Research

In July 2025, I joined BruinML as an Applied Researcher and soon became the president of the group in 2026. Since then, I’ve co-authored a handful of papers which you can check out below!

For course and personal projects, see the Projects page.

Selected Work

1. Accelerating Low-Frequency Convergence for Limited-Angle DBT via Two-Channel Fidelity in PDHG (CT Meeting 2026)
   Taro Iyadomi, Ricardo Parada, Anna Kim, Lily Jiang, Emil Sidky, William Chang
   Enhanced Chambolle-Pock algorithm with two-channel approach for breast cancer detection, achieving faster convergence while maintaining reconstruction quality on simulated breast phantoms. Selected for Oral Presentation CT-Meeting 2026.
   arXiv | GitHub | PDF

Preprints

1. Accelerated Proximal Optimization in Wasserstein and Sobolev Spaces (2026)
   William Chang, Taro Iyadomi, Tianyu Wang
   PDF

2. Curvature-Dependent Optimization of Deep Linear Networks on Riemannian Manifolds (2026)
   Zhixuan Li, Taro Iyadomi, Luke Jones, Sean He, Muztaba Syed, William Chang, Bo Xiong
   PDF

3. Beyond Weisfeiler–Lehman: Topological Features Increase Graph Neural Network Expressivity (2026)
   Luke Jones, Lucas Schardt, Aaditya Bilakanti, Taro Iyadomi, William Chang
   PDF

4. Curvature-Aware Pointmap Regression for 3D Reconstruction (2026)
   Taro Iyadomi, Jiayi Liwei, Max Bregler, William Chang
   PDF

5. ZoomQ: Adaptive Action Discretization for Continuous-Action RL (2026)
   Taro Iyadomi, Larissa Xu, Khang Nguyen, Ricardo Parada, William Chang, Senthil Yogamani
   PDF

6. Learnable Obfuscation for Temporally Related Video Data (2026)
   Taro Iyadomi, Solomon Xu, Rain Chai, Landon Mulford, William Chang, Nader Sehatbakhsh
   PDF

7. Thompson Sampling for Pure Exploration in Graph-Structured Bandits (2026)
   Taro Iyadomi, Larissa Xu, Chenzhang Zhao, William Chang
   PDF

* Alphabetical authorship