AI agents running research on single-GPU nanochat training automatically

~950 line, minimal, extensible LLM inference engine built from scratch.

Convert OpenStreetMap (OSM) data to RDF Turtle, including the object geometries and all their DE-9IM spatial relations. Weekly updated dumps for the whole planet (~ 200 billion triples) and for eac…

Python sample codes and documents about Autonomous vehicle control algorithm. This project can be used as a technical guide book to study the algorithms and the software architectures for beginners.

End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.

This repo is aimed at deploying the autoware.universe with carla 0.9.15 on Jetson Orin.

Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

Elevating Vision-based 3D Object Detection by Local Density-Aware Dense Spatial Occupancy

[CVPR2024] NeuRAD: Neural Rendering for Autonomous Driving

NeuroNCAP benchmark for end-to-end autonomous driving

Video Indexing with object and outlier detection (IJCAI-24)

(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"

This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD

[KDD'2026] "VideoRAG: Chat with Your Videos"

Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.

A self-learning tutorail for CUDA High Performance Programing.

RAG Time: A 5-week Learning Journey to Mastering RAG

This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Extensible, lightweight HTTP request scheduler for OpenLambda

[CVPR‘ 2025 ] JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Multi-label-image-classification with Multi-method CLIP

Agent Zero AI framework

The SQL-RL-GEN is an algorithm based on a Reinforcement Learning approach with a reward function generated by a LLM to guide the agent's training process in solving the specific text2SQL generation…

Finetuning LLMs for the Text2Sparql task

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Ship AI Agents to Google Cloud in minutes, not months. Production-ready templates with built-in CI/CD, evaluation, and observability.