Yuyang Hu

Email h.yuyang@wustl.edu

Location St. Louis, MO

Google Scholar Profile

I am a Research Scientist at Google’s Computational Imaging Team (LUMA) and a Ph.D. student in Electrical Engineering at Washington University in St. Louis, advised by Prof. Ulugbek Kamilov. I was a Research Intern at Mitsubishi Electric Research Laboratories (MERL) and a Student Researcher at Google before joining full-time.

My research focuses on computational imaging, Image/Video Generative Model, and deep learning. I develop fast, efficient, and interpretable algorithms for solving large-scale imaging problems. My recent work spans:

Inference-time Scaling for diffusion models in image restoration (NeurIPS 2025)
Plug-and-play priors by generalizing regularization-by-denoising to leverage pre-trained restoration networks (ICLR 2024, ICML 2025)
Multimodal diffusion models for satellite image cloud removal (IEEE TGRS)

Research Interests: Image/Video Generative Model, Computational Imaging, Inverse Problems, Image Restoration, Deep Learning

news

Dec 01, 2025	Joined Google as a Research Scientist in the Computational Imaging Team (LUMA).
Nov 01, 2025	Our paper “Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration” was accepted to NeurIPS 2025.
May 01, 2025	Our paper “Stochastic Deep Restoration Priors for Imaging Inverse Problems” was accepted to ICML 2025.
Feb 01, 2025	Joined Google as a Student Researcher in the Computational Imaging Team (LUMA), hosted by Dr. Mauricio Delbracio.
May 01, 2024	Joined Mitsubishi Electric Research Laboratories (MERL) as a Research Intern in the Computer Vision Group, hosted by Dr. Suhas Lohit.

selected publications

arXiv

ADOBI: Adaptive Diffusion Bridge for Blind Inverse Problems with Application to MRI Reconstruction

Yuyang Hu, Albert Peng, Wei Gan, and 1 more author

arXiv preprint, 2024

arXiv Bib

@article{hu2025adobi,
  title = {ADOBI: Adaptive Diffusion Bridge for Blind Inverse Problems with Application to MRI Reconstruction},
  author = {Hu, Yuyang and Peng, Albert and Gan, Wei and Kamilov, Ulugbek S.},
  journal = {arXiv preprint},
  volume = {2411.16535},
  year = {2024},
}

NeurIPS

Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration

Yuyang Hu, Kaixuan Mei, Morteza Sahraee-Ardakan, and 3 more authors

In Advances in Neural Information Processing Systems (NeurIPS), 2025

arXiv Bib

@inproceedings{hu2025kds,
  title = {Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration},
  author = {Hu, Yuyang and Mei, Kaixuan and Sahraee-Ardakan, Morteza and Kamilov, Ulugbek S. and Milanfar, Peyman and Delbracio, Mauricio},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
}

IEEE TGRS

Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal

Yuyang Hu, Suhas Lohit, Ulugbek S. Kamilov, and 1 more author

IEEE Transactions on Geoscience and Remote Sensing, 2024

arXiv Bib

@article{hu2024tgrs,
  title = {Multimodal Diffusion Bridge with Attention-Based SAR Fusion for Satellite Image Cloud Removal},
  author = {Hu, Yuyang and Lohit, Suhas and Kamilov, Ulugbek S. and Marks, Tim K.},
  journal = {IEEE Transactions on Geoscience and Remote Sensing},
  year = {2024},
}

ICML

Stochastic Deep Restoration Priors for Imaging Inverse Problems

Yuyang Hu, Albert Peng, Wei Gan, and 3 more authors

In International Conference on Machine Learning (ICML), 2025

arXiv Bib

@inproceedings{hu2025shaarp,
  title = {Stochastic Deep Restoration Priors for Imaging Inverse Problems},
  author = {Hu, Yuyang and Peng, Albert and Gan, Wei and Milanfar, Peyman and Delbracio, Mauricio and Kamilov, Ulugbek S.},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
}