202510 hf 2025-10-14 hf 2025-10-13 hf 2025-10-12 hf 2025-10-11 hf 2025-10-10 hf 2025-10-09 hf 2025-10-08 hf 2025-10-07 hf 2025-10-06 hf 2025-10-05 hf 2025-10-04 hf 2025-10-03 hf 2025-10-02 hf 2025-10-01 202509 hf 2025-09-30 hf 2025-09-29 hf 2025-09-28 hf 2025-09-27 hf 2025-09-26 hf 2025-09-25 hf 2025-09-24 hf 2025-09-23 hf 2025-09-22 hf 2025-09-21 hf 2025-09-20 hf 2025-09-19 hf 2025-09-18 hf 2025-09-17 hf 2025-09-16 hf 2025-09-15 hf 2025-09-14 hf 2025-09-13 hf 2025-09-12 hf 2025-09-11 hf 2025-0 ...

202510 weibo 2025-10-14 weibo 2025-10-13 weibo 2025-10-12 weibo 2025-10-11 weibo 2025-10-10 weibo 2025-10-09 weibo 2025-10-08 weibo 2025-10-07 weibo 2025-10-06 weibo 2025-10-05 weibo 2025-10-04 weibo 2025-10-03 weibo 2025-10-02 weibo 2025-10-01 202509 weibo 2025-09-30 weibo 2025-09-29 weibo 2025-09-28 weibo 2025-09-27 weibo 2025-09-26 weibo 2025-09-25 weibo 2025-09-24 weibo 2025-09-23 weibo 2025-09-22 weibo 2025-09-21 weibo 2025-09-20 weibo 2025-09-19 weibo 2025-09-18 weibo 2025-09-17 weibo 202 ...

数据来源：ArXiv Domain LLM Domain Papers1. One Token to Fool LLM-as-a-JudgeGenerative reward models (also known as LLMs-as-judges), which use large language models (LLMs) to evaluate answer quality, are increasingly adopted in reinforcement learning with verifiable rewards (RLVR). They are often preferred over rigid rule-based metrics, especially for complex reasoning tasks involving free-form outputs. In this paradigm, an LLM is typically prompted to compare a candidate answer against a ground-tru ...

数据来源：ArXiv Domain LLM Domain Papers1. CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding TasksLarge Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, de ...

数据来源：ArXiv Domain LLM Domain Papers1. CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding TasksLarge Language Models (LLMs) have significantly advanced the state-of-the-art in various coding tasks. Beyond directly answering user queries, LLMs can also serve as judges, assessing and comparing the quality of responses generated by other models. Such an evaluation capability is crucial both for benchmarking different LLMs and for improving response quality through response ranking. However, de ...

数据来源：ArXiv Domain LLM Domain Papers1. Web-Browsing LLMs Can Access Social Media Profiles and Infer User DemographicsLarge language models (LLMs) have traditionally relied on static training data, limiting their knowledge to fixed snapshots. Recent advancements, however, have equipped LLMs with web browsing capabilities, enabling real time information retrieval and multi step reasoning over live web content. While prior studies have demonstrated LLMs ability to access and analyze websites, thei ...

数据来源：ArXiv Domain LLM Domain Papers1. Comparing Apples to Oranges: A Dataset & Analysis of LLM Humour Understanding from Traditional Puns to Topical JokesHumour, as a complex language form, is derived from myriad aspects of life, whilst existing work on computational humour has focussed almost exclusively on short pun-based jokes. In this work, we investigate whether the ability of Large Language Models (LLMs) to explain humour depends on the particular humour form. We compare models on si ...

数据来源：ArXiv Domain LLM Domain Papers1. From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?Generative pretraining (the “GPT” in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from massive, unstructured datasets. We use the term foundation models to refer to large pretrained systems that can be adapted to a wide range ...

数据来源：gtrend.yapie.me twentyhq/twentyBuilding a modern alternative to Salesforce, powered by the community. ⭐ Stars: 29974 🍴 Forks: 3456 📝 Language: TypeScript black-forest-labs/fluxOfficial inference repo for FLUX.1 models ⭐ Stars: 22872 🍴 Forks: 1627 📝 Language: Python GraphiteEditor/Graphite2D vector & raster editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow. ⭐ Stars: 13645 🍴 Forks: 633 📝 Language: Rust adityachand ...

数据来源：gtrend.yapie.me twentyhq/twentyBuilding a modern alternative to Salesforce, powered by the community. ⭐ Stars: 29974 🍴 Forks: 3456 📝 Language: TypeScript black-forest-labs/fluxOfficial inference repo for FLUX.1 models ⭐ Stars: 22872 🍴 Forks: 1627 📝 Language: Python GraphiteEditor/Graphite2D vector & raster editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow. ⭐ Stars: 13645 🍴 Forks: 633 📝 Language: Rust adityachand ...

数据来源：gtrend.yapie.me GraphiteEditor/Graphite2D vector & raster editor that melds traditional layers & tools with a modern node-based, non-destructive, procedural workflow. ⭐ Stars: 15119 🍴 Forks: 680 📝 Language: Rust twentyhq/twentyBuilding a modern alternative to Salesforce, powered by the community. ⭐ Stars: 32034 🍴 Forks: 3571 📝 Language: TypeScript nextcloud/all-in-one📦 The official Nextcloud installation method. Provides easy deployment and maintenance with most features ...

数据来源：github.com/trending Any Languagesmicrosoft/generative-ai-for-beginners21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/ ⭐ Stars: 89399 🍴 Forks: 📝 Language: Jupyter Notebook NanmiCoder/MediaCrawler小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫 ⭐ Stars: 24782 🍴 Forks: 📝 Language: Python zaidmukaddam/sciraScira (Formerly MiniPerplx) is a minimalistic AI-powered search engi ...

数据来源：github.com/trending Any Languagesmicrosoft/generative-ai-for-beginners21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/ ⭐ Stars: 90135 🍴 Forks: 📝 Language: Jupyter Notebook NanmiCoder/MediaCrawler小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫 ⭐ Stars: 24986 🍴 Forks: 📝 Language: Python zaidmukaddam/sciraScira (Formerly MiniPerplx) is a minimalistic AI-powered search engi ...

数据来源：github.com/trending Any LanguagesNanmiCoder/MediaCrawler小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫 ⭐ Stars: 26240 🍴 Forks: 📝 Language: Python Genesis-Embodied-AI/GenesisA generative world for general-purpose robotics & embodied AI learning. ⭐ Stars: 25622 🍴 Forks: 📝 Language: Python LadybirdBrowser/ladybirdTruly independent web browser ⭐ Stars: 44654 🍴 Forks: 📝 Language: C++ swagger-api/swagger-uiSwagger UI is a colle ...

数据来源：github.com/trending Any LanguagesNanmiCoder/MediaCrawler小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫 ⭐ Stars: 26460 🍴 Forks: 📝 Language: Python Genesis-Embodied-AI/GenesisA generative world for general-purpose robotics & embodied AI learning. ⭐ Stars: 25663 🍴 Forks: 📝 Language: Python LadybirdBrowser/ladybirdTruly independent web browser ⭐ Stars: 44713 🍴 Forks: 📝 Language: C++ swagger-api/swagger-uiSwagger UI is a colle ...