Summary of Research
My research focuses on using machine learning for solving inverse problems in imaging and physics. I am particularly interested in unsupervised learning and generative modeling for scientific and medical imaging. I want to apply these tools and techniques in realistic scenarios, where training data is often highly limited or nonexistent. I believe that developing improved computational methods for this challenging problem setting may ultimately enable new scientific discoveries.
Publications
* indicates equal contribution.
Preprints:
2. Yuanyun Hu, E. Bell, Guijin Wang, and Yu Sun. PRISM: Probabilistic and Robust Inverse Solver with Measurement-Conditioned Diffusion Prior for Blind Inverse Problems. arXiv preprint arXiv:2509.16106, 2025.
1. Ismail Alkhouri*, E. Bell*, Avrajit Ghosh*, Shijun Liang, Rongrong Wang, and Saiprasad Ravishankar.Understanding Untrained Deep Models for Inverse Problems: Algorithms and Theory. arXiv preprint arXiv:2502.18612, 2025.
Journal Articles:
3. E. Bell, Daniel A. Serino, Ben S. Southworth, Trevor Wilcox, and Marc Klasky. Learning robust parameter inference and density reconstruction in flyer plate impact experiments. Scientific Reports, 2025.
2. Daniel A. Serino, E. Bell, Marc Klasky, Ben S. Southworth, Balasubramanya Nadiga, Trevor Wilcox, and Oleg Korobkin. Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions. Scientific Reports, 2025.
1. Shijun Liang*, E. Bell*, Qing Qu, Rongrong Wang, and Saiprasad Ravishankar. Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction. IEEE Transactions on Computational Imaging, 2025.
Conference Proceedings:
5. E. Bell*, Shijun Liang*, Ismail Alkhouri, and Saiprasad Ravishankar. Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction. IEEE Asilomar Conference on Signals, Systems, and Computers, 2025.
4. Shijun Liang*, E. Bell*, Avrajit Ghosh, and Saiprasad Ravishankar. Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization. IEEE Asilomar Conference on Signals, Systems, and Computers, 2024.
3. Ismail Alkhouri*, Shijun Liang*, E. Bell, Qing Qu, Rongrong Wang, and Saiprasad Ravishankar. Image Reconstruction via Autoencoding Sequential Deep Image Prior. Advances in Neural Information Processing Systems (NeurIPS), 2024.
2. E. Bell, Michael T. McCann, and Marc Klasky. Supervised Reconstruction for Silhouette Tomography. Electronic Imaging, 2024.
1. E. Bell*, Shijun Liang*, Qing Qu, and Saiprasad Ravishankar. Robust Self-Guided Deep Image Prior. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.
Awards
- NSF Graduate Research Fellowship (GRFP), 2025 (declined for CSGF)
- Ferdinand Hamburger, Jr. Fellowship in Electrical Engineering, 2025
- Michigan State University Alumni Distinguished Scholarship, 2020-2024
- Michigan State University Board of Trustees Award, 2024
- Dr. Paul and Wilma Dressel Endowed Scholarship, 2022 and 2024
- Best Presentation Award, LANL Theoretical Division Student Symposium, 2023
- Dr. Marshall and Barbara Hestenes Endowed Scholarship, 2023
- R.E. Phillips Memorial Scholarship, 2021