Hoang M. Truong

Trương Minh Hoàng 🇻🇳

Hi! I’m a recent graduate from the University of Science, Viet Nam National University Ho Chi Minh City (VNU-HCM).

I am interested in how machines can understand and interact with the real world. My research focuses on vision-language models, egocentric (first-person) video understanding, and robotics foundation models, with the goal of building scalable and robust AI systems capable of cross-modal understanding and real-world interaction.

Publications

vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

Khanh D. Nguyen, Hoang M. Truong, An T. Le

Under Review

Summary We present vla.simd, which accelerates CPU inference by a median 1.4× over compiled PyTorch, and introduce IMPACT, a language-conditioned ACT policy supplying at least 30 actions/s on Raspberry Pi 5.

Website GitHub arXiv

Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation

Hoang M. Truong, Hai Nguyen-Truong, Dang Huynh

CVPR Workshop 2026

Summary We improve open-vocabulary segmentation through hyperbolic rotation and fine-tuning, aligning visual and textual semantics while preserving hierarchical structure.

Website GitHub arXiv

Dual-Path Enhancements in Event-Based Eye Tracking: Augmented Robustness and Adaptive Temporal Modeling

Hoang M. Truong, Vinh-Thuan Ly, Thuan-Phat Nguyen, Huy G. Tran, Tram T. Doan

CVPR Workshop 2025

Summary We improve event-based eye tracking through robust data augmentation and adaptive temporal modeling, handling abrupt eye movements and sparse, noisy inputs.

Paper arXiv

TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints

Vinh-Thuan Ly, Hoang M. Truong, Xuan-Huong Nguyen

ICCV Workshop 2025

Summary We combine RGB and depth through a Mixture-of-Experts module, enabling a lightweight vision-language model to match larger systems on evaluated warehouse spatial reasoning tasks.

Website arXiv