- Development of a large language model for Vietnamese and its applications (Đang tiến hành)
- Extreme rainfall forecasting using machine learning methods (Đang tiến hành)

Đã hoàn thành:
- Big data observatory: Mining text for green, inclusive, resilient development insight (World Bank)
- Smart text mining system for legal and administrative documents (VIASM)
- Research on elliptic curve cryptography libraries which enable user-defined curves (Mdiua, Japan)
- Readability assessment of K-12 textbooks (World Bank)
- Improving search results for an e-commerce website (VinGroup)
- Probabilistic methods for analyzing the hidden structures in large datasets (VNUH)
- Relation extractions from unconventional text (Alt, Japan)
- Named entity recognition in conversational text (Alt, Japan)
- Inference methods for analyzing the hidden semantics in big data (Nafosted)
- Some unsupervised learning algorithms and their applications in NLP (HUS)
- Developing a computational model for the semantic processing of Vietnamese (VNUH)
- Building linguistic resources for Vietnamese syntactic parsing with tree-adjoining grammars (VNUH)