Hai Nguyen-Truong
|
I am an incoming PhD student at Northeastern University, where I am fortunate to be advised by Prof. Lorenzo Torresani. Previously, I obtained my MPhil in Computer Science and Engineering from HKUST under the supervision of Prof. Sai-Kit Yeung, following a B.S. in Computer Science (Advanced Program) with highest distinction (GPA: 3.93/4.0) from the University of Science, VNU - HCM, guided by Assoc. Prof. Minh-Triet Tran.
Currently, my work targets the development of World Foundation Multimodal Models capable of discovering the underlying physical laws and causal relationships within multimodal data.
📚 Featured Publications
TransCues introduces an efficient transformer-based segmentation architecture capable of handling transparent, reflective, and general objects. By proposing Boundary Feature Enhancement (BFE) and Reflection Feature Enhancement (RFE), we enable the model to better capture subtle details in both glass and non-glass regions, resulting in more accurate and robust segmentation.
VATEX is a novel method for referring image segmentation that leverages vision-aware text features to improve text understanding. By decomposing language cues into object and context understanding, the model can better localize objects and interpret complex sentences, leading to significant performance gains.
SegTransVAE is the first work exploiting the hybrid architecture between CNN, Transformers with the Variational Autoencoder (VAE) branch to the network to reconstruct the input images jointly with segmentation.
🔥 News
- 2025.11 🎯 Paper Accepted! Our paper "TransCues" was accepted to WACV 2026.
- 2025.08 🚀 New Role! Joined Fulbright University Vietnam as a Research Assistant.
- 2025.06 🏆 Best Poster Presentation Award at AVSTC - Joint recognition from the Australian Govt, UTS, and PTIT.
- 2024.11 🚀 New Role! Joined Huawei Hong Kong Research Center.
- 2024.10 🎯 Paper Accepted! My first paper "VATEX" was accepted to WACV 2025.
💻 Experience
Research Assistant in Computer Vision
2025.08 - Current | Fulbright University Vietnam
- Conducted research on Video Diffusion Models, focusing on Physical Plausibility of Video Generation.
- Host weekly meeting and research seminar in our CV group.
- Assist junior student in Capstone and Thesis project on Computer Vision.
AI Research Engineer
2024.11 - 2025.04 | Huawei Hong Kong Research Center
- Contributing to MindONE project, focusing on multimodal/multitask generation models and optimizing it on Ascend NPU.
Research Resident
2022.03 - 2022.07 | VinAI Research
- Conducted research in spatio-temporal tasks: video instance/panoptic segmentation, 4D point cloud panoptic segmentation.
🎖 Honors, Awards & Competitions
Academic
- 2025 Best Poster Presentation Award at AVSTC
- 2024 UGC Research Travel Grant - HKUST
- 2022-2024 Postgraduate Scholarship (PGS) - HKUST
- 2022 Merit Award for Highest Distinction
- 2022 Third Prize, EURÉKA
Competitions & Math
- 2023 & 2024 🥈 Runner-up - Maritime CV Workshop (WACV)
- 2020 🥇 First Prize - MediaEval Sports Video Classification
- 2021 🥇 First Prize - Ho Chi Minh AI Challenge
- 2017 & 2018 🥉 Third Prize - Vietnamese Math Olympiads
- 2015 & 2016 🥇 Gold Medal - April 30th Math Olympiad