diagnosis prediction 1efficient training 1large language models 1longitudinal data 1pediatric health records 1residual stream expansion 1risk forecasting 1sparse computation 1transformer architectures 1transformer models 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.LG2026
xHC: Expanded Hyper-Connections
Xiangdong Zhang, Xiaohan Qin, Sunan Zou +10
The paper introduces xHC, a method that expands the residual stream of Transformers to many parallel streams using temporal feature augmentation and a sparse update scheme, enablin…
cs.LG2026
TEDDY: A Pediatric Foundation Model for Risk Forewarning from ICD-Coded Diagnostic Histories
Matthew Brady Neeley, Jorge Botas, Johnathan Jia +5
The paper introduces TEDDY, a compact transformer model that learns from pediatric ICD-10 diagnosis histories to predict disease onset and visit timing up to years in advance.