Wei Sun’s Personal Website

I am a PhD researcher in Computer Science at KU Leuven, supervised by Prof. Marie-Francine Moens. My research connects medical natural language processing with multilingual large language models, with a focus on efficient adaptation, knowledge editing, and explainable AI.

Expected graduation · January 2027.

Previously, I completed my master's degree at Aalto University under the supervision of Prof. Pekka Marttinen, and my bachelor's degree at Macau University of Science and Technology under Prof. Yanyan Liang. My work brings together method development and clinical applications through collaborations with European research projects and hospitals.

Research interests

  • Medical language understanding: Clinical information extraction, temporal relations, and automated medical coding.
  • Multilingual language models: Knowledge editing, cross-lingual transfer, and inference-time intervention.
  • Efficient & explainable AI: Parameter-efficient fine-tuning, evidence-based explanations, and weakly supervised argument mining.

Selected research

All publications
TACL · 2026 Accepted

Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

Wei Sun, Tingyu Qu, Jesse Davis, Marie-Francine Moens

Models event-pair interactions inside low-rank bottlenecks for temporal relation extraction with Adapter and LoRA fine-tuning.

Research projects

My contributions to collaborative European research projects.

AIDAVA

Medical language models & multilingual information extraction

Led research on medical language model pretraining and information extraction, from domain knowledge integration and parameter-efficient adaptation to multilingual temporal relation modeling and evaluation.

ANTIDOTE

Evidence-based explanations for medical AI

Led method development for medical evidence retrieval, question answering, and explanation generation. Developed weakly supervised argument mining to structure claims, evidence, and their relations.

INTERVENE

Clinical information extraction with limited supervision

Led low-resource information extraction research for Finnish clinical text, using medical ontologies to construct weak supervision and develop domain-adapted named entity recognition models.

Get in touch

For research inquiries and collaboration, please contact me by email.

s872078724@gmail.com