CV

Education

• B.Eng. in Software Engineering, specialized in Artificial Intelligence, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand, July 2023 – Present

Research Experience

• AI Research Intern, AI Singapore & VISTEC, Part-time, Singapore, April 2025 – Present
  • Participating in Southeast Asian LLM research.
  • Translated instruction-following datasets for Burmese LLM evaluation.
  • Built evaluation datasets for seven Burmese NLP tasks.
  • Evaluated Burmese NLP benchmarks for LLMs.
• Machine Learning Engineer, Looloo Technology, Part-time, Bangkok, Thailand, June 2025 – Dec 2025
  • Finetuned Flow Matching Transformer models for Thai TTS.
  • Finetuned speech-augmented language modeling for Thai language.
  • Created synthetic Thai speech datasets with 25k sentences using Thai TTS.
  • Built evaluation pipelines for Thai TTS systems.
• Lab. Member, Language Understanding Laboratory, Part-time, Remote, June 2022 – Present
  • Built large-scale Myanmar corpora for OCR and language modeling.
  • Supervised speech corpus creation for the medical domain.
  • Fine-tuned transformer models for sequence and token classification tasks.
  • Reproduced experiments for myNLP, the first Burmese NLP toolkit.

Achievements

• Full Scholarship: Child’s Dream Foundation Scholarship covering tuition, living expenses, and other expenses.
• Hackathon Winner: Season 2 Championship Award (50,000 THB) for the 42 Bangkok x CDG Group Hackathon.
• Best Paper Award: 20th IEEE iSAI-NLP Conference and 10th Anniversary of the Artificial Intelligence Association Thailand.

Teaching Experience

Publications

Peer-reviewed International Conferences

SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?

Wuttikorn Ponwitayarat, Raymond Ng, Jann Railey Montalan, Thura Aung, Jian Gang Ngui, Yosephine Susanto, William Tjhi, Panuthep Tasawong, Erik Cambria, Ekapol Chuangsuwanich, Sarana Nutanong, and Peerat Limkonchotiwat. (2026). "SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?"

Burmese-SAN: Burmese NLP Benchmark for Evaluating Large Language Models

Thura Aung, Jann Railey Montalan, Jian Gang Ngui, and Peerat Limkonchotiwat. (2026). "Burmese-SAN: Burmese NLP Benchmark for Evaluating Large Language Models."

myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging

Kaung Lwin Thant, Kwankamol Nongpong, Ye Kyaw Thu, Thura Aung, Khaing Hsu Wai, and Thazin Myint Oo. (2025). "myNER: Contextualized Burmese Named Entity Recognition with Bidirectional LSTM and fastText Embeddings via Joint Training with POS Tagging." Best Presentation Paper Award.

Enhancing Burmese News Classification using Kolmogorov-Arnold Head Finetuning

Thura Aung, Eaint Kay Khaing Kyaw, Ye Kyaw Thu, Thazin Myint Oo, and Thepchai Supnithi. (2025). "Enhancing Burmese News Classification using Kolmogorov-Arnold Head Finetuning." Best Paper Award.

ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features

Thura Aung, Ye Bhone Lin, Ye Kyaw Thu, and Thazin Myint Oo. (2025). "ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features."

myOCR: Optical Character Recognition for Myanmar Language with Post OCR Correction

Thura Aung, Ye Kyaw Thu, and Myat Noe Oo. (2024). "myOCR: Optical Character Recognition for Myanmar Language with Post OCR Correction."

myContradict: Semi-supervised Contradictory Sentence Generation for Myanmar Language

Ye Kyaw Thu, Thura Aung, and Ei Myat Nwe. (2024). "myContradict: Semi-supervised Contradictory Sentence Generation for Myanmar Language."

Neural Sequence Labeling Based Sentence Segmentation for Myanmar Language

Ye Kyaw Thu, Thura Aung, and Thepchai Supnithi. (2023). "Neural Sequence Labeling Based Sentence Segmentation for Myanmar Language."

Journal Articles

mySentence: Sentence Segmentation for Myanmar Language using Neural Machine Translation Approach

Thura Aung, Ye Kyaw Thu, and Zar Zar Hlaing. (2023). "mySentence: Sentence Segmentation for Myanmar Language using Neural Machine Translation Approach."

Skills

• Language Proficiency: Burmese (Native), English (Professional Fluency)
• Programming Languages: Python, Rust, C/C++, Java, JavaScript, SQL, Prolog
• Data Tools: NumPy, Pandas, SciPy
• Developer Tools: Git, Docker, VS Code, AWS SageMaker
• Frameworks and Libraries: PyTorch, TensorFlow, OpenCV, spaCy, NLTK, LangChain, OpenNMT, FastAPI, MLflow