🎉 CVPR 2025 🎉

I will be attending CVPR'25 from June 11-15 at the Music City Center in Nashville, TN to present PUP 3D-GS and Speedy-Splat at the main conference! Here are my scheduled appearances so far:

• June 11 (14:30-15:50): PUP 3D-GS will also be at the 4th Workshop on Uncertainty Quantification for Computer Vision (UNCV) poster session.
• June 13 (16:00-18:00): Come see PUP 3D-GS at Poster #48 in Exhibit Hall D!
• June 15 (10:30-12:30): Check out Speedy-Splat at Poster #46 in Exhibit Hall D!

My fellow PhD students, Alex Hanson and Yuanyuan Zhou, will also be attending. They are accomplished and approachable machine learning researchers who will be graduating soon and are actively seeking postdoctoral or industry positions. Feel free to reach out if you'd like to connect!

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 transferred to the PhD program in Spring 2025 after completing my BS/MS in Computer Science in 2024.

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.

News

• May 2025: Returned to STR as a Computer Vision Research Intern for the summer.
• February 2025: PUP 3D-GS and Speedy-Splat accepted to CVPR'25!
• January 2025: Transferred to the Computer Science PhD program at UMD! 🎉
• May 2024: Finished my BS/MS in Computer Science at UMD! 🎉

Research Highlights

	Speedy Deformable 3D Gaussian Splatting: Fast Rendering and Compression of Dynamic Scenes Preprint, 2025. PAPER CODE Achieve 10.38× faster rendering, 7.71× smaller model size, and 2.71× shorter training time for dynamic 3D Gaussian Splatting representations through temporal sensitivity pruning and flow-based Gaussian grouping. Allen Tu*, Haiyang Ying*, Alex Hanson, Yonghan Lee, Tom Goldstein, Matthias Zwicker
	Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives CVPR, 2025. PAPER POSTER VIDEO CODE Accelerate 3D Gaussian Splatting rendering speed by over 6× and reduce model size by over 90% through accurately localizing primitives during rasterization and pruning the scene 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 POSTER VIDEO CODE 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
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.	Biometric Recognition and Identification at Altitude and Range (IARPA BRIAR) Systems & Technology Research (STR), 2022-2025. I researched face recognition, body recognition, and multimodal fusion for our SOTA system. Ask me about: Recognizability prediction for face, body, and gait recognition. (2025) 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)

* denotes equal contribution.

Experience