"neural architecture design" Papers
5 papers found
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Akhiad Bercovich, Mohammed Dabbah, Omri Puny et al.
NeurIPS 2025spotlightarXiv:2503.18908
2
citations
From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs
Xin Li, Xiaotao Zheng, Zhihong Xia
NeurIPS 2025poster
Unleashing Vecset Diffusion Model for Fast Shape Generation
Zeqiang Lai, Zhao Yunfei, Zibo Zhao et al.
ICCV 2025highlightarXiv:2503.16302
14
citations
On the Nonlinearity of Layer Normalization
Yunhao Ni, Yuxin Guo, Junlong Jia et al.
ICML 2024poster
Rethinking Optimization and Architecture for Tiny Language Models
Yehui Tang, Kai Han, Fangcheng Liu et al.
ICML 2024poster