Hsun-Yu Kuo

I am an M.Sc. student in Computer Science at EPFL, specialising in computer science theory. My research interests include data-centric AI, reinforcement learning, robustness, extrapolation, and causality. More broadly, I am interested in how diversity can help shape better AI systems and a better society.

I am currently a project student at the MLO Lab at EPFL, where I work with Martin Jaggi and El Mahdi Chayti. Previously, I interned with the Robust Machine Learning Group at the Max Planck Institute for Intelligent Systems and the CKIP Lab at Academia Sinica.

Feel free to reach out if you would like to discuss research or potential collaboration.

News

Aug-Sep 2026	I will attend the 50th Machine Learning Summer School (MLSS 2026) in Tübingen, Germany, from August 31 to September 11, 2026.
Jul 2026	I presented our paper, “Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping”, as a poster at the ICML 2026 Workshop on Resource-Adaptive Foundation Model Inference (AdaptFM).
Aug 2025	Gave a talk on synthetic data weighting at the Guided Generation Group (GGG).
Jan 2025	Our paper, “Not All LLM-Generated Data Are Equal”, was accepted to ICLR 2025 and selected as a Spotlight.

Selected Publications

Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping

Hsun-Yu Kuo, El Mahdi Chayti, Patrik Reizinger, and 2 more authors

In ICML 2026 Workshop on Resource-Adaptive Foundation Model Inference, 2026

Bib Website

@inproceedings{kuo2025looped,
  title = {Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping},
  author = {Kuo, Hsun-Yu and Chayti, El Mahdi and Reizinger, Patrik and Brendel, Wieland and Jaggi, Martin},
  booktitle = {ICML 2026 Workshop on Resource-Adaptive Foundation Model Inference},
  year = {2026},
  url = {https://arxiv.org/abs/2606.29983},
}

ICLR ’25

Spotlight

Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification

Hsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao, and 2 more authors

Proceedings of the 13th International Conference on Learning Representations, 2025

Spotlight (top 5.1%)

Bib Website

@article{kuo2025llmgenerated,
  title = {Not All {LLM}-Generated Data Are Equal: Rethinking Data Weighting in Text Classification},
  author = {Kuo, Hsun-Yu and Liao, Yin-Hsiang and Chao, Yu-Chieh and Ma, Wei-Yun and Cheng, Pu-Jen},
  journal = {Proceedings of the 13th International Conference on Learning Representations},
  year = {2025},
  note = {Spotlight (top 5.1\%)},
  url = {https://openreview.net/forum?id=oI5tZaWkF9},
}