Trajectory-Invariant Latent Refinement (TILR), a training-free framework that constrains corrections to a stable refinement subspace and adaptively controls their magnitude, is proposed, which supports invariant subspaces as a practical basis for reliable latent refinement without retraining or backpropagation.
Arun Vignesh Malarkkan, M. Choudhury, Utkarsh Byahut et al.· 1 citation
This work proposes GRADE (GRadient-Aligned Data-centric rEcipe), a data-centric framework combining two mechanisms: a state-aware selector that continually admits samples aligned with the evolving multi-task gradient field, and a self-calibrating step-level gate that rejects updates likely to cause destructive overwrit...
Hong-Yu Cao, Yan-Chi Liu, Kun-Peng Liu et al.· 0 citations
High-dimensional bioinformatics data, characterized by a large number of features relative to the number of samples, pose major challenges such as the ``curse of dimensionality,''leading to overfitting, high computational cost, and poor generalization. Traditional feature selection methods often suffer from limited sca...
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shift); 3) validation sets often diverge from unseen test environments; or 4) standard generative models simply mimic outdated source d...