no code implementations • 8 Mar 2024 • Alexander Marrapese, Basem Suleiman, Imdad Ullah, Juno Kim
In this paper, we propose a novel framework for evaluating the nuanced conversation abilities of LLMs.
no code implementations • 2 Feb 2024 • Juno Kim, Taiji Suzuki
However, existing theoretical studies on how this phenomenon arises are limited to the dynamics of a single layer of attention trained on linear regression tasks.
no code implementations • 2 Dec 2023 • Juno Kim, Jaehyuk Kwon, Mincheol Cho, Hyunjong Lee, Joong-Ho Won
In this paper, we explore the use of heavy-tailed models to combat over-regularization.
no code implementations • 2 Dec 2023 • Juno Kim, Kakei Yamamoto, Kazusato Oko, Zhuoran Yang, Taiji Suzuki
In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates.
no code implementations • 10 Feb 2023 • Juno Kim
We propose a multidimensional smoothing spline algorithm in the context of manifold learning.
no code implementations • 8 Jun 2021 • Juno Kim
Social media creates crucial mass changes, as popular posts and opinions cast a significant influence on users' decisions and thought processes.