3 papers
cs.CL2026
Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
Chuang Ma, Qianying Liu, Tomoyuki Obuchi +6
Multimodal large language models (MLLMs) remain unreliable on spatial multiple-choice questions, and their failures are often attributed to poorly attended visual information. In t…
cs.LG2025
Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model
Chuang Ma, Tomoyuki Obuchi, Toshiyuki Tanaka
A phenomenon known as ''Neural Collapse (NC)'' in deep classification tasks, in which the penultimate-layer features and the final classifiers exhibit an extremely simple geometric…
stat.ML2025
When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study
Tomoyuki Obuchi, Toshiyuki Tanaka
A toy model of binary classification is studied with the aim of clarifying the class-wise resampling/reweighting effect on the feature learning performance under the presence of cl…