Yoshida, Kotaro

4 publications

TMLR 2025 An Empirical Study of Pre-Trained Model Selection for Out-of-Distribution Generalization and Calibration Hiroki Naganuma, Ryuichiro Hataya, Kotaro Yoshida, Ioannis Mitliagkas

ICLR 2025 Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryosuke Yamaki, Ryotaro Shimizu, Yuki Saito, Julian McAuley, Hiroki Naganuma

NeurIPSW 2024 Mastering Task Arithmetic: $\tau$Jp as a Key Indicator for Weight Disentanglement Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryosuke Yamaki, Ryotaro Shimizu, Yuki Saito, Julian McAuley, Hiroki Naganuma

TMLR 2024 Towards Understanding Variants of Invariant Risk Minimization Through the Lens of Calibration Kotaro Yoshida, Hiroki Naganuma