Production First and Production Ready End-to-End Speech Recognition Toolkit

TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation

A graph node engine and editor written in Javascript similar to PD or UDK Blueprints, comes with its own editor in HTML5 Canvas2D. The engine can run client side or server side using Node. It allow…

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2

Nexent 是一个可以零代码开发智能体的平台 —— 无需编排，无需复杂拖拉拽。基于 MCP 工具生态，Nexent 还提供强大的模型集成、数据处理、知识库管理能力。

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

A high-performance runtime framework for modern robotics.

[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide

🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 |

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

[CVPR 2025] FoundationStereo: Zero-Shot Stereo Matching

Go ahead and axolotl questions

A powerful tool for creating fine-tuning datasets for LLM

Official repository of ’Visual-RFT: Visual Reinforcement Fine-Tuning’

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

s1: Simple test-time scaling

CourtCheck is a computer vision project that detects/tracks tennis court boundaries and ball movements

基于大模型 RAG 知识库与知识图谱的问答平台。Llamaindex + VueJS + Flask + Neo4j。大模型适配 OpenAI、国内主流大模型平台的模型调用、本地 vllm 部署。

A modular graph-based Retrieval-Augmented Generation (RAG) system

Documentation of AnythingLLM by Mintplex Labs Inc.

NMPC, WBC, state estimation, and sim2real framework for legged robots based on OCS2 and ros-controls

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

fine-tune deepseek r1