no code implementations • 9 Feb 2024 • Jongmin Yoon, Juho Lee
Straightening the probability flow of the continuous-time generative models, such as diffusion models or flow-based models, is the key to fast sampling through the numerical solvers, existing methods learn a linear path by directly generating the probability path the joint distribution between the noise and data distribution.
no code implementations • NeurIPS 2021 • Giung Nam, Jongmin Yoon, Yoonho Lee, Juho Lee
We propose a simple approach for reducing this gap, i. e., making the distilled performance close to the full ensemble.
1 code implementation • 11 Jun 2021 • Jongmin Yoon, Sung Ju Hwang, Juho Lee
Recently, an Energy-Based Model (EBM) trained with Markov-Chain Monte-Carlo (MCMC) has been highlighted as a purification model, where an attacked image is purified by running a long Markov-chain using the gradients of the EBM.
1 code implementation • 19 Nov 2018 • Jongmin Yoon, Michael E. Peskin
We compute fermion pair production cross sections in $e^+e^-$ annihilation in models of electroweak symmetry breaking in warped 5-dimensional space.
High Energy Physics - Phenomenology
1 code implementation • 29 Oct 2018 • Jongmin Yoon, Michael E. Peskin
We analyze models of electroweak symmetry breaking in warped 5-dimensional space with gauge bosons and fermions in the bulk.
High Energy Physics - Phenomenology
1 code implementation • 22 Sep 2017 • Jongmin Yoon, Michael E. Peskin
We study fermion condensation in the Randall-Sundrum background as a setting for composite Higgs models.
High Energy Physics - Phenomenology