Yufei Chen

Tailoring public dataset mixtures for DP pre-training via private linear regression unlocks substantial utility gains, boosting X-ray classification AUC by up to 0.037 and reducing language model perplexity by 16%.

A large-scale reproducibility study to systematically investigate the impact of semantic ID design on generative recommendation under a unified experimental framework provides a controlled and reproducible understanding of semantic ID design and offers practical insights for future generative recommender systems.

LEAP reveals that separating evidence evaluation can drastically enhance the accuracy and interpretability of probabilistic forecasts in LLM applications.

Achieving precise medical image segmentation with limited labeled data is now possible by embracing intra-class heterogeneity through innovative prototype learning.

Prefix Retention Optimization boosts target identifier retention in multimodal generative retrieval, closing the critical indexing-decoding gap.

Overcome the limitations of existing semi-supervised segmentation methods by learning structural consensus across samples, achieving more generalizable pancreas segmentation under sparse supervision.