CV
A PDF version of my CV is available here.
Research Interests
Inverse problems and sparse recovery; computational imaging; generative modeling (diffusion, flow matching, autoregressive); attention mechanisms in measurement space; emerging interest in physics-constrained latent dynamics and world models.
Education
- Ph.D in Electrical & Computer Engineering, Johns Hopkins University, 2023 - Present
- Advisor: Prof. Trac D. Tran
- Selected coursework: Optimization in Data Science, Matrix Analysis, Random Matrix Theory, Probability Theory, Equivariant Machine Learning, Compressed Sensing, Wavelets
- M.S. in Electrical & Computer Engineering, University of Southern California, 2021 - 2023
- Advisor: Prof. Justin P. Haldar
- Honor Student
- B.S. in Automation, Xi’an Jiaotong University, 2016 - 2020
Research Experience
- 2024 - Present: Graduate Research Assistant — Attention-Guided Sparse Recovery
- Johns Hopkins University (Advisor: Prof. Trac D. Tran)
- Formulated an attention-guided sparse recovery framework: proved that self-attention computed on measurements y approximates attention on the underlying signal x under RIP-style conditions, yielding a bound on attention error.
- Designed TRUST, a hybrid ViT-encoder/U-Net-decoder with adaptive pooling and attention-guided skip connections coupling global support estimation with local detail refinement.
- Achieved consistent gains over U-Net, TransUNet, and Restormer across ImageNet-mask, FastMRI, and fiber microendoscope datasets while reducing hallucinations.
- Sep 2023 - Present: Graduate Research Assistant — Lensless Epi-Fluorescent Microendoscopy
- Johns Hopkins University (Advisors: Prof. Trac D. Tran & Prof. Mark A. Foster)
- Developed calibration-free sparse recovery (ElasticNet for sensing-matrix estimation, OMP for reconstruction) for fluorescence imaging through coded-aperture optics.
- Designed learning-based reconstruction pipelines with ~10x speedup over iterative baselines with higher image quality and fewer hallucinations.
- Extended the framework to region-of-interest reconstruction for real-time neuron imaging in deep-brain applications.
- 2024 - Present: Research Collaborator — Refinement for Autoregressive Image Generation (TensorAR / AGR)
- Tencent, Shenzhen (with Cheng Cheng)
- Reformulated autoregressive generation as a Markov process over overlapping tensors and derived the next-tensor factorization, enabling iterative refinement while preserving causal masking.
- Designed a discrete tensor noising scheme that eliminates copy-through leakage across overlaps, connecting the mechanism to discrete diffusion via a weighted cross-entropy objective.
- Ongoing work explores a bidirectional refiner attached to open-source AR backbones, targeting near-training-free deployment for video extension.
- May 2022 - May 2023: Research Assistant — Noise-Aware MRI Reconstruction
- Biomedical Imaging Group, University of Southern California (Advisor: Prof. Justin P. Haldar)
- Revealed the hidden-noise pitfall: rSoS “reference” images bias full-reference metrics (RMSE/SSIM), leading to mis-ranked reconstructions and suboptimal tuning.
- Derived a noncentral-chi error (NCE) metric from the NCC negative log-likelihood for non-prewhitened data, with a zero-point normalization for cross-scan comparability.
- Implemented parameter estimation from background regions, improving hyperparameter selection over noisy RMSE/SSIM.
Teaching Experience
- Teaching Assistant, EN.520.651 Random Signal Analysis, Johns Hopkins University, Fall 2024 & Fall 2025
- Led discussion sections, designed and graded problem sets and exams, and held weekly office hours for graduate students.
Publications
C. Cheng, L. Song, D. An, Y. Xiao, X. Zhang, H. Sun, Y. Shan. (2026). "From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation." International Conference on Learning Representations (ICLR).
D. Poppert, D. An, T. D. Tran. (2025). "Attention Networks for Spotlight SAR Motion Compensation." 59th Asilomar Conference on Signals, Systems, and Computers.
D. An, D. Poppert, J. Li, J. Pham, B. Sun, M. Foster, T. D. Tran. (2025). "Region-of-Interest Sparse Reconstruction for Lensless Coded-Aperture Optical Imaging." 59th Asilomar Conference on Signals, Systems, and Computers, pp. 1517-1521.
J. Li, D. An, M. Foster, T. D. Tran, et al. (2025). "A Minimally-Invasive Lensless Epi-Fluorescent Microendoscope Leveraging Learned Sensing." Under review at Optica.
D. Poppert, D. An, E. D. Jansing, T. D. Tran. (2025). "Motion Compensation for Synthetic Aperture Radar with the Vision Transformer." IEEE International Geoscience and Remote Sensing Symposium (IGARSS).
D. An, D. Poppert, J. Li, M. Foster, T. D. Tran. (2025). "TRUST: Transformer-Driven U-Net for Sparse Target Recovery." Under review at ICLR, 2026. arXiv:2506.01112.
J. Wang, D. An, J. P. Haldar. (2024). "The ‘hidden noise’ problem in MR image reconstruction." Magnetic Resonance in Medicine, 92(3), 982-996.
J. Wang, D. An, J. P. Haldar. (2023). "The problem of hidden noise in MR image reconstruction." Proc. International Society for Magnetic Resonance in Medicine (ISMRM).
Technical Skills
- Programming: Python (PyTorch, NumPy, SciPy), MATLAB, C/C++
- Methods: Optimization, sparse recovery, signal processing, generative modeling, deep learning
- Tools: Linux, Git, LaTeX, CUDA, multi-GPU training (DDP)
Professional Service
- Reviewer, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
- Reviewer, Conference on Neural Information Processing Systems (NeurIPS)
