Minh-Thien Nguyen

Minh-Thien Nguyen

Independent AI Researcher

Working on inference-time scaling, symbolic reasoning, and high-performance model serving.

Curriculum vitae
Portrait of Minh-Thien Nguyen

01

About

I am an independent AI researcher working on natural language processing and deep learning. My research interests are inference-time scaling, symbolic reasoning, high-performance model serving, embedding models, image-text retrieval for Vietnamese, optimal transport, retrieval-augmented generation, and image classification.

Alongside that I keep a set of personal projects on distributed training, TPU training, and retrieval-augmented generation for multiple-choice question answering over complex documents.

02

News

  1. Submitted the CoTu system paper to the EXACT Competition Track at the CSoNet 2026 special session, hosted at HCMUT.

  2. Final results announced for EXACT 2026 at IEEE IJCNN 2026. Team CoTu took the highest technical score of any team, 13.44/15, and placed 3rd overall.

  3. Preprint on model soups for Mekong Delta intangible-cultural-heritage image classification. Early accept at the Journal on Information Technologies and Communications.

  4. Preprint of ViCLIP-OT, a foundation vision-language model for Vietnamese image-text retrieval.

03

Publications

Preprints and journal papers. Author lists are as submitted.

ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport

Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang Pham

Preprint, submitted to The Visual Computer ·

A foundation vision-language model for Vietnamese image-text retrieval. It pairs CLIP-style contrastive learning with a Similarity-Graph Regularized Optimal Transport (SIGROT) loss to improve cross-modal consistency and reduce the modality gap.

CiteViCLIP-OT
@misc{tran2026viclipot,
  title        = {ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport},
  author       = {Tran, Quoc-Khang and Nguyen, Minh-Thien and Pham, Nguyen-Khang},
  year         = {2026},
  eprint       = {2602.22678},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url          = {https://arxiv.org/abs/2602.22678}
}

Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta

Quoc-Khang Tran, Minh-Thien Nguyen, Nguyen-Khang Pham

Journal on Information Technologies and Communications, Vol. 2025 No. 3 ·

A framework that combines the hybrid CoAtNet architecture with model soups, a weight-space ensembling technique that averages checkpoints from one training run without raising inference cost. The paper analyses the effect through bias-variance decomposition.

CiteModel Soups for ICH Classification
@article{tran2026soups,
  title   = {Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta},
  author  = {Tran, Quoc-Khang and Nguyen, Minh-Thien and Pham, Nguyen-Khang},
  journal = {Journal on Information Technologies and Communications},
  volume  = {2025},
  number  = {3},
  year    = {2026},
  doi     = {10.32913/mic-ict-research.v2025.n3.1395},
  url     = {https://arxiv.org/abs/2603.02181}
}

04

Competitions

EXACT 2026, IEEE IJCNN 2026 Competition ·

2nd International XAI Challenge for Transparent Educational Question-Answering

Highest technical score, 3rd overall

A neuro-symbolic Program-of-Thought pipeline for explainable educational QA under an 8B open-weight limit. Team CoTu took the highest final-round technical score of any team, 13.44/15, and placed 3rd overall once the equally weighted presentation score was included.

EXACT 2026 asks for answers that are correct and explainable, from self-hosted open-weight models capped at 8B parameters with a 60-second budget per query, over two tasks: logical reasoning over university regulations, and multi-step physics. The CoTu system writes a program instead of stating an answer, so regulation queries become a Z3 encoding whose entailment verdict grounds the deduction and physics becomes numerical Python, both sharing a self-correction loop and the same explained-JSON structure. Answer-type routing, distillation-based task fine-tuning, and SGLang with speculative decoding keep it inside the latency limit, and the system scored perfectly on physics in both automated selection rounds. Grounding answers in a symbolic solver produces verifiable deductions even at 4B scale; what remains hard is premise selection, not the deduction itself.

Pipeline of the CoTu system. A 4B backbone routes each question by answer type, then emits either a Z3 encoding for regulation queries or numerical Python for physics, both passing through a shared self-correction loop to a unified explained-JSON output.

Viettel AI Race 2025 ·

Multiple-Choice Question Answering Pipeline for Complex Technical Documents

An MCQA pipeline that answers questions over dense technical documentation, where the answer usually depends on retrieving the right passage rather than on reasoning once it is found.

05

Projects

Personal work, framed around the engineering decision each one turned on.

ViREx-Bench

A framework for inference-time scaling on Vietnamese reasoning tasks.

  • Python
  • Inference-time scaling
  • Evaluation

seas

A Smart Enrollment Advisory System for Can Tho University. Async throughout — FastAPI, SQLAlchemy, and Qdrant — so retrieval and database work overlap instead of serialising behind each other.

  • Python
  • FastAPI
  • SQLAlchemy
  • Qdrant

medical-llama2

Med-Alpaca-2-7b-chat, a medical chatbot fine-tuned from LLaMA 2 7B and served as a live demo.

  • Python
  • PyTorch
  • LLaMA 2 7B
  • Hugging Face

pre-training-gpt2

An end-to-end workflow for pre-training GPT-2 from scratch, targeting XLA-enabled devices through PyTorch/XLA so the same code path runs on both CUDA and TPU.

  • Python
  • PyTorch
  • PyTorch/XLA
  • CUDA
  • TPU

06

Writing

  1. Auxiliary Tree/Virtual Tree

    A technique for answering queries over a subset of a tree's vertices.

VNOI Magazine

  1. 2024
    Virtual Tree

    Cây ảo

    VNOI Magazine

  2. 2023
    Subtle Techniques with the Xor Operation

    Kỹ thuật tinh tế về phép Xor

    VNOI Magazine

All posts →

07

Contact