no code implementations • EMNLP 2020 • Byung-Ju Choi, Jimin Hong, David Park, Sang Wan Lee
Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive.
no code implementations • 22 Mar 2024 • Geon Yeong Park, Hyeonho Jeong, Sang Wan Lee, Jong Chul Ye
The evolution of diffusion models has greatly impacted video generation and understanding.
1 code implementation • NeurIPS 2023 • Geon Yeong Park, Jeongsol Kim, Beomsu Kim, Sang Wan Lee, Jong Chul Ye
Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment.
1 code implementation • CVPR 2023 • Geon Yeong Park, Sangmin Lee, Sang Wan Lee, Jong Chul Ye
Neural networks are often biased to spuriously correlated features that provide misleading statistical evidence that does not generalize.
Ranked #2 on Facial Attribute Classification on bFFHQ
no code implementations • 11 Oct 2022 • Geon Yeong Park, Chanyong Jung, Sangmin Lee, Jong Chul Ye, Sang Wan Lee
Specifically, we first pretrain a biased encoder in a self-supervised manner with the rank regularization, serving as a semantic bottleneck to enforce the encoder to learn the spuriously correlated attributes.
no code implementations • 7 Oct 2022 • Jungbae Park, Jinyoung Kim, Soonwoo Kwon, Sang Wan Lee
Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates.
no code implementations • 10 Aug 2022 • Anil Yaman, Joel Z. Leibo, Giovanni Iacca, Sang Wan Lee
Here we show that by introducing a model of social norms, which we regard as emergent patterns of decentralized social sanctioning, it becomes possible for groups of self-interested individuals to learn a productive division of labor involving all critical roles.
1 code implementation • CVPR 2022 • Hyung-gun Chi, Myoung Hoon Ha, Seunggeun Chi, Sang Wan Lee, QiXing Huang, Karthik Ramani
Human skeleton-based action recognition offers a valuable means to understand the intricacies of human behavior because it can handle the complex relationships between physical constraints and intention.
Ranked #7 on Skeleton Based Action Recognition on N-UCLA
1 code implementation • 18 Jun 2021 • Anil Yaman, Nicolas Bredeche, Onur Çaylak, Joel Z. Leibo, Sang Wan Lee
Based on these findings, we hypothesized that meta-control of individual and social learning strategies provides effective and sample-efficient learning in volatile and uncertain environments.
no code implementations • ICCV 2021 • Geon Yeong Park, Sang Wan Lee
Here we adopt an information-theoretic approach to identify and resolve the potential adverse effect of the multiple domain discriminators on MDA: disintegration of domain-discriminative information, limited computational scalability, and a large variance in the gradient of the loss during training.
no code implementations • ICCV 2021 • Geon Yeong Park, Sang Wan Lee
To overcome such limitations, we deviate from the existing input-space-based adversarial training regime and propose a single-step latent adversarial training method (SLAT), which leverages the gradients of latent representation as the latent adversarial perturbation.
no code implementations • 1 Jan 2021 • Geon Yeong Park, Sang Wan Lee
Our framework shows that the information shared across domains cannot be gleaned with multiple discriminators.
no code implementations • 20 Sep 2020 • Byung-Ju Choi, Jimin Hong, David Keetae Park, Sang Wan Lee
Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive.
no code implementations • 14 Aug 2020 • Hyeonmook Park, Jungbae Park, Sang Wan Lee
We demonstrate that the proposed model is highly efficient, and provides more accurate speaker verification than GE2E.
2 code implementations • 9 Jul 2020 • Dongjae Kim, Jee Hang Lee, Jae Hoon Shin, Minsu Abel Yang, Sang Wan Lee
In the reliability test, which includes the latent behavior profile and the parameter recoverability test, we showed that the prefrontal RL reliably learned the latent policies of the humans, while all the other models failed.