
Research
研究
研究業績
カテゴリー
研究領域
年
-
Disappearance of Timestep Embedding: A Case Study on Neural ODE and Diffusion Models
Bum Jun Kim, Yoshinobu Kawahara, Sang Woo Kim
Transactions on Machine Learning Research (TMLR)
-
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks
Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR)
-
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Hiroki Furuta, Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo
Transactions on Machine Learning Research (TMLR).