Hi, welcome to my world. I am a freelance AI researcher and I am working in Natural Language Processing. I also know a bit about image processing and signal processing. I like to challenge myself and explore new technological challenges. I’m a boring man. (I heard someone say that I’m not boring at all.)

News and Updates

2024

• 22/12/2024: I conducted a collaborative class with NTI-VietAI on the topic “Advancing Intelligent Systems with Language Models: Automotive, Robotics, and Beyond.” The session offered fresh perspectives on the applications of LLM in emerging industries such as electric vehicles and robotics.
• 22/10/2024: My team and I co-developed and released the LLaMA-Frog model. This model, based on LLaMA3-3B, is optimized for deployment on mobile environments while achieving accuracy comparable to or exceeding ChatGPT and Gemini on various tasks.
• 24/07/2024: I faced significant challenges related to health and finances. It was a deeply emotional time.
• 15/07/2024: I welcomed my first son into the world. He is absolutely adorable.
• 10/07/2024: I initiated the XanhMaps project with the support of many talented young colleagues at VinGroup.
• 01/01/2024: My colleagues and I continued advancing language models at VinBigData. We also developed and upgraded VinBase 2.0, an enhanced version of VinBase powered by large language models and Agentic capabilities.

2023

• 26/12/2023: My team successfully developed a large language model at VinBigData. Additionally, we released an open-source language model to support the research community in Vietnam.
• 24/05/2023: I proposed adapting existing English-centric language models to support low-resource languages like Vietnamese. I submitted this proposal to several organizations, including GCR, to secure resources for experimentation.
• 26/04/2023: After more than a year as acting team leader, I was officially appointed as the Lead of the Language Representation Team at VinBigData. Together, we tackled NLU challenges for various projects.
• 08/02/2023: Following the rise of ChatGPT at the end of 2022, I presented to leadership and proposed developing VinBigData’s own large language model.
• 13/01/2023: I received the Employee of the Year award for 2022 at VinBigData.

2022

• 24/12/2022: I got married.
• 22/12/2022: My team launched VinBase 1.0, a chatbot platform designed for businesses.
• 13/12/2022: I conducted a short-term training program for the “10 Institute” under the Ministry of National Defense. Over one month, I assisted officers in building AI systems tailored to their unique challenges.
• 15/09/2022: I taught a class at Hanoi University of Industry on “AI Research and Applications in Business.” I had the opportunity to exchange ideas with school leaders and faculty members, sharing insights and vision from a business perspective.
• 26/04/2022: I was nominated for the position of team leader at VinBigData, with a one-year probation period to confirm the appointment.
• 01/01/2022: I joined the VinBase project, a multi-modal chatbot platform at VinBigData. My colleagues and I rebuilt the entire AI model system for the platform, successfully releasing VinBase 1.0 within the same year.

2021

• 08/08/2021: At the 28th anniversary of VinGroup, my team and I successfully launched the first smart virtual assistant integrated into VinFast electric vehicles. We continued to develop virtual assistants for other VinFast models in subsequent years (VFe34, VF5, VF6, VF7, VF8, VF9).
• 26/05/2021: During the peak of the Covid-19 pandemic, I embarked on a three-month business trip to Hon Tre, Nha Trang, to develop the smart virtual assistant for VinFast electric vehicles (VFe34).
• 27/04/2021: I began my journey at VinBigData - VinGroup as a Natural Language Processing Specialist. During this time, I also continued my role at Sun Asterisk Inc. until I officially left in June 2021.
• 23/06/2021: After nearly 3 years working at AI research team, I have officially left my job at Sun Asterisk Inc.
• 18-04-2021: Our paper “Contrastive Learning for Natural Language-Based Vehicle Retrieval” has been accepted in the 5-th AI City Challenge CVPR 2021 Workshop (AI City - CVPR 2021). We also ranked 4th in the challenge.
• 31-03-2021: Our paper “An Analysis of Dual Networks for Sequence Tagging”, has been accepted in The 15th International Workshop on Semantic Evaluation (SemEval 2021).
• 31-03-2021: Our team “SunBear” won the first prize in the shared task of the International Conference on Document Analysis and Recognition ICDAR 2021 Competition for “Multimodal Emotion Recognition on Comics scenes”.
• 09-02-2021: Our NLP Research team won 2nd place in the Toxic Spans Detection challenge by The 15th International Workshop on Semantic Evaluation (SemEval 2021).

2020

• 18-12-2020: My team won the first prize in the shared task of Vietnamese Universal Dependency Parsing (VLSP 2020).
• 18-12-2020: My team gained the 3rd prize in the shared task of (Vietnamese) Relation Extraction (VLSP 2020).
• 18-12-2020: My team gained the 3rd prize in the shared task of Reliable Intelligence Identification on Vietnamese Social Network Sites (VLSP 2020).
• 12-11-2020: We achieved the Best Paper Award Certificate at The 12th IEEE International Conference on KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2020).
• 09-10-2020: Our paper “Improving BERT-Based Noisy Text Classification with Knowledge of the Data domain”, has been accepted in The 6th Workshop on Noisy User-generated Text (WNUT 2020). My team was in the TOP 10 of best teams at Identification of informative COVID-19 English Tweets.
• 14-09-2020: Our paper “From Universal Language Model to Downstream Task: Improving RoBERTa-Based Vietnamese Hate Speech Detection”, has been accepted in The International Conference on Knowledge and Systems Engineering (KSE 2020). We also won the Best Paper Award with this paper.
• 01-06-2020: I have achieved Tensorflow Developer Certificate.

2019

• 04-11-2019: I represented our team and talked about AI in Electroencephalography techniques at SoICT Day 2019 organized Hanoi University of Science and Technology.
• 16-11-2019: My team gained the 3rd prize at ERC2019: Emotion Recognition Challenge.
• 12-10-2019: I won the first prize at Vietnamese Language and Speech Processing 2019 Hate Speech Detection on Social Networks Challenge.
• 12-10-2019: I gained the 3rd prize at Vietnamese Language and Speech Processing 2019 Text-to-Speech Challenge.
• 06-10-2019: I have presented about OCR techniques and DX revolution at Vietnam Frontier Summit organized by Vietnam Television VTV24 and rubikAI.
• 22-07-2019: My first paper was accepted at GCCE, Osaka, Japan. I had a 1 week business trip there and had great experiences.
• 14-06-2019: I’m a speaker at Vietnam Mobile Day 2019 and talking about “Build your own artificial intelligence assistant similar to Google assistant”.
• 14-03-2019: My team won 2nd and 3rd place at CMC AI Contest: Face recognition.