Haoyuan Li

I am a PhD candidate at Eindhoven University of Technology (TU/e), working under the supervision of Prof. Aaqib Saeed and Mathias Funk.

My research focuses on decentralized AI and on-device learning, with an emphasis on developing data-centric intelligent systems that learn from multimodal sensory signals. This work aims to enable scalable and privacy-preserving AI solutions for healthcare and other real-world applications. My recent work explores agentic systems that assist and automate decentralized AI research, aiming to advance collaboration and autonomy in distributed learning environments. Prior to this, I completed my MSc in Computer Science at Uppsala University, where I specialized in scalable data engineering.

I am actively seeking research internship opportunities and welcome inquiries. Please feel free to reach me via Email.

news

Oct 15, 2025	Our latest work on the Agentic AI in automating decentralized AI systems is now on Arxiv!
Jun 20, 2025	We have two short papers accepted at TTODLer-FM @ ICML’25 and CFAgentic @ ICML’25!
May 19, 2025	Our full paper is accepted at IEEE Internet of Things Journal!

selected publications

2025

IoTJ

FAST: Federated Active Learning With Foundation Models for Communication-Efficient Sampling and Training

Haoyuan Li, Mathias Funk, Jindong Wang, and 1 more author

IEEE Internet of Things Journal, 2025

Short Paper @ Tiny Titans: The next wave of On-Device Learning for Foundational Models (TTODLer-FM) Workshop at ICML 2025.

Bib Website

@article{li2025fast,
  bibtex_show = {true},
  title = {FAST: Federated Active Learning With Foundation Models for Communication-Efficient Sampling and Training},
  author = {Li, Haoyuan and Funk, Mathias and Wang, Jindong and Saeed, Aaqib},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  publisher = {IEEE},
  note = {Short Paper @ <a href="https://ttodlerfm.gitlab.io/">Tiny Titans: The next wave of On-Device Learning for Foundational Models (TTODLer-FM) Workshop at ICML 2025</a>.},
}

2024

IEEE BigData

Collaboratively learning federated models from noisy decentralized data

Haoyuan Li, Mathias Funk, Nezihe Merve Gürel, and 1 more author

In 2024 IEEE International Conference on Big Data (BigData), 2024

Short Paper @ Data-centric Machine Learning Research Workshop at ICML 2024.

Bib Website

@inproceedings{li2024collaboratively,
  bibtex_show = {true},
  title = {Collaboratively learning federated models from noisy decentralized data},
  author = {Li, Haoyuan and Funk, Mathias and G{\"u}rel, Nezihe Merve and Saeed, Aaqib},
  booktitle = {2024 IEEE International Conference on Big Data (BigData)},
  pages = {7879--7888},
  year = {2024},
  organization = {IEEE},
  note = {Short Paper @ <a href="https://dmlr.ai/cfp-icml24/">Data-centric Machine Learning Research Workshop at ICML 2024</a>.},
}