Production-ready platform for agentic workflow development.

AI模型接口管理与分发系统，支持将多种大模型转为统一格式调用，支持OpenAI、Claude等格式，可供个人或者企业内部管理与分发渠道使用，本项目基于One API二次开发。🍥 The next-generation LLM gateway and AI asset management system supports multiple languages.

OpenWebUI 二开版本，支持余额管理和充值

Enhanced ChatGPT Clone: Features Agents, DeepSeek, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message se…

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

This is the official repository for the code and datasets in the paper "Progressive Open Space Expansion for Open-Set Model Attribution", CVPR 2023.

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…

中文简历模板，可添加照片，详细注释

[ICCV 2023 Oral]: Scaling Data Generation in Vision-and-Language Navigation

AI Research Platform for Reinforcement Learning from Real Panoramic Images.

Official implementation of Learning from Unlabeled 3D Environments for Vision-and-Language Navigation (ECCV'22).

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …

End-to-End Object Detection with Transformers

Open-source and strong foundation image recognition models.

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

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

ThesisUESTC-电子科技大学毕业论文模板

[NeurIPS'23] Emergent Correspondence from Image Diffusion

Low rank adaptation for Vision Transformer

High-Resolution Image Synthesis with Latent Diffusion Models

[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

[CVPR 2022] Joint hand motion and interaction hotspots prediction from egocentric videos

Train transformer language models with reinforcement learning.

Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).

Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification

Create a Gephi Citation Graph based on Text Analysis of PDFs from Zotero