Zobrazeno 1 - 10
of 128
pro vyhledávání: '"Lee, Suyoung"'
Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image. Existing works based on neural radiance fields demonstrate successful 3D reconstruction qual
Externí odkaz:
http://arxiv.org/abs/2410.20686
Offline reinforcement learning (RL) has progressed with return-conditioned supervised learning (RCSL), but its lack of stitching ability remains a limitation. We introduce $Q$-Aided Conditional Supervised Learning (QCS), which effectively combines th
Externí odkaz:
http://arxiv.org/abs/2402.02017
With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target scene to specific domain, primarily due to their training strategies
Externí odkaz:
http://arxiv.org/abs/2311.13384
The recent success of Transformer in natural language processing has sparked its use in various domains. In offline reinforcement learning (RL), Decision Transformer (DT) is emerging as a promising model based on Transformer. However, we discovered t
Externí odkaz:
http://arxiv.org/abs/2310.03022
Autor:
Lee, Suyoung, Lee, Sangjae, Jung, Saegyeol, Jung, Jiwon, Kim, Donghan, Lee, Yeonjae, Seok, Byeongjun, Kim, Jaeyoung, Park, Byeong Gyu, Šmejkal, Libor, Kang, Chang-Jong, Kim, Changyoung
Altermagnetism is a newly identified fundamental class of magnetism with vanishing net magnetization and time-reversal symmetry broken electronic structure. Probing the unusual electronic structure with nonrelativistic spin splitting would be a direc
Externí odkaz:
http://arxiv.org/abs/2308.11180
Autor:
Kim, Younsik, Oh, Dongjin, Huh, Soonsang, Song, Dongjoon, Jeong, Sunbeom, Kwon, Junyoung, Kim, Minsoo, Kim, Donghan, Ryu, Hanyoung, Jung, Jongkeun, Kyung, Wonshik, Sohn, Byungmin, Lee, Suyoung, Hyun, Jounghoon, Lee, Yeonghoon, Kim, Yeongkwan Kimand Changyoung
Publikováno v:
Review of Scientific Instruments 92, 073901 (2021)
In spectroscopic experiments, data acquisition in multi-dimensional phase space may require long acquisition time, owing to the large phase space volume to be covered. In such case, the limited time available for data acquisition can be a serious con
Externí odkaz:
http://arxiv.org/abs/2107.00844
Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms do not achi
Externí odkaz:
http://arxiv.org/abs/2106.10147
Publikováno v:
In Energy 15 April 2024 293
Autor:
Lee, Suyoung, Chung, Sae-Young
The generalization ability of most meta-reinforcement learning (meta-RL) methods is largely limited to test tasks that are sampled from the same distribution used to sample training tasks. To overcome the limitation, we propose Latent Dynamics Mixtur
Externí odkaz:
http://arxiv.org/abs/2105.13524
Motion blur is a common photography artifact in dynamic environments that typically comes jointly with the other types of degradation. This paper reviews the NTIRE 2021 Challenge on Image Deblurring. In this challenge report, we describe the challeng
Externí odkaz:
http://arxiv.org/abs/2104.14854