Researcher

Xinyan Yu

2 developments in the corpus

Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.

Latest

Everything in the corpus, newest first.

SEP 9, 2026 · JOURNAL ARTICLE

A Latent profile and network intervention analysis of psychosomatic symptoms in lung cancer immunotherapy patients

PLOS One

Cross-sectional observational study identifying symptom phenotypes and generating hypotheses about intervention targets through network analysis and computer simulation, without intervention trials or prospective validation.

PreliminaryCancer Survivorship and Care Danwen Zheng Xiaoli Sun

Reported

C1 phenotype prevalence25.1%

C2 phenotype prevalence29.2%

C3 phenotype prevalence45.6%

AUG 7, 2026 · PREPRINT

SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time

arXiv

This is a machine learning systems paper presenting a novel framework (SkillAligner) evaluated on agent benchmarks, without peer review, reporting improvements over baselines but lacking clinical or definitive real-world validation.

PreliminaryLizhou Liang Yuntai Bao Qinfeng Li

Study details

DesignEmpirical comparative evaluation across mul…

InterventionSkillAligner: training-free execution-time…

ComparatorExisting skill-use baselines (not named or…