Yanli Wang
2 papers · Latest:
Quantitative Methods (Biology)
LAFA: A Framework for Reproducible Longitudinal Assessment of Protein Function Annotation Models
LAFA is a new framework for continuous, reproducible, and longitudinal assessment of protein function prediction models, addressing CAFA's periodic limitation.
2604.20782
Natural Language ProcessingBeyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations
Robust conformal prediction for LLMs uses internal Layer-Wise Information (LI) scores to improve reliability, especially under distribution shift.
2604.16217
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.