Starred repositories
Application for Mind Mapping, Knowledge Management, Project Management. Develop, organize and communicate your ideas and knowledge in the most effective way.
A mind map, outline for obsidian,It support mobile and desktop
2023-2025中国节假日、调休、补班日历，ICS格式，可供IPhone、Google Calendar、Outlook等客户端订阅，包含节假日API
Free proxy,VPN,免费代理,网络加速,科学上网,机场订阅,翻墙,梯子 無料プロキシ 무료 프록시 Gratis gratuit Бесплатный прокси gratuito Gratis Darmowe Ücretsiz بروكسي مجاني मुफ्त प्रॉक्सी พร็อกซีฟรี miễn phí
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI 翻译 + AI 分析简报直推手机，也支持接入 MCP 架构，赋能 AI 自然语言对…
Must-read Papers on Knowledge Editing for Large Language Models.
Code for paper "SPG Sandwiched Policy Gradient for Masked Diffusion Language Models"
A comprehensive guide for beginners in the field of data management and artificial intelligence.
Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.
Mobile-Agent: The Powerful GUI Agent Family
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Towards a Unified View of Large Language Model Post-Training
[SIGGRAPH 2024] Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
Official frugal and native macOS Syncthing application bundle
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.
A data index and query language over Markdown files, for https://obsidian.md/.