Incentivizing "Thinking with Long Videos" via Native Tool Calling

🚀 Lightweight Redis GUI 🌐Full platform support🔥为爱发电💞

[CVPR 2025] LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant

SmartCodable is a data parsing library built on Swift’s Codable, designed for simple usage and strong real-world compatibility. It gracefully handles missing fields, default values, and evolving JS…

The Next-Generation Webhooks Gateway.

vue admin vue3 vue3admin vueadmin vue3.0-admin elegant-admin element element-plus template.vue3,vite,typescript,vue后台管理,vue3后台管理

AI4S-Discovery是基于多智能体架构的开源科研辅助工具，单人在Windows笔记本上开发完成。通过6个专业智能体自动完成文献采集（arXiv/PubMed等）、质量评分、图谱构建、技术成熟度评估和创新假设生成。集成FAISS向量搜索、MiniCPM-2B模型，支持CPU/GPU双模式，内存≤12GB。提供Web/API/CLI三种交互方式，实现AES-256加密、JWT认证等企业级…

去中心化工具包

A visual animation engine for demonstrating relativity physics

LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting

一个开源的 自动化运维 平台 (DevOps)

rust.std in c++

CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning

Welcome to the project repository for POPE (Promptable Pose Estimation), a state-of-the-art technique for 6-DoF pose estimation of any object in any scene using a single reference.

dlADMM: Deep Learning Optimization via Alternating Direction Method of Multipliers

[ACM MM 2025] SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation. https://arxiv.org/abs/2506.03139

A modern, high-performance mathematical expression evaluator built with Pratt Parsing and Stack-based VM

[Survey] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

vue3.x + vite5.x + element-plus 低代码平台 nocode 可视化拖拽 可视化编辑器 可视化建模 数据源自建 建站工具、可视化搭建工具 ai 低代码 ai nocode 深度集成 ai

一个零知识证明协议的简易实现

简小派求职方法论，正确找工作的方法

A macOS Photos–style photo manager for Windows — folder-native, non-destructive, with HEIC/MOV Live Photo, map view, and GPU-accelerated browsing.

vue3-elementPlus-admin,vue3-elementPlus-template

这是一个结合了RAG（Retrieval-Augmented Generation）和网络搜索功能的Agent项目，能够同时检索本地知识库和进行网络搜索，为用户提供全面的信息服务。项目通过API调用大语言模型进行推理，同时使用本地的bce-embedding-base_v1嵌入模型和Chroma向量数据库处理本地知识库检索，并采用ms-marco-MiniLM-L-6-v2交叉编码模型进行结…

【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

customizing the GitHub contribution graph, allowing you to draw various patterns on it.在你的GitHub贡献历史上画画！