Author

Hoifung Poon

h-index 50 View on Semantic Scholar

We have 1 of 115 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Sep 2026

Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models

This work proposes a reinforcement learning (RL) fine-tuning framework that treats EHR foundation models as generative policies over patient trajectories, and finds that RL fine-tuning consistently improves over pre-trained backbones and strong baselines.

Yu-Xin Xiao, Sheng Zhang, C. Singh et al. · arXiv.org · 0 citations