Lam Nguyen

Researcher, AI for Scientific Discovery

I play with semantic search and database internals.

I am a researcher working on AI for scientific discovery. My research focuses on designing algorithms and building a semantic data layer for LLMs: getting the right context to a model, from the right source, at a bounded cost. I approach LLM reasoning through the lens of databases, making retrieval trustworthy, context-aware, and cache-aware. I hold an M.S. in Computer Science from Case Western Reserve University, advised by Dr. Yinghui Wu, with a thesis on ontology matching with knowledge retrieval and efficient language models.

In practice that means a few connected threads. Database systems, in OntoDB, a database management system for ontologies supporting SPARQL. Natural language interfaces to databases (NLIDB), in Hermes, a library that turns questions into SPARQL. Query validation, in OntoCheck, which checks whether an ontology can answer the questions its domain asks. Retrieval-grounded matching, in KROMA, which retrieves context for an LLM to align ontologies. And long-horizon, memory-augmented agents for scientific discovery in cost-bounded settings, in MOIRA, steered by a harness of small decision models.

GoalScientific discovery
AgentsMOIRA: memory-augmented, cost-bounded agents
InterfaceHermes: natural-language questions to SPARQL
TrustOntoCheck: query-driven ontology validation
IntegrationKROMA: retrieval-grounded ontology matching
DatabaseOntoDB: database management system for ontologies

Before this I trained competitive programming, reaching the top 1.26% in LeetCode contests with 1000+ problems solved, and I still find data structures and algorithms a useful lens for thinking about agentic memory.

Reaching me is O(log log log n), practically a constant. Please feel free to reach out at lamng3.work [at] gmail [dot] com if you'd like to talk about any of the above.

Experiences

Selected Publications

  1. L. Nguyen, E. Frakes, H. Ma, O. Dernek, R. H. French, and Y. Wu. MOIRA: Memory-Augmented Ontology Integration with Cost-Bounded Reasoning Agents. [Code]
  2. L. Nguyen, E. Barcelos, R. French, and Y. Wu. KROMA: Ontology Matching with Knowledge Retrieval and Large Language Models. International Semantic Web Conference (ISWC), 2025. [Paper] [Code]
  3. R. Kundu, R. Mehdi, V. D. Tran, E. Frakes, A. Daundkar, M. Sumudumalie, V. S. Mandayam, J. A. Lample, M. Li, L. S. Bruckman, E. I. Barcelos, A. Sehirlioglu, R. H. French, and Y. Wu. OntoCheck: Query-Driven Ontology Assessments for Scientific Domain Applications. [Paper] [Code]
  4. L. Nguyen. Ontology Matching with Knowledge Retrieval and Efficient Large Language Models. M.S. thesis, Case Western Reserve University, 2025. [Thesis]

Open Source

Service

Reviewing: Co-reviewer, IEEE BigData 2024.