Started my M.Sc. at INRS under the supervision of Prof. Long Bao Le.
About
I am an M.Sc. student in Telecommunications at the Institut national de la recherche scientifique (INRS), supervised by Prof. Long Bao Le. My research focuses on world models and vision-language-action (VLA) models for robot learning, building on my previous work in robust visual question answering and multimodal learning.
I am interested in how embodied AI systems can learn to act and generalize across environments. I received my B.Sc. in Information Technology from VNUHCM - University of Science 
in 2025 and contribute to research and teaching at AI VIETNAM 
.
- Perception
Visual observations of the environment.
- World Model
Model physical scenes and their dynamics.
- Prediction & action
Anticipate future states. Plan what comes next.
News
Counterfactual Reasoning for Robust VQA accepted at KES 2026.
ViInfographicVQA presented at the AAAI 2026 Workshop on AI for Scientific Research.
ViVQA-X: our Vietnamese VQA-NLE dataset paper published online by Springer.
DAM-QA published at the ICCV 2025 VisionDocs Workshop.
Research Interests
World Models
Current research interest
Learning representations of how environments evolve, with the goal of supporting prediction and planning for robot learning.
Vision-Language-Action
Current research interest
Connecting visual observations and language instructions to actions that generalize across physical environments.
Robust Multimodal Reasoning
Building on prior work
Studying how vision-language systems reason beyond shortcuts, building on my work in counterfactual reasoning and visual question answering.
