QUAN VAN NGUYEN

Ñ Ho Chi Minh City +84-969-***-***

# ad4e0p@r.postjobfree.com # ad4e0p@r.postjobfree.com

§ GitHub Profile: minhquan6203

EDUCATION

• University of Information and Technology - Vietnam National University HCM 2021 - Current (Expected 2025) Bachelor in Data Science

GPA: 3.2/4

Interest: Multi-modal, NLP, CV, AI system, Data Engineering, Cloud Computing. EXPERIENCE

Research student - University of Information and Technology - Vietnam National University HCM

•Multi-modal 06/2023 - current

Project: Vietnamese Visual Question Answering

– Advisor: MSc. Kiet Van Nguyen and Nghia Hieu Nguyen

– Tool & Technology: PyTorch, Natural Language Processing, Computer Vision, Deep Learning.

– Contruct new datasets and develop methods to improve the VQA model in the Vietnamese language.

•Natural Languge Processing 01/2024 - current

Project: Vietnamese AI Generated Detector

– Advisor: PhD. Trong-Hop Do

– Tools & Technologies: PyTorch, Natural Language Processing, Deep Learning, Data Crawling.

– Build new datasets and conduct deep learning models capable of distinguishing between human-written text and AI- generated text in education domain.

SKILLS

Programming: Python(proficient), C/C++, C#, R, SQL(prior experience). Frameworks: PyTorch(proficient), TensorFlow, Keras, Spark(prior experience). Tools: VSCode, Jupyter Notebook, Terminal, Google Colab, Git, Docker, PowerBI. Knowledge & Course: Machine Learning & Deep Learning, Calculus, Linear Algebra, Discrete Math, Probability & Statistic, Data Structure and Algorithm, Cloud Computing, Distributed Database, Basic Software. Soft skills: English, management skill, teamwork.

PROJECTS

•AI Hackathon - Face Analysis Challenge 01/2024 - 02/2024 Competition project - Role: Leader - Team size: 3

– Tool & Technology: Computer Vision, Image Processing, Deep Learning, Pytorch, Docker, Yolov8.

– In charge of implementation and development of effective method for face detection and analysis based on object detection and classification models.

– Conduct quantization and optimization method to accelerate the model on Embedded System

– Finally achieved second prize against 50+ national teams.

– Source code HERE

•VLSP 2023 challenge on Visual Reading Comprehension for Vietnamese 10/2023 - 12/2023 Competition project - Role: Leader - Team size: 4

– Tool & Technology: Conputer Vision, Natural Languge Processing, Large Languge Model, Pytorch, LoRA.

– Developed novel approaches that leverage the transformer-based encoder-decoder language model and combine infor- mation from both objects, OCR to address the Visual Question Answering (VQA) challenge in Vietnamese language.

– achieved the 4th place on the leaderboard in the private test phase of the competition.

– Aaccepted paper by VLSP2023 workshop.

– Source code HERE

•UIT Data Sciene Challenge Group B - Vietnamese Fact Checking 09/2023 - 11/2023 Competition project - Role: Leader - Team size: 4

– Tool & Technology: Natural Language Processing, Data Analysis, Data Preprocessing, Pytorch.

– Create a rule based to split sentence for evidence retrival. Then proposed a solution by combining pre-trained language models with a proposed Support Vector Machine (SVM) kernel to address verdict classification in the Fact Checking task.

– achieved the highest position in group B in the Fact Checking task.

– Source code HERE

•Data Science Advanced Analysis 2023 Competition - Link Prediction for Wikipedia Articles 04/2023 - 06/2023 Competition project - Role: Leader - Team size: 4

– Tool & Technology: Natural Language Processing, Data Analysis, Data Preprocessing, Pytorch.

– Design the Vanilla Fully Connected based on Neural Network and Mutual Attention Transformer method which dual attention textual feature in two nodes to tackle the link prediction task in the competition.

– achieved nearly absolute score on the public test and private test and take the 4th place with on the leaderboard.

– Accepted paper by DSAA conference.

– Source code HERE

ACHIEVEMENTS

•Second prize - AI Challenge: Facial Analysis [HERE] Organized by Pixta Vietnam, Co-Host AI and Viblo. 02/2024

•Third prize - VLSP2023: Legal Textual Entailment Recognition [HERE] Organized by VLSP - Vietnamese Language and Speech Processing 12/2023

•Top 4 private test - VLSP2023: Visual Reading Comprehension for Vietnamese [HERE] Organized by VLSP - Vietnamese Language and Speech Processing 12/2023

•First prize - Group B DSC 2023: Vietnamese Fact Checking [HERE] Organized by Faculty of Information Science and Engineering, University of Information Technology 11/2023

•Top 4 private test - DSAA 2023: Link Prediction for Wikipedia Articles [HERE] Organized by Data Science Advanced Analysis Conference (rank A core 2021) 06/2023 PUBLICATIONS

MAT: Effective Link Prediction via Mutual Attention Transformer [HERE] Accepted by Data Science Advanced Analysis Conference (DSAA) (rank A core 2021) 11/2023 PREFERENCES

•MSc. Kiet Van Nguyen

Vice Dean Faculty of Information Science and Engineering University of Information and Technology

ad4e0p@r.postjobfree.com

•PhD. Trong-Hop Do

Faculty of Information Science and Engineering

University of Information and Technology

ad4e0p@r.postjobfree.com

•Nghia Hieu Nguyen

Faculty of Information Science and Engineering

University of Information and Technology

ad4e0p@r.postjobfree.com

Contact this candidate