MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Background Matting: The World is Your Green Screen

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.

cube studio开源云原生一站式机器学习/深度学习/大模型AI平台，mlops算法链路全流程，算力租赁平台，notebook在线开发，拖拉拽任务流pipeline编排，多机多卡分布式训练，超参搜索，推理服务VGPU虚拟化，边缘计算，标注平台自动化标注，deepseek等大模型sft微调/奖励模型/强化学习训练，vllm/ollama/mindie大模型多机推理，私有知识库，AI模型市场…

OpenVLA: An open-source vision-language-action model for robotic manipulation.

[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

My learning notes/codes for ML SYS.

XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

OpenMMLab Pre-training Toolbox and Benchmark

「画像処理100本ノック」中文版本！为图像处理初学者设计的 100 个问题。

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Streamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁，一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭…

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Improved AnimateDiff for ComfyUI and Advanced Sampling Support

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

OpenMMLab Model Deployment Framework

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Plenoxels: Radiance Fields without Neural Networks

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Base on YOLOv5 Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Isaac Gym Environments for Legged Robots

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance