Stars
Differentiable optical lens simulator for end-to-end cameras.
This is the first open source version of PEEC of our group. Its a quasi-static model for free-space electromagnetic problem. It gives equivalent circuit model conductors in a free-space. Gmsh is re…
Cognitive-Informed Multimodal Sentiment Analysis Framework
Wi-Fi IQ capture system using USRP B210 (Dockerized)
KoalaQA 是一款 AI 大模型驱动的开源售后服务社区，提供 AI 回答、AI 搜索、AI 运营等能力，帮助你快速落地售后客服、社区问答、自助服务等场景，帮助团队显著降低人工运营成本、提升客户满意度与响应效率，助力实现 ZCR（Zero Contact Resolution）目标。
Code for paper [CLMN: Concept based Language Models via Neural Symbolic Reasoning]
项目名称：OpenArk灵枢：基于 DAYU200 与 Wheeltec ROS 机器人的原生 AI 协同控制系统 文档版本：V1.1 硬件环境： 控制端：OpenHarmony DAYU200 (RK3568，OpenHarmony ≥ 5.0 Release) 机器人端：ROS 小车 (Ubuntu 18.04 + ROS Melodic + ARM64) || 水下机器人（由于水下机…
RealSee3D: A multi-view RGB-D dataset combining real-world captures and procedurally generated scenes, with extensible annotations for diverse 3D vision research.
Vue-devtools Plugin For vConsole & Eruda ( vConsole & Eruda 的 Vue-devtools 插件 )
A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning
Official Implementation of Paper [DualCamCtrl: Dual-Branch Diffusion Model for Geometry-Aware Camera-Controlled Video Generation]
Superduper: End-to-end framework for building custom AI applications and agents.
Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization
Official implementation of [OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation]
VisionForge是一个轻量级、高扩展性的大模型图片训练&描述工具生成器，支持多家大模型API（Google、OpenAI 兼容、DeepSeek、Qwen、GLM、Claude、Doubao、自定义模型）。 它提供多图片上传、提示词优化、自动生成JSONL训练数据、多项信息分析（标签、OCR、场景分类、主色调、置信度、推理原因）等能力。 支持实时统计图表（置信度分布直方图与趋势曲线），…
A cross-platform GUI library for Rust, inspired by Elm
An ultra-lightweight and blazing-fast MQTT Messaging Broker/Bus for IoT Edge & SDV
DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
Node based GUI for The Composers Desktop Project
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
A WebGL accelerated JavaScript library for training and deploying ML models.
🌍 lightweight C++17 ply 3d mesh format importer & exporter
The easiest, most secure way to use WireGuard and 2FA.