Kim, Juno

14 publications

NeurIPS 2025 Hessian-Guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points Naoya Yamamoto, Juno Kim, Taiji Suzuki

ICML 2025 Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation Juno Kim, Denny Wu, Jason D. Lee, Taiji Suzuki

ICLR 2025 Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li

ICLR 2025 Transformers Provably Solve Parity Efficiently with Chain of Thought Juno Kim, Taiji Suzuki

ICLR 2024 $t^3$-Variational Autoencoder: Learning Heavy-Tailed Data with Student's T and Power Divergence Juno Kim, Jaehyuk Kwon, Mincheol Cho, Hyunjong Lee, Joong-Ho Won

NeurIPSW 2024 Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression Juno Kim, Dimitri Meunier, Arthur Gretton, Taiji Suzuki, Zhu Li

ICLR 2024 Symmetric Mean-Field Langevin Dynamics for Distributional Minimax Problems Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki

NeurIPS 2024 Transformers Are Minimax Optimal Nonparametric In-Context Learners Juno Kim, Tai Nakamaki, Taiji Suzuki

ICMLW 2024 Transformers Are Minimax Optimal Nonparametric In-Context Learners Juno Kim, Tai Nakamaki, Taiji Suzuki

ICMLW 2024 Transformers Are Minimax Optimal Nonparametric In-Context Learners Juno Kim, Tai Nakamaki, Taiji Suzuki

ICLRW 2024 Transformers Learn Nonlinear Features in Context Juno Kim, Taiji Suzuki

ICML 2024 Transformers Learn Nonlinear Features in Context: Nonconvex Mean-Field Dynamics on the Attention Landscape Juno Kim, Taiji Suzuki

NeurIPSW 2024 Transformers Provably Solve Parity Efficiently with Chain of Thought Juno Kim, Taiji Suzuki

NeurIPSW 2023 Symmetric Mean-Field Langevin Dynamics for Distributional Minimax Problems Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki