Allen Tu

I am a Ph.D. student in Computer Science at the University of Maryland, College Park, advised by Professor Tom Goldstein. My research focuses on building efficient, reliable, and scalable vision systems for real-world environments, spanning 3D/4D reconstruction, multimodal biometric recognition, and generative modeling. A central theme of my work is selective computation: developing methods that determine what to compute, what to trust, and when additional modeling capacity is most useful under limited data, distribution shift, and finite computational budgets. Much of my recent work centers on making 3D and 4D Gaussian Splatting substantially smaller and faster while preserving visual fidelity and reliability, and more broadly on unifying efficiency, reliability, and interpretability in vision systems.

I have published at leading computer vision venues including CVPR and FG, with contributions spanning efficient 3D/4D scene representations, uncertainty-aware modeling, selective generative refinement, and biometric recognition. My research is shaped by collaborations across academia and industry, including prior work at Systems & Technology Research (STR), and is applied to challenging problems in 3D reconstruction and biometrics. I previously mentored undergraduate researchers as a Peer Research Mentor in the FIRE: Capital One Machine Learning program and co-organize the inaugural SPAR-3D Workshop on security, privacy, and adversarial robustness in 3D generative vision models at CVPR 2026. I received my B.S./M.S. in Computer Science from the University of Maryland in 2024.

CV and publications: tuallen.github.io