Author

Chiang-Hsuan Hsu

h-index 3 View on Semantic Scholar

We have 2 of 15 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.

#machine learning Jun 2026

Learning to Refine Hidden States for Reliable LLM Reasoning

ReLAR is proposed, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding that improves accuracy, generation quality, and reasoning stability with substantially lower inference overhead than explicit reasoning baselines.

Chiang-Hsuan Hsu, Jui-Ming Yao · arXiv.org · 0 citations

#natural language process... Preprint Aug 2026

DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening

DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support for type 2 diabetes mellitus risk screening and guideline-grounded report generation from electronic health records (EHRs).

Yung Wei Shueh, Zhi-Jie Chen, Chiang-Hsuan Hsu et al. · 0 citations