Vu (Anthony) Le

I'm a first year Computer Science PhD student in the University of Massachusetts Amherst, where I am advised by VP Nguyen on quantum computing. I also work at the Accelerator Technology & Applied Physics division at Berkeley Lab on scalable ML-powered FPGA-based quantum control for superconducting quantum bits as an affiliate student. I am also interested in quantum machine learning with a focus on quantum neural networks.

Prior to joining UMass Amherst, I had the pleasure of working with Bo Han on neural rendering for immersive telepresence systems and amazing industry folks on face identification using vision transformers. I gained valuable hands on experience working as a software and AI engineer along the way.

My CV will be available upon request.

Contact:

Scholar  /  Github  /  LinkedIn  /  Blogs

profile photo

News

  • 01/2025: I open sourced my GitHub repository and tutorials for the QubiC quantum control system
  • 12/2024: I officially become a research affiliate with Berkeley Lab.
  • 09/2024: My new academic website with the .us (United States) domain is live now.
  • 09/2024: One paper accepted at ACM SenSys 2024.
  • 09/2024: I joined University of Massachusetts Amherst, USA as a PhD student.
  • 01-04/2024: I received multiple offers to pursue my CS PhD in the USA.
  • 10/2023: One paper accepted at IEEE/CVF WACV.
  • 06/2022: I graduated with a bachelor degree from Vietnam National University, Hanoi.

Selected Research

I'm interested in quantum computing, computer architecture, deep learning, and scalable networked systems. Most of my research is about computer systems, systems and computer vision applications. Some papers are highlighted.

blind-date MagicStream: Bandwidth-conserving Immersive Telepresence via Semantic Communication
Ruizhi Cheng, Nan Wu, Vu Le, Eugene Chai, Matteo Varvello , Bo Han
ACM SenSys 2024,   (A* conference)
project page  /  paper

MagicStream, a first-of-its-kind semantic-driven immersive telepresence system that effectively extracts and delivers compact semantic details of captured 3D representation of users, instead of traditional bit-by-bit communication of raw content.

blind-date Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers
Hai Phan, Cindy Le, Vu Le, Yihui He, Anh Totti Nguyen
CVF/WACV 2024   (A conference)
project page  /  paper  /  code  /  poster  /  presentation

Using vision transformers for out-of-distribution data face identification, runs twice faster while achieving comparable performance with the state of the art DeepFace-EMD model.

Miscellanea

Apart from being a researcher, I'm also an experienced software and devops engineer. I enjoy building scalable backend systems that can handle large traffics.

Web Traffic

Thanks Jon Barron for the website template.