Skip to content
View yh-yao's full-sized avatar
🪴
Grow strong
🪴
Grow strong
30 followers · 6 following

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Starstruck

Achievements

Achievement: Pull Sharkx2Achievement: YOLOAchievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: Starstruck

Block or report yh-yao

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
yh-yao/README.md

Google Scholar GitHub

Agents Reasoning PostTraining Federated Learning

Hi 👋 I'm Yuhang Yao

🔬 Researcher working on LLM agents, reasoning systems, scalable agent infrastructure, and post-training.

🎓 PhD from Carnegie Mellon University

🌐 Homepage: https://yuhangyao.com 📫 Email: [email protected]

🚀 Selected Projects

DIG — Dynamic Decision Paths for Agent Collaboration https://happyeureka.github.io/dig/

GAP — Graph-Based Agent Planning with Parallel Tool Use https://github.com/WJQ7777/Graph-Agent-Planning

FedGraph — Federated Graph Learning Framework https://github.com/FedGraph/fedgraph

FedGCN — Federated Graph Convolutional Networks https://github.com/yh-yao/FedGCN

📄 Selected Research

Agent Systems

arXiv DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths

arXiv GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning

arXiv Toward Super Agent Systems with Hybrid AI Routers

arXiv TensorOpera Router: A Multi-Model Router for Efficient LLM Inference

arXiv ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency

Federated Graph Learning

arXiv
FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks
NeurIPS 2023

arXiv
FedGraph: A Research Library and Benchmark for Federated Graph Learning

📚 Book

Build AI Agents from Scratch: LLM‑Driven Agent Design and Practice

https://github.com/yh-yao/super_agent_book

Pinned Loading

  1. FedGCN FedGCN Public

    Official Code for FedGCN [NeurIPS 2023]

    Jupyter Notebook 75 15

  2. FedGraph/fedgraph FedGraph/fedgraph Public

    FedGraph (Federated Graph) is a library built upon PyTorch to easily train Graph Neural Networks under federated setting.

    Python 70 5

  3. FedRule FedRule Public

    Official Code for FedRule: Federated Rule Recommendation System with Graph Neural Networks

    Python 14 4

  4. awesome-rl-ai-agents awesome-rl-ai-agents Public

    A curated list of recent progress and resources on Reinforcement Learning for AI Agents.

    5 1

  5. awesome-edge-ai-agents awesome-edge-ai-agents Public

    Curated list of papers, frameworks, benchmarks, and applications for multimodal AI agents (LLMs, text-to-image, speech, world models, etc.) on mobile and edge devices.

    7 3

  6. awesome-federated-large-language-models awesome-federated-large-language-models Public

    A curated list of resources on Federated Large Language Models (FedLLMs) – an emerging paradigm that trains or adapts large language models (LLMs) across distributed data sources while preserving p…

    1