Yoshida, Kotaro

6 publications

ICLR 2026 DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging Kotaro Yoshida, Yuji Naraki, Takafumi Horie, Ryotaro Shimizu, Ioannis Mitliagkas, Hiroki Naganuma

ICLR 2026 On Fairness of Task Arithmetic: The Role of Task Vectors Laura Gomezjurado Gonzalez, Hiroki Naganuma, Kotaro Yoshida, Takafumi Horie, Yuji Naraki, Ryotaro Shimizu

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