Yuhang Yao
Building Super-Intelligent Agents
I am a Senior Research Engineer at Zoom, working on conversation intelligence, virtual agents, and post-training.
Previously, I was a founding research scientist at TensorOpera AI, where I helped build a production LLM agent system from 0 to 1M DAU. I earned my PhD in Computer Engineering from Carnegie Mellon University in 2024, advised by Prof. Carlee Joe-Wong, and completed my bachelor's degree in Computer Science (IEEE Honor Class) at Shanghai Jiao Tong University in 2019.
Open to collaboration on efficient agent systems. For conversations, feel free to reach out via LinkedIn or email.
News
| Jul 05, 2026 | Our VISTA coding benchmark was covered by 机器之心. |
|---|---|
| Jun 28, 2026 | Released the VISTA benchmark and leaderboard for visual spec-to-web-app coding agents; read the paper. |
| Nov 10, 2025 | Graph based Agent Planning, GAP are accepted by NeurIPS workshop Nora. |
| Nov 01, 2025 | FedGraph and FedLink are accepted by NeurIPS workshop NPGML. |
| Aug 04, 2025 | Gave an 1-min talk at Berkeley Agentic AI Summit! Finished 10K (6.2 miles) at San Francisco Marathon! |
| May 09, 2025 | Got the A.G. Milnes Award 2025 (Best PhD Thesis Award at CMU ECE Department)!! |
| May 07, 2025 | Check my interview from MIT Technology Review and DeepTech Wechat Blog. |
| Mar 01, 2025 | Deployed the Super Agent System CoCo at ChainOpera Platform. |
| Jun 28, 2024 |
We have released pretrained LLM Fox-1-1.6B
and instruction version Fox-1-1.6B-Instruct-v0.1. Top-3 among Small Language Models!
|
| Feb 15, 2024 | We are developing FedGraph library for federated graph learning. |
| Feb 01, 2024 | I join TensorOpera AI as a research scientist for generative AI. |
| Dec 10, 2023 | FedGCN and WyzeRule are accepted by NeurIPS. FedML-HE gets accepted by FL-NeurIPS workshop. |
Selected Publications
2026
-
Federated large language models: Current progress and future directionsPacific-Asia Conference on Knowledge Discovery and Data Mining, 2026
2025
2024
-
-
Efficient Federated Graph Learning: Formulation, Algorithms and ApplicationsCarnegie Mellon University , 2024🏆 A.G. Milnes Award (Best Thesis Award)
2023
2022
-
A neural-based bandit approach to mobile crowdsourcingIn Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications , 2022