Poster by Jaemin Park Papers
2 papers found
First Attentions Last: Better Exploiting First Attentions for Efficient Parallel Training
Gyudong Kim, Hyukju Na, Jin Kim et al.
NEURIPS 2025poster
From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers
Yoon Hyeok Lee, Jaemin Park, Taejin Paik et al.
ICML 2025poster