Research
研究
研究業績
カテゴリー
研究領域
年
-
Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability
Bum Jun Kim, Shohei Taniguchi, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo
Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence (UAI 2026), August 2026
-
Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
Gnankan Landry Regis N’guessan, Bum Jun Kim
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), July 2026
-
Unlocking Noise-Resistant Vision: Key Architectural Secrets for Robust Models Against Gaussian Noise
Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), July 2026
-
Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model
Kotaro Ikeda, Masanori Koyama, Jinzhe Zhang, Kohei Hayashi, Kenji Fukumizu
Advances in Neural Information Processing Systems 38 (NeurIPS 2025), December 2025.
-
When Does Metadata Conditioning (NOT) Work for Language Model Pre-Training? A Study with Context-Free Grammars
Rei Higuchi, Ryotaro Kawata, Naoki Nishikawa, Kazusato Oko, Shoichiro Yamaguchi, Sosuke Kobayashi, Seiya Tokui, Kohei Hayashi, Daisuke Okanohara, Taiji Suzuki
Conference on Language Modeling (COLM 2025), October 2025
-
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo.
Advances in Neural Information Processing Systems (NeurIPS 2025), Spotlight, December 2025
-
A computational model of canonical cortical microcircuits for dynamic Bayesian inference and control as inference
Naohiro Yamauchi, Yoshimasa Tawatsuji, Yudai Suzuki, Hiroshi Yamakawa, Kenji Doya
Neuroscience Research, July 2025
-
A Unified MDP Framework for Solving Robust, Convex, Multi-Discount Constraints, and Beyond
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Wataru Kumagai, Paavo Parmas, Yutaka Matsuo
Proceedings of the Reinforcement Learning Conference (RLC 2025), Finding the Frame Workshop, June 2025
-
FullDiffusion: Diffusion Models Without Time Truncation
Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
International Conference on Learning Representations (ICLR 2025), DeLTa Workshop, April 2025
-
FullDiffusion: Diffusion Models Without Time Truncation
Shohei Taniguchi, Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo
International Conference on Learning Representations (ICLR 2025), DeLTa Workshop, April 2025