I am a fourth-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 and token mixing in measurement space;
• Continual learning and model merging under fixed budgets;
• Emerging interest in 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 IEEE TPAMI (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

Honors & Awards

• Top Reviewer, Conference on Neural Information Processing Systems (NeurIPS), 2026
• MRM Highlights Selection, Magnetic Resonance in Medicine, 2025
• Honor Student, M.S. in Electrical & Computer Engineering, University of Southern California, 2023

Experience

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

• Proved that self-attention on measurements approximates attention on the underlying signal under RIP-style conditions, and established a “global analysis, local reconstruction” design principle for encoder-decoders
• Derived a pre-training diagnostic that predicts when attention beats uniform mixing from a conditional-variance statistic

Johns Hopkins University, Baltimore, MD, 2025 - Present
Graduate Research Assistant — Memory-Bounded Continual Learning;
Advisors: Prof. Trac D. Tran & Prof. Vishal M. Patel;
Research experience:

• Developed sparse consolidation of task adapters into a fixed-size store, with a compressed-sensing forecast of how far back stored adaptations remain recoverable
• Benchmarked against parameter-efficient and merging baselines on ImageNet-R and OmniBench-1K over horizons up to 100 tasks

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:

• Built calibration-free sparse recovery for fluorescence imaging through coded-aperture optics, reaching ~10x speedup over iterative baselines
• Extended the framework to region-of-interest reconstruction for real-time neuron imaging in deep-brain applications

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

• Reformulated autoregressive generation as a Markov process over overlapping tensors with a discrete tensor-noising scheme, connecting iterative refinement to discrete diffusion
• Designed an acceptance-gated correction policy for frozen AR generators that preserves well-tuned samples while repairing degraded ones

Teaching

• EN.520.646 Wavelets and Filter Banks
  Teaching Assistant, Fall 2026, Johns Hopkins University
• EN.520.651 Random Signal Analysis
  Teaching Assistant, Fall 2024 & Fall 2025, Johns Hopkins University

Service

• Reviewer, Conference on Neural Information Processing Systems (NeurIPS), 2026 — Top Reviewer
• Reviewer, International Conference on Learning Representations (ICLR), 2027
• Reviewer, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 - Present
• Reviewer, UniReps Workshop, NeurIPS, 2026