Turning Mathematical Rigor into Evaluated, Trustworthy AI Systems.
I am an undergraduate AI researcher and engineer in the Honors Program in Information Technology at the University of Science, Vietnam National University Ho Chi Minh City (VNU-HCM), where I maintain a 9.50/10.0 GPA (with 10.0/10.0 in Probability & Statistics and Calculus 2B).
My path in computer science began at Hung Vuong High School for the Gifted in Gia Lai, where I specialized in Informatics, won First Prize in the Gia Lai Provincial Excellent Student Contest in Informatics (Grade 12 Table A), and co-founded the HV TechG+ Informatics Club. Entering VNU-HCM University of Science in 2023 as a VietSeeds Foundation Scholar and 100% Tuition Merit Scholar, I focused on the intersection of mathematical foundations, information retrieval, and trustworthy machine learning.
Across my research at SELab (HCMUS — multimedia lifelog retrieval at ACM ICMR LSC '26, rPPG physiological sensing at ICMV '26, and biometric privacy at FDSE '26), AITHENA Lab (HCMUS — automated fact verification at KES '26, NLP, and legal LLM reasoning diagnostics at FJCAI '26), and the VNG – Saigon AI Hub Applied AI Lab, I investigate a unifying question: how can AI systems retrieve, verify, and reason over complex multimodal or structured evidence without succumbing to surface-level shortcuts?
Beyond research and system engineering, I actively contribute to the academic and student community. I won Champion at both the HCMUS Student Leadership Competition (2023) and the Faculty of IT Leadership Competition (2024), organized AI talkshows and academic review programs for hundreds of students, represented the VNU system as an International Academic Delegate at the ASEAN University Network (AUN) Summer Camp at De La Salle University (Philippines, July 2025) and the NUS Asian Undergraduate Symposium & REGEN Asia Summit (Singapore, July 2025), and completed ten voluntary blood donations between 2024 and 2026.

Le Van Truong
Published as: Van-Truong Le · Lê Văn Trường
- PRIMARY INSTITUTION
- University of Science, Vietnam National University Ho Chi Minh City (VNU-HCM)
- ACADEMIC PROGRAM
- Faculty of Information Technology — Honors Program (23CNTN)
- RESEARCH LABORATORIES
- SELab & AITHENA Lab (HCMUS) · VNG – Saigon AI Hub (Applied AI Lab Batch 1)
- CUMULATIVE GPA
- 9.50 / 10.0 (Honors Program)
- ORCID IDENTIFIER
- 0009-0008-7015-7392
Education & Coursework
University of Science, Vietnam National University Ho Chi Minh City (VNU-HCM)
Bachelor of Science in Information Technology — Honors Program in Information Technology (Cử nhân Tài năng — 23CNTN)
- ·Cumulative GPA: 9.50/10.0 across intensive Honors IT mathematical and computer science curriculum.
- ·Recipient of 100% Tuition Waiver and Academic Merit Scholarships across consecutive semesters (2023–2026).
- ·Named to the Faculty of Information Technology Golden Achievement Board (Bảng vàng thành tích Khoa CNTT) in 2024 and 2025.
- ·Member of the HCMUS ICPC Competitive Programming Team (2024) and Presenter at the 3rd HCMUS Young Scientists Conference (2026).
Hung Vuong High School for the Gifted, Gia Lai
High School Diploma — Specialized in Computer Science (Chuyên Tin học) — Specialized Informatics Track (Class C8)
- ·Top Student in Class (Học sinh giỏi nhất lớp) for three consecutive academic years (2020–2021, 2021–2022, 2022–2023).
- ·First Prize in the Gia Lai Provincial Excellent Student Contest in Informatics (Grade 12 Table A, 2022–2023) & Member of the Provincial National Olympiad Training Team.
- ·Third Prize in Hue-ICT Challenge Pro Track (2023) and Third Prize in the Regional National Youth Informatics Contest (2023).
- ·Co-founder of HV TechG+, the school's computer science and technology club.
Four Principles Guiding My Work
Evidence-Grounded Reasoning
Standard dense embeddings compress complex claims into flat vectors that blur crucial factual predicates, dates, and temporal order. My primary research replaces surface similarity with structured evidence grounding: temporal Event Knowledge Graphs (ChronoSeek), retriever-aligned hard negative cross-encoders (SemEval/KES '26), and provenance-aware expert routing (GraphCURE).
Diagnostic Failure Analysis
High benchmark averages frequently hide systematic reasoning collapses. Across 5,922 Vietnamese legal statute questions and 300 expert-graded essays (FJCAI '26), we categorized 7 distinct failure modes—showing that models with strong multiple-choice accuracy still hallucinate abrogated statutes in open-ended legal reasoning.
Hybrid Analytical + Learned Priors
Domain priors—such as graph Laplacian Fiedler vectors in road disruption estimation (ResiliRoad) or facial skin masks in remote photoplethysmography (SKIA)—accelerate learning when aligned with the signal, but can hurt when violated. I design gated residual architectures that adaptively down-weight analytical priors.
Research-to-Engineering Integration
Research ideas only prove their worth when they survive real-world system constraints: sub-6 ms Neo4j graph queries under a live 4-minute competition clock at ACM ICMR LSC '26, 124 FPS two-stage video anomaly detection, and deterministic Zenodo evaluation harnesses.
Skills Mapped to Evaluated Systems
Rather than arbitrary percentage bars, every technical capability is anchored to concrete systems, publications, and experimental pipelines in this portfolio.
Information Retrieval & RAG
ChronoSeek (ACM ICMR LSC '26) · Multilingual Fact-Checking (KES '26) · ViMELD Legal Retrieval · Global Tech 100K-News RAG
NLP, LLMs & Speech AI
SemEval-2025 Fact-Checking Reranker · Vietnamese Legal LLM Evaluation (FJCAI '26) · ViProDID 63-Province Dialect MoE · CrisisX VR
Graph Machine Learning & Network Science
ResiliRoad Spectral-Prior Graph Learning (13 OSM Networks) · ViMELD Citation Graph
Computer Vision & Signal Processing
SKIA Motion-Robust rPPG (ICMV '25) · FLeX Fingerprint Privacy (FDSE '25) · Two-Stage Exam Cheating Detection (FJCAI '26)
Statistical Evaluation & Reproducibility
Area-Clustered OSM Inference · Paired-Bootstrap Routing Validation (GraphCURE) · Training-Free Fact Verification Cache