Yirong Shen 沈毅荣

Department of Electrical and Electronic Engineering

Imperial College London

London, United Kingdom

I am a PhD student in the Department of Electrical and Electronic Engineering at Imperial College London.

My research lies at the intersection of information theory and machine learning. I am broadly interested in the mathematical foundations of learning and inference, with a focus on generative modeling and statistical learning theory. My work explores how information-theoretic ideas can help us understand learning systems and develop principled methods. I am also interested in recent advances in machine intelligence and their practical applications.

Before my PhD, I largely squandered my odyssey years on CS:GO — perhaps not the most wisely spent years. ;( Check out my FACEIT profile.

Selected Publications

arXiv

One-Step Generative Modeling via Unbalanced Optimal Transport

Yirong Shen, Mengfei Xia, Junpeng Jing, and 2 more authors

arXiv preprint arXiv:2609.32708, Sep 2026

Bib HTML PDF

@article{shen2026onestep,
  title = {{One-Step Generative Modeling via Unbalanced Optimal Transport}},
  author = {Shen, Yirong and Xia, Mengfei and Jing, Junpeng and Gan, Lu and Ling, Cong},
  journal = {arXiv preprint arXiv:2609.32708},
  year = {2026},
  month = sep,
  archiveprefix = {arXiv},
  primaryclass = {cs.IT},
  url = {https://arxiv.org/abs/2609.32708},
}

ICML

Rényi Diffusion Models

Yirong Shen, Lu Gan, and Cong Ling

In Proceedings of the 43rd International Conference on Machine Learning, Jul 2026

Bib HTML PDF

@inproceedings{shen2026renyi,
  title = {{R{\'e}nyi Diffusion Models}},
  author = {Shen, Yirong and Gan, Lu and Ling, Cong},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning},
  pages = {110870--110911},
  year = {2026},
  month = jul,
  volume = {306},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v306/shen26g.html},
}

ISIT

Smoothing Linear Codes by Rényi Divergence and Applications to Security Reduction

Hao Yan, Yirong Shen, and Cong Ling

In 2026 IEEE International Symposium on Information Theory (ISIT), Jun 2026

DOI Bib HTML PDF

@inproceedings{yan2026smoothing,
  title = {{Smoothing Linear Codes by R{\'e}nyi Divergence and Applications to Security Reduction}},
  author = {Yan, Hao and Shen, Yirong and Ling, Cong},
  booktitle = {2026 IEEE International Symposium on Information Theory (ISIT)},
  pages = {1--6},
  year = {2026},
  month = jun,
  publisher = {IEEE},
  doi = {10.1109/ISIT62367.2026.11653870},
  url = {https://ieeexplore.ieee.org/document/11653870},
}

NeurIPS

Information Theoretic Learning for Diffusion Models with Warm Start

Yirong Shen, Lu Gan, and Cong Ling

In The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), Dec 2025

Bib HTML PDF

@inproceedings{shen2025information,
  title = {{Information Theoretic Learning for Diffusion Models with Warm Start}},
  author = {Shen, Yirong and Gan, Lu and Ling, Cong},
  booktitle = {The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  month = dec,
  url = {https://openreview.net/forum?id=3IbKbmNci3},
}

ISIT

Generalized Score Matching: Bridging f-Divergence and Statistical Estimation Under Correlated Noise

Yirong Shen, Lu Gan, and Cong Ling

In 2025 IEEE International Symposium on Information Theory (ISIT), Jun 2025

Bib HTML PDF

@inproceedings{shen2025generalized,
  title = {{Generalized Score Matching: Bridging $f$-Divergence and Statistical Estimation Under Correlated Noise}},
  author = {Shen, Yirong and Gan, Lu and Ling, Cong},
  booktitle = {2025 IEEE International Symposium on Information Theory (ISIT)},
  pages = {1--6},
  year = {2025},
  month = jun,
  organization = {IEEE},
  url = {https://ieeexplore.ieee.org/document/11195353},
}

News

Sep 26, 2026	Our preprint “One-Step Generative Modeling via Unbalanced Optimal Transport” is now available on arXiv.
Apr 28, 2026	Our paper “Rényi Diffusion Models” has been accepted by ICML 2026!
Mar 28, 2026	Our paper “Smoothing Linear Codes by Rényi Divergence and Applications to Security Reduction” has been accepted by IEEE ISIT 2026!

All news →