1 code implementation • 21 Jun 2023 • Yookoon Park, David M. Blei
In this paper, we propose a novel criterion for reliable predictive uncertainty: a model's predictive variance should be grounded in the empirical density of the input.
1 code implementation • 30 Nov 2022 • Yookoon Park, Mahmoud Azab, Bo Xiong, Seungwhan Moon, Florian Metze, Gourab Kundu, Kirmani Ahmed
Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness.
no code implementations • 30 Nov 2022 • Yookoon Park, Chris Dongjoo Kim, Gunhee Kim
Based on the Laplace approximation of the latent variable posterior, VLAEs enhance the expressiveness of the posterior while reducing the amortization error.
1 code implementation • 7 Dec 2021 • Yookoon Park, Sangho Lee, Gunhee Kim, David M. Blei
We argue that the deep encoder should maximize its nonlinear expressivity on the data for downstream predictors to take full advantage of its representation power.
4 code implementations • NAACL 2018 • Yookoon Park, Jaemin Cho, Gunhee Kim
To solve the degeneration problem, we propose a novel model named Variational Hierarchical Conversation RNNs (VHCR), involving two key ideas of (1) using a hierarchical structure of latent variables, and (2) exploiting an utterance drop regularization.
no code implementations • ICML 2017 • Juyong Kim, Yookoon Park, Gunhee Kim, Sung Ju Hwang
We propose a novel deep neural network that is both lightweight and effectively structured for model parallelization.