3 papers
eess.SP2026
Batch Effects In Brain Foundation Model Embeddings
Ye Tao, Bradley T. Baker, Yu Wu +4
Foundation models show strong potential for large-scale, high-dimensional biomedical applications, yet their ability to capture relevant neurobiological characteristics remains und…
cs.CR2026
Functional Approximation Methods for Differentially Private Distribution Estimation
Ye Tao, Anand D. Sarwate
The cumulative distribution function (CDF) is fundamental for characterizing random variables, making it essential in applications that require privacy-preserving data analysis. Th…
cs.AI2026
From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades
Yu Wu, Shuo Wu, Ye Tao +2
Standard LLM cascades improve efficiency by deferring difficult queries from weak to strong models. However, these systems are typically static: when faced with repeated or semanti…