About Me

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.

News

• February 2026: SpeeDe3DGS and SplatSuRe accepted to CVPR 2026! 🚀 🗺️
• December 2025: SPAR-3D Workshop accepted to CVPR 2026 in Denver! 🏔️
• December 2025: TransFIRA accepted to FG 2026 in Kyoto! ⛩️
• December 2025: I joined Rednote (小红书)! 🐼
• June 2025: Thank you for visiting PUP 3D-GS and Speedy-Splat at CVPR 2025 in Denver! 🎸

Research Highlights BibTeX References

	SpeeDe3DGS: Speedy Deformable 3D Gaussian Splatting with Temporal Pruning and Motion Grouping CVPR 2026 PAPER CODE WEBSITE Boost DeformableGS rendering speed from 20 to 276 FPS using temporal sensitivity pruning and groupwise SE(3) motion distillation, all while preserving the superior image quality of per-Gaussian neural motion. Allen Tu*, Haiyang Ying*, Alex Hanson, Yonghan Lee, Tom Goldstein, Matthias Zwicker
	SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting CVPR 2026 PAPER CODE WEBSITE Enhance 3D Gaussian Splatting by selectively injecting super-resolution only where high-frequency detail is missing, yielding sharper results and improved perceptual quality without introducing multi-view inconsistencies. Pranav Asthana, Alex Hanson, Allen Tu, Tom Goldstein, Matthias Zwicker, Amitabh Varshney
	TransFIRA: Transfer Learning for Face Image Recognizability Assessment FG 2026 PAPER CODE WEBSITE Redefine template-based recognition through encoder-grounded recognizability prediction that learns directly from embedding geometry via class-center similarity and angular separation, enabling principled filtering, calibrated weighting, and cross-modal explainability that surpass prior FIQA methods in accuracy, interpretability, and generality. Allen Tu, Kartik Narayan, Joshua Gleason, Jennifer Xu, Matthew Meyn, Tom Goldstein, Vishal Patel
	Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives CVPR 2025 PAPER CODE WEBSITE Accelerate 3D Gaussian Splatting rendering speed by 2× for free by accurately localizing primitives during rasterization and over 6× in total by pruning the scene by more than 90% during training, providing a significantly higher speedup than existing techniques while maintaining competitive image quality. Alex Hanson, Allen Tu, Geng Lin, Vasu Singla, Matthias Zwicker, Tom Goldstein
	PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting CVPR 2025 PAPER CODE WEBSITE Prune 90% of primitives from any pretrained 3D Gaussian Splatting model using a mathematically principled sensitivity score, more than tripling rendering speed while retaining more salient foreground information and higher visual fidelity than previous techniques at a substantially higher compression ratio. Alex Hanson*, Allen Tu*, Vasu Singla, Mayuka Jayawardhana, Matthias Zwicker, Tom Goldstein
	SPAR-3D: Security, Privacy, and Adversarial Robustness in 3D Generative Vision Models CVPR 2026 Workshop WEBSITE FLYER The SPAR-3D workshop brings together the 3D vision, AI security, and multimodal reasoning communities to advance robustness, traceability, and trustworthy 3D generative systems. Organizers: Nicole Meng, Yingjie Lao, Francis Engelmann, Ethan Rathbun, Shaoyi Huang, Allen Tu, Josué Martínez-Martínez, Dongjin Song, Faysal Hossain Shezan, Renjie Wan
	IARPA Walk-through Rendering from Images of Varying Altitude (WRIVA) UMIACS, August 2023 — Present. 3D/4D RESEARCH Unconstrained 3D reconstruction and novel view synthesis in challenging real-world environments. Efficient rendering, compression, and training methods for 3D and 4D Gaussian Splatting (3DGS/4DGS) [1, 2, 3] Multi-view consistent super-resolution for training 3DGS with low-resolution imagery Image, video, and multiview diffusion model priors for sparse-view 3D reconstruction Uncertainty quantification algorithms for 3DGS and Neural Radiance Fields (NeRF)
	IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) STR, June 2022 — January 2026. BIOMETRICS RESEARCH Multimodal fusion of incomplete face, body, and gait information in severe operational conditions. Transfer Learning for Face Image Recognizability Assessment Learned Frame Feature Aggregation for Face Recognition with Low-Quality Video Operating Condition-Invariant Barlow Twins and Multimodal Ensembling Style-Based Appearance Flow for Clothing-Robust Body Representation Learning

* denotes equal contribution.

Experience