no code implementations • 23 Apr 2024 • Raehyuk Jung, Hyojun Go, Jaehyuk Yi, Jiho Jang, Daniel Kim, Jay Suh, Aiden Lee, Cooper Han, Jae Lee, Jeff Kim, Jin-Young Kim, Junwan Kim, Kyle Park, Lucas Lee, Mars Ha, Minjoon Seo, Abraham Jo, Ed Park, Hassan Kianinejad, SJ Kim, Tony Moon, Wade Jeong, Andrei Popescu, Esther Kim, EK Yoon, Genie Heo, Henry Choi, Jenna Kang, Kevin Han, Noah Seo, Sunny Nguyen, Ryan Won, Yeonhoo Park, Anthony Giuliani, Dave Chung, Hans Yoon, James Le, Jenny Ahn, June Lee, Maninder Saini, Meredith Sanders, Soyoung Lee, Sue Kim, Travis Couture
This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language.
no code implementations • 15 Mar 2024 • Jin-Young Kim, Hyojun Go, Soonwoo Kwon, Hyun-Gyoon Kim
By organizing timesteps or noise levels into clusters and training models with descending orders of difficulty, we facilitate an order-aware training regime, progressing from easier to harder denoising tasks, thereby deviating from the conventional approach of training diffusion models simultaneously across all timesteps.
1 code implementation • 14 Mar 2024 • Byeongjun Park, Hyojun Go, Jin-Young Kim, Sangmin Woo, Seokil Ham, Changick Kim
To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation.
1 code implementation • 26 Dec 2023 • Sangmin Woo, Byeongjun Park, Hyojun Go, Jin-Young Kim, Changick Kim
This work introduces HarmonyView, a simple yet effective diffusion sampling technique adept at decomposing two intricate aspects in single-image 3D generation: consistency and diversity.
2 code implementations • 11 Oct 2023 • Byeongjun Park, Sangmin Woo, Hyojun Go, Jin-Young Kim, Changick Kim
Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL).
no code implementations • 8 Jun 2023 • Yunsung Lee, Jin-Young Kim, Hyojun Go, Myeongho Jeong, Shinhyeok Oh, Seungtaek Choi
In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME).
no code implementations • 7 Jun 2023 • Jin-Young Kim, Soonwoo Kwon, Hyojun Go, Yunsung Lee, Seungtaek Choi
Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones.
1 code implementation • NeurIPS 2023 • Hyojun Go, Jinyoung Kim, Yunsung Lee, SeungHyun Lee, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi
Through this, our approach addresses the issue of negative transfer in diffusion models by allowing for efficient computation of MTL methods.
no code implementations • 30 May 2023 • Hyun Seung Lee, Seungtaek Choi, Yunsung Lee, Hyeongdon Moon, Shinhyeok Oh, Myeongho Jeong, Hyojun Go, Christian Wallraven
To mitigate these issues, here we propose a novel retrieval approach CEAA that provides effective learning in educational text classification.
no code implementations • 26 May 2023 • Shinhyeok Oh, Hyojun Go, Hyeongdon Moon, Yunsung Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi
To this end, we propose to paraphrase the reference question for a more robust QG evaluation.
1 code implementation • CVPR 2023 • Hyojun Go, Yunsung Lee, Jin-Young Kim, SeungHyun Lee, Myeongho Jeong, Hyun Seung Lee, Seungtaek Choi
For that, the existing practice is to fine-tune the guidance models with labeled data corrupted with noises.
no code implementations • 4 Oct 2022 • Yunsung Lee, Gyuseong Lee, Kwangrok Ryoo, Hyojun Go, JiHye Park, Seungryong Kim
In addition, through Fourier analysis of feature maps, the model's response patterns according to signal frequency changes, we observe which inductive bias is advantageous for each data scale.
no code implementations • 15 Sep 2022 • Byeongjun Park, Hyojun Go, Changick Kim
Although recent methods generate high-quality novel views, synthesizing with only one explicit or implicit 3D geometry has a trade-off between two objectives that we call the "seesaw" problem: 1) preserving reprojected contents and 2) completing realistic out-of-view regions.
no code implementations • 8 Nov 2021 • Junyoung Byun, Hyojun Go, Changick Kim
We apply the GADA strategy to two existing attack methods and show overwhelming performance improvement in the experiments on the LFW and CPLFW datasets.
no code implementations • 8 Nov 2021 • Byeongjun Park, Taekyung Kim, Hyojun Go, Changick Kim
In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features.
no code implementations • 13 Jan 2021 • Junyoung Byun, Hyojun Go, Changick Kim
In this paper, we pay attention to an implicit assumption of query-based black-box adversarial attacks that the target model's output exactly corresponds to the query input.