About Me

I am a second-year graduate student in Computer Science at the University of Maryland, College Park advised by Professor Tom Goldstein. I previously graduated with my BS in Computer Science and minor in Statistics from the University of Maryland in December 2022.

I am broadly interested in the intersection of deep learning, computer vision, and graphics. My recent work focuses on 3D scene reconstruction, and I am currently funded by the IARPA Walk-through Rendering from Images of Varying Altitude (WRIVA) program. Additionally, I have research and teaching experience in multimodal biometric recognition, large language models, vision encoders, generative adversarial networks, image quality metrics, and visualization recommendation.

Recent News

• November 2024: Transferring into the Computer Science PhD program at UMD in Spring 2025!
• September 2024: Published our PUP 3D-GS code and website.
• August 2024: Started my second year as a graduate student at UMD.
• June 2024: Released our PUP 3D-GS preprint to arXiv.
• May 2024: Returned to STR as a Computer Vision Research Intern.
• May 2024: Finished my BS/MS in Computer Science at UMD! 🎉 Extended to transfer to the PhD program.

Research Highlights

Hover to play video.	PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting Preprint, 2024. PAPER CODE Prune 90% of primitives from 3D Gaussian Splatting (3D-GS) scenes using a mathematically principled sensitivity pruning score, more than tripling rendering speed with minimal loss of visual fidelity and salient foreground information. Alex Hanson*, Allen Tu*, Vasu Singla, Mayuka Jayawardhana, Matthias Zwicker, Tom Goldstein
Hover to zoom in. Predict and Aggregate [1, 2] improves the CMC and ROC performance of the SOTA face recognition system by an empirical upper bound of 11.54% at the evaluation thresholds.	IARPA Biometric Recognition and Identification at Altitude and Range (BRIAR) Systems & Technology Research, 2022-2024. I researched face recognition, body recognition, and multimodal fusion for our SOTA system. Ask me about: Knowledge distillation for face probe-to-gallery feature similarity prediction. (2024) Feature clustering and aggregation for face recognition from videos. (2024) Training operating condition-invariant face encoders. (2023) Model ensembling and mixed-voting classifiers for open search. (2023) Data augmentation via garment transfer for training clothing-invariant body encoders. (2022) Mentors: Dr. Jennifer Xu, Prof. Vishal Patel, Prof. Rama Chellappa, Noam Eshed, Matthew Meyn, Dr. Mark Keck, Dr. Nathan Shnidman

Related Experience

I am always open to collaborations — please email me if you would like to chat or get involved!
See my CV for full details and other experiences.