Vu Le

A heterogeneous computing pipeline for real-time recurrent ML inference on a spatial AI accelerator. Independent computation is parallelized on an AI Engine array while the sequential state update (biggest bottnecks) runs in FPGA programmable logic, targeting a sub-microsecond latency budget. Matches a full-resolution feed-forward accuracy, which has millions of parameters, while outperformed prior deployed classifiers at a fraction of the hardware cost.

Detection and Tracking of Drone Swarms using LiDAR

Tasnim Azad Abir, Vu Le, Endrowednes Kuantama, Pranjol Sen Gupta, Austin Copley, Judith Dawes, Mohammad Islam, Richard Han, Phuc Nguyen

ACM MobiSys 2025 · A* conference

LiSWARM is a low-cost LiDAR system for accurate 3D tracking and recognition of drones in large swarms. Using point cloud processing, clustering, and neural networks, it achieves up to 98% accuracy and scales to 15,000 drones—enabling applications in airspace security, drone shows, and sensitive area monitoring.

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

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.