Author

Hong-Yu Cao

3 papers indexed here

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.

#artificial intelligence Preprint Oct 2026

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

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...

Hong-Yu Cao, Yan-Chi Liu, Kun-Peng Liu et al. · 0 citations

#artificial intelligence Preprint Oct 2026

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

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shift); 3) validation sets often diverge from unseen test environments; or 4) standard generative models simply mimic outdated source d...

Hong-Yu Cao, Xin-Yuan Wang, Arun Vignesh Malarkkan et al. · 1 citation

#artificial intelligence Preprint Sep 2026

Flat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator

Data shape determines how features are structured, how patterns are separated, and how distributions cover the underlying domain. Poor data shape can make models learn noise rather than generalizable structure. This paper studies robust feature-centric data reshaping: generating feature transformations that remain usef...

Hong-Yu Cao, Kun-Peng Liu, Fei Xie et al. · 1 citation