne_AI: There's an open-source tool on GitHub called daily-arXiv-ai-enhanced that turns 'paper chasing' into a daily automated routine. It fetches the latest arXiv papers daily and uses DeepSeek and other large models to generate Chinese summaries, helping you quickly stay on top of the latest AI research.

There is an open-source tool on GitHub: daily-arXiv-ai-enhanced, which helps you turn “chasing papers” into a daily automated routine. It crawls the latest arXiv papers every day and uses large models like DeepSeek to generate Chinese summaries, allowing you to keep up with the latest AI research progress in less time. GitHub: http://github.com/dw-dengwei/daily-arXiv-ai-enhanced… Official website: https://dw-dengwei.github.io/daily-arXiv-ai-enhanced… Main highlights: - Daily automatic updates: covers three major directions – computer vision, graphics, and natural language processing - Automatic Chinese summary generation: uses LLM to extract key points, significantly reducing reading cost - Highly customizable: you can choose paper categories, summary language, and the AI model used - Zero-server deployment: fully automated based on GitHub Actions, saving effort - Historical archiving by date: easily look back at past paper updates - Personalized configuration: supports email and user information customization Getting started is also simple: Fork the project, fill in the API Key, and it runs. Suitable for those who want to “browse” the latest papers every day. — # dw-dengwei/daily-arXiv-ai-enhanced Source: https://github.com/dw-dengwei/daily-arXiv-ai-enhanced # 🚀 daily-arXiv-ai-enhanced > [!CAUTION] > If your jurisdiction has censorship requirements for academic data, run this code with caution; any secondary distribution version must fulfill compliance review obligations (including but not limited to original paper compliance, AI compliance), otherwise all legal consequences shall be borne by the downstream. > [!CAUTION] > If your jurisdiction has censorship requirements for academic data, run this code with caution; any secondary distribution version must remove the entrance accessible to China and fulfill the content review obligations, otherwise all legal consequences will be borne by the downstream. This innovative tool transforms how you stay updated with arXiv papers by combining automated crawling with AI-powered summarization. ## ✨ Key Features 🎯 Zero Infrastructure Required - Leverages GitHub Actions and Pages - no server needed - Completely free to deploy and use 🤖 Smart AI Summarization - Daily paper crawling with DeepSeek-powered summaries - Cost-effective: Only ~0.2 CNY per day 💫 Smart Reading Experience - Personalized paper highlighting based on your interests - Cross-device compatibility (desktop & mobile) - Local preference storage for privacy - Flexible date range filtering 🧩 SKILL System - Plug-and-play skill modules for customizing paper filtering ⚙️ Easy Preference Export & Integration - One-click copy in Settings to export your keywords and authors configuration - Seamlessly combine exported preferences with SKILL for reproducible and shareable setups 👉 Try it now! (https://dw-dengwei.github.io/daily-arXiv-ai-enhanced/) - No installation required https://github.com/user-attachments/assets/b25712a4-fb8d-484f-863d-e8da6922f9d7 # How to use This repo will daily crawl arXiv papers about cs.CV, cs.GR, cs.CL and cs.AI, and use DeepSeek to summarize the papers in Chinese. If you wish to crawl other arXiv categories, use other LLMs, or other languages, please follow the instructions. Otherwise, you can watch the video above first and directly use this repo in https://dw-dengwei.github.io/daily-arXiv-ai-enhanced/. Please star it if you like :) If you want to customize categories, LLMs, or languages, click here. ## Instructions 1. Fork this repo to your own account and delete my own information in buy-me-a-coffee. 2. Go to: your-own-repo -> Settings -> Secrets and variables -> Actions 3. Go to Secrets. Secrets are encrypted and used for sensitive data 4. Create two repository secrets named OPENAI_API_KEY and OPENAI_BASE_URL, and input corresponding values. 5. [Optional] Set a password in secrets.ACCESS_PASSWORD if you do not wish others to access your page. (see https://github.com/dw-dengwei/daily-arXiv-ai-enhanced/pull/64) 6. Go to Variables. Variables are shown as plain text and are used for non-sensitive data 7. Create the following repository variables: 1. CATEGORIES: separate the categories with “,”, such as “cs.CL, cs.CV” 2. LANGUAGE: such as “Chinese” or “English” 3. MODEL_NAME: such as “deepseek-chat” 4. EMAIL: your email for push to GitHub 5. NAME: your name for push to GitHub 8. Go to your-own-repo -> Actions -> arXiv-daily-ai-enhanced 9. You can manually click Run workflow to test if it works well (it may take about one hour). By default, this action will automatically run every day. You can modify it in .github/workflows/run.yml 10. Set up GitHub pages: Go to your own repo -> Settings -> Pages. In Build and deployment, set Source="Deploy from a branch", Branch="main", "/(root)". Wait for a few minutes, go to https://.github.io/daily-arXiv-ai-enhanced/. Please see this issue (https://github.com/dw-dengwei/daily-arXiv-ai-enhanced/issues/14) for more precise instructions. # Contributors Thanks to the following special contributors for contributing code, discovering bugs, and sharing useful ideas for this project!!! JianGuanTHU Chi-hong22 chaozg quantum-ctrl Zhao2z eclipse0922 xuemian168 Lrrrr549 AinzRimuru fengxueguiren zerocpp # Acknowledgement We sincerely thank the following individuals and organizations for their promotion and support!!! Github_Daily AIGCLINK 阮一峰的网络日志 科技爱好者周刊 (第 353 期) 《HelloGitHub》 月刊第 111 期 # Star history Stargazers over time (https://starchart.cc/dw-dengwei/daily-arXiv-ai-enhanced) # Buy me a coffee here