Highly accomplished PhD Candidate at KAIST specializing in Deep Reinforcement Learning, Robot Learning, and Manipulation. Proven expertise in developing cutting-edge AI solutions, evidenced by multiple publications in top-tier conferences and three patents. Seeking advanced research or R&D roles to leverage extensive experience in Vision-Language Models and complex system optimization.
Hanoi, Hanoi, Viet Nam
→
Summary
Spearheaded software development and security initiatives for embedded systems, enhancing product robustness and performance for G-Innovations Vietnam.
Highlights
Developed and implemented secure software solutions for embedded systems, significantly enhancing product reliability and data integrity.
Contributed to the design and optimization of embedded system architectures, improving overall system performance and efficiency.
Conducted rigorous testing and debugging of software components, ensuring high-quality deliverables and minimizing post-deployment issues.
Collaborated effectively with cross-functional teams to integrate software modules, ensuring seamless functionality and timely project completion.
Hanoi, Hanoi, Viet Nam
→
Summary
Conducted impactful undergraduate research in Digital Signal Processing and Embedded Systems, contributing to foundational academic projects at EDABK Lab, HUST.
Highlights
Assisted in the development and prototyping of Digital Signal Processing algorithms for various embedded applications, laying groundwork for advanced research.
Performed comprehensive data analysis and experimental validation for research projects, contributing to successful academic studies and technical reports.
Gained hands-on experience with embedded system design and implementation, effectively applying theoretical knowledge to practical research challenges.
Collaborated closely with senior researchers on project tasks, significantly enhancing technical skills and mastering research methodologies.
Awarded By
Hyundai Motor Foundation
Awarded for living expenses support for graduate studies, recognizing academic excellence and potential.
Awarded By
Korea Advanced Institute of Science and Technology (KAIST)
Full tuition scholarship for the Ph.D. program in Electrical Engineering, recognizing outstanding academic performance.
Awarded By
Korea Advanced Institute of Science and Technology (KAIST)
Full tuition scholarship for the M.S. program in Electrical Engineering, recognizing outstanding academic performance.
Awarded By
European Conference on Computer Vision Workshop
Achieved first place in a competitive challenge focusing on super-resolution for mobile devices.
Awarded By
Hanoi University of Science and Technology (HUST)
Awarded for exceptional academic performance in Electrical and Electronic Engineering in 2015 and 2016.
Published by
International Conference on Machine Learning (ICML)
Summary
Pioneering research leveraging large vision-language models to improve rating-based reinforcement learning effectiveness.
Published by
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Summary
Developed a novel policy learning approach utilizing vision-language model feedback, circumventing traditional reward modeling.
Published by
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Summary
Contributed to research on enhancing sample efficiency in reinforcement learning through large vision-language model distillation.
Published by
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Summary
Researched and proposed a vector quantization method to effectively mitigate adversarial perturbations in deep reinforcement learning.
Published by
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Summary
Contributed to research on sample-efficient reinforcement learning using a curiosity-driven contrastive forward dynamics model.
Python, C++.
Linux, ROS, Git, Docker.
Deep Reinforcement Learning, Robot Learning, Manipulation, Vision-Language Models, Predictive Coding, Decision Transformers, Digital Signal Processing, Embedded Systems Security, Machine Learning, Statistical Learning Theory.
Deep Reinforcement Learning, Robot Learning, Manipulation.