Hello!

I'm Hieu Tran, an NLP enthusiast focused on large language models & text generation

Get in touch heraclex12@gmail.com
scholar github linkedin

Background

I'm currently a PhD student at University of Maryland, College Park (UMD), where my research interests lie in Large Language Models (LLMs) and Machine Translation. Previously, I was a Senior ML Engineer at BLACKBOX AI, specializing in cutting-edge research on large language models and their applications in code generation. With over five years of hands-on experience, I bring a wealth of expertise to the table. I'm also a member of VietAI, advised by Minh-Thang Luong, where we focus on advancing artificial intelligence research in the Vietnamese community.

When I'm not in front of a computer screen, I'm probably swimming, watching movies, or taking my cute pets for a walk.

Skills
Languages
  • Python
  • NodeJS
  • SQL
  • SPARQL
Libraries
  • Pytorch
  • Transformers
  • PEFT
  • scikit-learn
Tools
  • Google Cloud Platform
  • Linux
  • Git
  • Docker
  • Kubernetes
  • MongoDB
AI
  • Machine Learning
  • Natural Language Processing
  • Generative AI
  • Research
Experience
BLACKBOX AI
Sep. 2023 - Jul. 2024
Senior ML Engineer
VietAI
May 2021 - Present
NLP Research Collaborator
MoMo (M_Service)
Aug. 2021 - Sep. 2023
AI Research Engineer
AISIA Lab
Sep. 2020 - Jul. 2021
Undergraduate Research Student
Zalo Group - VNG Corporation
Apr. 2019 - Aug. 2021
AI Engineering Intern
View My Resume
Publications
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation

arXiv preprint:2402.14874v2, 2024

Phuc Phan*, Hieu Tran*, Long Phan

CODE
Enriching Biomedical Knowledge for Low-resource Language Through Translation

EACL, 2023

Long Phan*, Tai Dang*, Hieu Tran*, Trieu H. Trinh*, Vy Phan, Lam D. Chau, Minh-Thang Luong

BLOG CODE
🌸 MTet: Multi-domain Translation for English and Vietnamese

arXiv preprint:2210:05610, 2022

Chinh Ngo*, Trieu H Trinh*, Long Phan*, Hieu Tran*, Tai Dang, Hieu Nguyen, Minh Nguyen, Minh-Thang Luong

BLOG CODE
🤗 BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

arXiv preprint arXiv:2211.05100, 2022

Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, and 386 others including Hieu Tran

CODE
🤗 The BigScience ROOTS Corpus: A 1.6 TB Composite Multilingual Dataset

NeurIPS, 2022

Hugo Laurençon, Lucile Saulnier, Thomas Wang, Christopher Akiki, and 50 others including Hieu Tran

CODE
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation

NAACL SRW, 2022

Long Phan, Hieu Tran, Hieu Nguyen, and Trieu H. Trinh

BLOG
SciFive: a text-to-text transformer model for biomedical literature

arXiv preprint arXiv:2106.03598, 2021

Long N Phan, James T Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, Grégoire Altan-Bonnet

CODE
CoTexT: Multi-task Learning with Code-Text Transformer

NLP4Prog @ ACL, 2021

Long Phan, Hieu Tran, Daniel Le, Hieu Nguyen, James Anibal, Alec Peltekian, Yanfang Ye

CODE
SPBERT: an Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs

ICONIP, 2021 (Acceptance rate ~20%)

Hieu Tran, Long Phan, James Anibal, Binh T. Nguyen, Truong-Son Nguyen

CODE
VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?

arXiv preprint arXiv:2110.04257, 2021

Hieu Nguyen, Long Phan, James Anibal, Alec Peltekian, Hieu Tran

Hierarchical transformer encoders for vietnamese spelling correction

IEA/AIE, 2021

Hieu Tran, Cuong V Dinh, Long Phan, Son T Nguyen

An Efficient Transformer-Based Model for Vietnamese Punctuation Prediction

IEA/AIE, 2021

Hieu Tran, Cuong V Dinh, Quang Pham, Binh T. Nguyen

CODE
Leveraging Transfer Learning for Reliable Intelligence Identification on Vietnamese SNSs (ReINTEL)

arXiv preprint arXiv:2012.07557, 2020

Trung-Hieu Tran, Long Phan, Truong-Son Nguyen, Tien-Huy Nguyen

CODE
Activities
Unlocking the potential of GenAI for coding | 2023

Gave a talk at Google Devfest HCM 2023

Explore the Power of AI - Career Trends in This Industry | 2023

Gave a talk at BKACAD and USAID Wise Online Event

Shaping Your NLP Career Path in 2024 | 2023

Gave a talk at VietAI

Advanced Class in NLP | 2023

Lecturer at VietAI Advanced Class in NLP

Challenges and Opportunities When Working In AI Industry | 2022

Gave a talk at Van Lang University

MTet: Multi-domain Translation for English and Vietnamese | 2022

Gave a talk at Google I/O Extended Hanoi 2022

BigScience Research Contributor

A one-year long research workshop on large multilingual models and datasets mainly leading by HuggingFace

How MoMo Builds an AI Chatbot

Blog at MoMo Technology (Medium)

Outstanding Undergraduate Thesis Award

Undergraduate Thesis, HCMC University of Science