3 papers
cs.LG2026
Understanding Generalization from Embedding Dimension and Distributional Convergence
Junjie Yu, Zhuoli Ouyang, Haotian Deng +5
Deep neural networks often generalize well despite heavy over-parameterization, challenging classical parameter-based analyses. We study generalization from a representation-centri…
cs.LG2026
Local Intrinsic Dimension of Representations Predicts Alignment and Generalization in AI Models and Human Brain
Junjie Yu, Wenxiao Ma, Chen Wei +4
Recent work has found that neural networks with stronger generalization tend to exhibit higher representational alignment with one another across architectures and training paradig…
q-bio.NC2025
Scale-Invariance Drives Convergence in AI and Brain Representations
Junjie Yu, Wenxiao Ma, Jianyu Zhang +4
Despite variations in architecture and pretraining strategies, recent studies indicate that large-scale AI models often converge toward similar internal representations that also a…