3 papers
cs.LG2026
Modular Norm RandOpt: Population-Efficient Ensembling through Architecture-Aware Perturbations
Kirato Yoshihara, Hiroaki Hamade
RandOpt samples weight-perturbed language models and ensembles top-ranked candidates through plurality voting, but its global perturbation scale ignores heterogeneous module geomet…
cs.LG2026
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
Kirato Yoshihara
Weight-space geometry plays a central role in neural network optimization, yet manifold constraints are often applied uniformly across all weight matrices. In this work, we ask whe…
eess.IV2026
VesselBridge3D: A Foundation Model Adaptation Framework for Label-Efficient 3D Vessel Segmentation
Kirato Yoshihara, Yohei Sugawara, Yuta Tokuoka +1
State-of-the-art vessel segmentation methods typically require large-scale annotated datasets and suffer from severe performance degradation under domain shifts. In clinical practi…