Cite
Notes
Only stored in your browser.
Attribution
Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
arXiv 2025
ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate
arXiv 2024
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
arXiv 2023
from 3 papers
Yusuke Iwasawa
Yutaka Matsuo
Go Nagahara
Hiroki Furuta
Keno Harada
Masahiro Suzuki
Seong Cheol Jeong
Shohei Taniguchi
Tomoshi Iiyama
Yuta Oshima