Stars
The Robust Risk Engine of the Quant Enthusiasts Community
Simulate flight path visualization using Three.js.
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
A framework for agentic tool use training with reinforcement learning
MatchFlow is a full-stack invoice processing and purchase-order matching system—built on Clean Architecture with a React+Nginx front-end, a .NET 6 API back-end, Azure Form Recognizer OCR, Azure Blo…
A Framework for LLM-based Multi-Agent Reinforced Training and Inference
The open source Solver AI for Java and Kotlin to optimize scheduling and routing. Solve the vehicle routing problem, employee rostering, task assignment, maintenance scheduling and other planning p…
This repository contains my homework solutions for the Modern C++ for Computer Vision course at University of Bonn (WS 2023/24). The course covers modern C++ techniques and their application in com…
Code examples for Robotics, Vision & Control 3rd edition in Python
A web application to generate configuration files for the JSBSim Flight Dynamics Model.
Aircraft design optimization made fast through computational graph transformations (e.g., automatic differentiation). Composable analysis tools for aerodynamics, propulsion, structures, trajectory …
Simplifying reinforcement learning for complex game environments
Financial management SPA app created using ASP.NET Core, knockout.js and Typescript
For optimization algorithm research and development.
Python library to train neural networks with a strong focus on hydrological applications.
NLP Zero to Hero in just 10 Kernels
React.js + Three.js 3d room planner & product configurator(bundled version)
Open Source Routing Machine - C++ backend
The library for web and native user interfaces.
A python library for structural analysis and design
Base code for 15-462/662: Computer Graphics at Carnegie Mellon University
Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019