ECCV 2026
360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
A comprehensive benchmark and a training-free method for 360° image perception using MLLMs.
Quang Nguyen is an AI researcher focused on Computer Vision, Multimodal AI especially Multimodal Large Language Models for vision-language understanding, and their AI applications for domain-specific problems. He is currently working at the University of Wollongong, following a 3-year postdoctoral fellowship at RIKEN AIP and a visiting research position at Tohoku University.
He has published research papers in international venues like CVPR, ECCV, EACL, and IJCAI. He is passionate about bridging the gap between foundational AI research and practical, impactful technology.
Feel free to reach out for collaborations!
Research interests
Computer VisionMultimodal AI(M)LLMsMultimodal AI ApplicationsVision-Language Understanding
Selected publications
A few papers that best represent my current work. See Google Scholar for the full list.
EACL 2026
CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning
Improving multimodal table understanding with code-driven reasoning.
CACIE 2025
Multimodal artificial intelligence approaches using large language models for expert-level landslide image analysis
Large language models deliver expert-level assessments for landslide image analysis and hazard response.
IEEE T-IV 2024
Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction
Studies multimodal perception models for anticipating hazardous events in autonomous driving scenarios.
ECCV 2022
GRIT: Faster and Better Image Captioning Transformer Using Dual Visual Features
Presents GRIT, a dual-feature transformer that improves both speed and accuracy for image captioning.
IJCAI 2021
Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks
Enhances interactive instruction following agents with wide-context perception and iterative reasoning.
ECCV 2020
Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs
Introduces an efficient attention design capturing full interactions in visual dialog systems.
FG 2019
CapsuleNet for Micro-expression Recognition
Applies capsule networks to the challenging task of recognizing subtle micro-expressions.
Experience
Academic Staff
University of WollongongTeaching and research on multimodal AI and multimodal large language models.Visiting Researcher
Tohoku University, SendaiContinued collaboration with the Computer Vision group under Prof. Takayuki Okatani.Postdoctoral Researcher
RIKEN AIP, TokyoWorked on multimodal AI (especially MLLMs) for domain-specific perception, planning, and reasoning across robotics, traffic, and environmental intelligence.Machine Learning Research Intern
Preferred Networks, TokyoBuilt efficient end-to-end object tracking systems and collaborated with product teams on deployment.Machine Learning Engineer (Part-time)
Laboro.AI, TokyoDeveloped computer vision models for industrial clients; contributed to face detection and recognition products.Machine Learning Research Intern
Fujitsu, TokyoPrototyped LSTM-based question-answering systems for enterprise knowledge bases.
Education
Ph.D. in Information Sciences
Tohoku UniversityGPA: 4.0/4.0. Dean’s Award. Advisor: Prof. Takayuki OkataniMaster in Information Sciences
Tohoku UniversityGPA: 3.9/4.0. Advisor: Prof. Takeshi Tokuyama and Assoc. Prof. Jinhee ChunBachelor in Computer Science
Vietnam National University, UETGPA: 3.9/4.0, highest of cohort. Advisor: Assoc. Prof. Ha Quang ThuyFostering ASEAN Future Leaders
Daejeon University, South KoreaGPA: 4.4/4.5. Fully funded one-year exchange program for 20 ASEAN students
Honours
Recognized for outstanding Ph.D. research in multimodal AI
Awarded for top Ph.D. research presentation in Information Sciences
First place for interactive instruction-following agent competition at ECCV 2020
Fellowship to Honda YES awardees who pursue studies in Japan
Full scholarship for Ph.D. studies in 2017-2022
Fostering ASEAN Future Leaders Scholarship
Fully funded scholarship for one-year exchange program in South Korea in 2015-2016
Hoa Trang Nguyen Award
Prestigious award recognizing outstanding academic achievement
Show all awards and scholarships (23 total) Show fewer
Data Science Summer School Scholarship
Selected to attend Data Science Summer School at Gottingen University, Germany
For top 10 engineering students in Vietnam.
Third Prize of National Scientific Student Research Conference
Recognized for outstanding research presentation at the national level
Excellent Thesis Award
Best Bachelor’s thesis with highest score 10/10
First Prize of Scientific Student Research Conference
First place award for research presentation at the national conference
Excellent Student Award
Highest GPA among the K57 cohort
American Chamber (AmCham) Scholarship
Scholarship awarded by the American Chamber of Commerce and the US Embassy in Vietnam
Machine Learning Summer School Scholarship
Selected to attend Machine Learning Summer School at Kyoto University, Japan
Merit-based University Scholarships
Received merit-based scholarships throughout undergraduate studies (2013-2017)
Shinnyo-en Scholarships
Awarded in 3 consecutive years (2013-2016) for academic excellence from Shinnyo-en Foundation, Japan.
Second Highest Score in University Entrance Examination
Achieved the second highest score in the UET entrance examination
Merit-based New South Wales University Scholarship
Merit-based cholarship from University of New South Wales, Australia
First Prize of Vietnam National Chemistry Olympiad
First place in the National Chemistry Olympiad competition
Telecom Corporation Scholarship
Scholarship awarded by Vietnam Telecom Corporation for academic excellence
Odon Vallet Scholarship for Top High-School Students
Prestigious scholarship for top high-school students in Vietnam from Odon Vallet Foundation, France
Third Prize of National Chemistry Olympiad
Third place in the Vietnam National Chemistry Olympiad competition
Open to collaboration
Im glad to hear from researchers and students working on multimodal models, or anyone applying them to cross-domain problems. Feel free to reach out for potential collaborations.