Weirui Kuang
多智能体系统 · AgentScope · CoPaw
海有舟可渡，山有路可行
I am a researcher at Tongyi Lab, Alibaba Group, where I focus on pushing the boundaries of artificial intelligence through innovative research and open-source contributions. My work spans multiple cutting-edge domains in machine learning.
Developing efficient architectures for large-scale graph neural networks, including transformer-based models for massive graphs.
Building comprehensive frameworks for privacy-preserving machine learning, from traditional FL to large language model fine-tuning.
Creating scalable platforms for multi-agent applications, enabling developers to build complex AI systems with ease.
Core Maintainer
Personal AI Assistant that works for you and grows with you. Easy to install, deploy locally or on cloud, supports multiple chat platforms with extensible skills.
Core Maintainer
Production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, and full-stack observability.
Core Developer
Multi-agent platform for building LLM-powered applications with flexible architectures and comprehensive tooling.
Core Developer
Comprehensive federated learning platform supporting traditional FL, graph FL, and LLM fine-tuning with privacy preservation.
Senior Machine Learning Engineer
Research Intern
Research Intern
Mathematics and Applied Mathematics
Our paper "FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning" accepted by KDD 2024
AgentScope WorkStation, a drag-and-drop multi-agent development platform, is now online!
"Coarformer: Transformer for large graph via graph coarsening" accepted by TKDE
🏆 FederatedScope-GNN wins Best Paper Award at KDD 2022 ADS Track