Introducing OWLv2: Google's Breakthrough in Zero-Shot Object Detection

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

Codebase for "Demystifying Black-box Models with Symbolic Metamodels", NeurIPS 2019.

Incremental Knowledge Graphs Constructor Using Large Language Models

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

Rime输入法安装脚本，让一切更轻松。Make using Rime easy.

WarAgent: LLM-based Multi-Agent Simulation of World Wars

Generative Agents: Interactive Simulacra of Human Behavior

Orchestrate zero-shot computer vision models

A guidance language for controlling large language models.

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

A multithreaded 🕸️ web crawler that recursively crawls a website and creates a 🔽 markdown file for each page, designed for LLM RAG

基于ReAct手搓一个Agent Demo

Create knowledge graphs with LLMs

Build ChatGPT over your data, all with natural language

OpenMMLab Pre-training Toolbox and Benchmark

Multimodal RAG using LlamaIndex, Qdrant, llama.cpp for document QA with local VisonLLM and embedding models

Powerful menu bar manager for macOS

A distributed, fast open-source graph database featuring horizontal scalability and high availability

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

🌚 🌍 🌝 GeoIP 规则文件加强版，支持自行定制 V2Ray dat 格式文件 geoip.dat、MaxMind mmdb 格式文件、sing-box SRS 格式文件、mihomo MRS 格式文件、Clash ruleset、Surge ruleset 等。Enhanced edition of GeoIP files for V2Ray, Xray-core, sing-box,…

Blender addon to convert a blender scene to a Helios scene (LiDAR simulation, 3D point clouds)

Convert any text to a graph of knowledge. This can be used for Graph Augmented Generation or Knowledge Graph based QnA

Training and evaluation pipeline for MEG and EEG brain signal encoding and decoding using deep learning. Code for our paper "Decoding speech perception from non-invasive brain recordings" published…

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

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

A programming framework for agentic AI 🤖 (PyPi: autogen-agentchat)

Images to inference with no labeling (use foundation models to train supervised models).