Authors

Hongyu Cao

Publications 2

Preprint Open access

Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning

Hongyu Cao, Yanchi Liu, Kunpeng Liu et al. · 2026

LoRA fine-tuning adapts small language models (SLMs) to heterogeneous instruction data within a low-rank update subspace, making it vulnerable to three structural problems: conflicting gradients that cancel, static data selection that cannot track evolving learning dynamics, and subspace saturation that causes later up …

Preprint Open access

Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweighting

Hongyu Cao, Xinyuan Wang, Arun Vignesh Malarkkan et al. · 2026

In many industrial applications, 1) tabular data is scarce and imbalanced and thus requires synthetic expansion; 2) input distributions drift between training and deployment (covariate shift); 3) validation sets often diverge from unseen test environments; or 4) standard generative models simply mimic outdated source d …

Co-authors