I am a third year PhD student in the Electrical and Computer Engineering Department at Johns Hopkins University, under the guidance of Professor Trac D. Tran.

Before joining JHU, I completed my Master’s degree in Electrical and Computer Engineering at the University of Southern California, working closely with Prof. Justin Haldar. Prior to that, I earned my B.S. in Automation at Xi’an Jiaotong University in China.

To know more about me, here is my CV.

Research Interest

My current research focuses on:

• Inverse problems and sparse recovery;
• Computational imaging;
• Generative modeling (diffusion, flow matching, autoregressive);
• Attention mechanisms in measurement space;
• Physics-constrained latent dynamics and world models.

Selected Publications

From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
C. Cheng, L. Song, Di An, Y. Xiao, X. Zhang, H. Sun, Y. Shan
International Conference on Learning Representations (ICLR), 2026

TRUST: Transformer-Driven U-Net for Sparse Target Recovery
Di An, D. Poppert, J. Li, M. Foster, T. D. Tran
Under review at ICLR, 2026 (arXiv:2506.01112)

Region-of-Interest Sparse Reconstruction for Lensless Coded-Aperture Optical Imaging
Di An, D. Poppert, J. Li, J. Pham, B. Sun, M. Foster, T. D. Tran
59th Asilomar Conference on Signals, Systems, and Computers, 2025

The “hidden noise” problem in MR image reconstruction
Jiayang Wang, Di An, Justin P. Haldar
Magnetic Resonance in Medicine, 2024 (Selected as MRM Highlights, 2025)

A full list is available on my publications page.

Education

Johns Hopkins University, 2023 - Present;
Ph.D in Electrical and Computer Engineering

University of Southern California, 2021 - 2023;
MS in Electrical and Computer Engineering, Awarded as Honor Student

Xi’an Jiaotong University, 2016 - 2020;
BS in Automation

Experience

Johns Hopkins University, Baltimore, MD, 2024 - Present
Graduate Research Assistant — Attention-Guided Sparse Recovery;
Advisor: Prof. Trac D. Tran;
Research experience:

• Formulated an attention-guided sparse recovery framework with provable RIP-style guarantees
• Designed TRUST, a hybrid ViT-encoder/U-Net-decoder for sparse target recovery

Johns Hopkins University, Baltimore, MD, Sep. 2023 - Present
Graduate Research Assistant — Lensless Epi-Fluorescent Microendoscopy;
Advisors: Prof. Trac D. Tran & Prof. Mark A. Foster;
Research experience:

• Developed calibration-free sparse recovery for fluorescence imaging through coded-aperture optics
• Built learning-based reconstruction pipelines with ~10x speedup over iterative baselines

Tencent, Shenzhen, China, 2024 - Present
Research Collaborator — Refinement for Autoregressive Image Generation;
Research experience:

• Reformulated autoregressive generation as a Markov process over overlapping tensors
• Designed a discrete tensor noising scheme connecting the mechanism to discrete diffusion

University of Southern California, Los Angeles, May. 2022 - May. 2023
Research Assistant, Biomedical Imaging Group;
Advisor: Prof. Justin Haldar;
Research experience:

• Revealed the hidden-noise pitfall biasing full-reference metrics in MR image reconstruction
• Derived a noncentral-chi error metric improving hyperparameter selection

School of Computing at NUS, Singapore, Jul. 2019 - Aug. 2019
Summer School, Tele-Robot & Deep-Learning;
Advisor: Prof. SOO Yuen Jien;
Research experience:

• Used Raspberry Pi and Arduino communicating with each other to control a tele-robot
• Implemented SLAM into the tele-robot to achieve mapping ability
• Trained a neural network for the tele-robot to recognize obstacles in its path

Teaching

• EN.520.651 Random Signal Analysis
  Teaching Assistant, Fall 2024 & Fall 2025, Johns Hopkins University

Service

• Reviewer, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
• Reviewer, Conference on Neural Information Processing Systems (NeurIPS)