Kumano, Soichiro

5 publications

ICLR 2026 Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

ICLR 2024 Theoretical Understanding of Learning from Adversarial Perturbations Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

NeurIPS 2024 Wide Two-Layer Networks Can Learn from Adversarial Perturbations Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

NeurIPS 2023 Adversarial Training from Mean Field Perspective Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

NeurIPSW 2023 Theoretical Explanation for Generalization from Adversarial Perturbations Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki