Naoki Nishikawa
~Naoki_Nishikawa1
6
论文总数
6.0
年均投稿
平均评分
接收情况6/6
会议分布
NeurIPS
2
ICML
2
ICLR
1
COLM
1
发表论文 (6 篇)
20256 篇
4
Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency
NeurIPS 2025Poster
4
Nonlinear transformers can perform inference-time feature learning
ICML 2025Poster
4
State Space Models are Provably Comparable to Transformers in Dynamic Token Selection
ICLR 2025Poster
4
When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
COLM 2025Poster
5
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
NeurIPS 2025Spotlight
4
Mixture of Experts Provably Detect and Learn the Latent Cluster Structure in Gradient-Based Learning
ICML 2025Poster