Xuan Thanh Nguyen

• Reinforcement Learning 

• Deep Learning for Computer Vision

• Control Algorithms 

• Multimodal Large Language Model 

• B.E. in Electrical Engineering (Automation Control Major, Talented Program), HCMUT, Ho Chi Minh city, Viet Nam. 2010-2015 (GPA:8.34/10 Top 10  - K2010)  

• M.S. in Electrical Engineering, KAIST, Daejeon, Korea, 2018-2020 (GPA:3.66/4.3)

• Ph.D. in Electrical Engineering, KAIST, Daejeon, Korea,2020-Present (GPA:3.79/4.3 )

• Member of Artificial Intelligence & Machine Learning Lab (UAIM), KAIST, Daejeon, Korea, 2018-Present 

• Programming Languages: C, C++, C++(Qt), Python

• Deep Learning Frameworks: Pytorch, Jax, Tensorflow

• Embedded software programming (C/C++), GUI programming(Qt C++), ROS programming (C++/Python), Deep Learning programming (Python)

• HCMUT excellent student scholarship for every 2010 - 2015

• Full Kaist Scholarship for Master-PhD program (2018-Present)

• FPT Sofware - Embedded Software Engineer 2014 - 2015

• SCTV - R&D Engineer 2015-2016

• Steinsvik - R&D Engineer 2016-2018 (6 months working in Norway)

• UAIM LAB - Full-time Machine Learning Ph.D. Scholarship 2018-Now 

• End-to-end Autonomous UAV system (LabVIEW for Ground Control Station; C for firmware and PID-based control algorithm; OrCAD for PCB design) - HCMUT 2014.

• AutoSar Development (Automotive  Hardware Abstraction Layer) (C/C++ Embedded Software Dev and Test) - FPT Software (Vietnamese Company) 2014 

• Video Transmission System  (C on embedded Linux Set-op Box) - SCTV (Vietnamese Company) 2015

• Steinsvik Vision System (C  for Cameras, Sensors firmware implementation; C++ QT QML for HMI) - Steinsvik (Norwegian company) 2016

• Steinsvik Camera Diagnostic Software (Develop RS485-like Orbit Protocol for device computer communication; QT QWidget for HMI) - Steinsvik (Norwegian Company) 2017

• Aurora Filming Aided System (Build up a Qt CANopen stack for Controlling Motors; Qt QML for HMI) - KFX Technology (USA Company) 2018

• Yaskawa Filming Aided System (Python/C++ for using Roboman SDK + Qt QWidget for HMI) - Libre Technology  (Malaysia Company) 2019

• Ground Control Station and Drone Control (C++/QtQML for Ground Control Station; C++ROS2 for drone firmware) - Argosdyne (Korean Company) 2023-2024

• IoT Monitoring System with AI predictive maintenance  (Python for front-end, back-end, and AI development; AWS for hosting systems) - WEEV (Korean company) 2025

CONFERENCE & JOURNAL

• Thanh Nguyen, Chang D. Yoo, One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning, ICLR 2026

• Thanh Nguyen*, Tung M. Luu*, Tri Ton, and Chang D. Yoo, Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses, ICPRAI 2024.

• Thanh Nguyen, Tung M. Luu, Tri Ton, Sungwoong Kim, Chang D. Yoo, Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning, IEEE Access 2024

• Tung Luu, Thanh Nguyen, Joshua Tian Jin Tee, Sungwoong Kim, Chang Yoo, Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization,  IROS 2024. 

• Thang Vu, Kookhoi Kim, Thanh Nguyen, Tung M. Luu, Junyeong Kim, Chang D. Yoo,  Scalable SoftGroup for 3D Instance Segmentation on Point Clouds,  TPAMI 2023.

• Thanh Nguyen, Trung Xuan Pham, Chaoning Zhang, Tung M. Luu, Thang Vu, and Chang D. Yoo. "DimCL: Dimensional Contrastive Learning for Improving Self-Supervised Learning", IEEE Access 2023

• Tung Luu, Thanh Nguyen, Thang Vu, Chang D. Uoo. Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning, IEEE ACCESS 2022.

• Tung M Luu, Thang Vu, Thanh Nguyen, Chang D Yoo. Visual pretraining via contrastive predictive model for pixel-based reinforcement learning, MDPI Sensors 2022

• Trung Xuan Pham, Jin Woong Choi, Rusty John Lloyd Mina, Thanh Nguyen, Sultan Rizky Madjid, Chang D Yoo. Lad: A hybrid deep learning system for benign paroxysmal positional vertigo disorders diagnostic, IEEE ACCESS 2022.

• Thang Vu, Kookhoi Kim, Tung M. Luu, Thanh Nguyen, Chang D. Yoo. SoftGroup for 3D Instance Segmentation on Point Clouds, CVPR 2022.

• Thanh Nguyen, Tung Luu, Thang Vu and Chang D. Yoo. Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model, IROS 2021.

• Thanh Nguyen et al Chang D. Yoo. Robust MAML: Prioritization task buffer with adaptive learning process for model agnostic meta-learning, ICASSP 2021.

• Thanh Nguyen, Tung Luu, Thang Vu, Chang D. Yoo. A pre-training framework for learning feature representation in visual observation reinforcement learning, Theieie 2021 

• Thanh Nguyen, Chang D. Yoo. A survey on meta-learning, KAIA 2020.

• Thanh Nguyen, Hieu Nguyen, Chang D. Yoo. GDCA-GAN based single image super-resolution with Dual discriminators and Channel Attention, KAIA 2019.

WORKSHOP

• Thanh Nguyen, Tung Luu, Chang Dong Yoo.  Fast and Memory-Efficient Uncertainty-Aware Framework for Offline Reinforcement Learning with Rank One MIMO Q network - The Workshop on Policy Learning in Geometric Spaces, IEEE IROS 2023

• Thanh Nguyen, Tung Luu, Chang Dong Yoo.  Towards Robust Robot Perception: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses - The Workshop on Learning by Asking for Intelligent Robots and Agents, IEEE ROMAN 2023

PATENTS

• Computing apparatus and method for implementing end-to-end deep learning framework for sample-efficient image-based reinforcement learning, KR-10-2022-0173811 (2022.12.13)

• Computing apparatus and method for implementing end-to-end deep learning framework for sample-efficient image-based reinforcement learning, US-Application

• A framework for representation learning using Self-Supervised Learning and dimensional contrastive Learning, KR-Application