Zobrazeno 1 - 10
of 605
pro vyhledávání: '"Lee, Dongjun"'
Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent
Externí odkaz:
http://arxiv.org/abs/2410.20772
Narrow passage path planning is a prevalent problem from industrial to household sites, often facing difficulties in finding feasible paths or requiring excessive computational resources. Given that deep penetration into the environment can cause opt
Externí odkaz:
http://arxiv.org/abs/2410.20697
Dataset bias is a significant challenge in machine learning, where specific attributes, such as texture or color of the images are unintentionally learned resulting in detrimental performance. To address this, previous efforts have focused on debiasi
Externí odkaz:
http://arxiv.org/abs/2406.06134
Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of h
Externí odkaz:
http://arxiv.org/abs/2405.07467
Autor:
Shin, Juhyeon, Lee, Jonghyun, Lee, Saehyung, Park, Minjun, Lee, Dongjun, Hwang, Uiwon, Yoon, Sungroh
In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label. We developed a grad
Externí odkaz:
http://arxiv.org/abs/2402.09004
In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to downstream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre-trained weights frozen. Howev
Externí odkaz:
http://arxiv.org/abs/2308.14960
Sequential recommendation addresses the issue of preference drift by predicting the next item based on the user's previous behaviors. Recently, a promising approach using contrastive learning has emerged, demonstrating its effectiveness in recommendi
Externí odkaz:
http://arxiv.org/abs/2308.03400
For many robotic manipulation and contact tasks, it is crucial to accurately estimate uncertain object poses, for which certain geometry and sensor information are fused in some optimal fashion. Previous results for this problem primarily adopt sampl
Externí odkaz:
http://arxiv.org/abs/2305.16778
In this paper, we present a new multibody physics simulation framework that utilizes the subsystem-based structure and the Alternating Direction Method of Multiplier (ADMM). The major challenge in simulating complex high degree of freedom systems is
Externí odkaz:
http://arxiv.org/abs/2302.14344
Autor:
Lee, Dongjun1 (AUTHOR) mouse87@skku.edu, Choi, Ahnryul2 (AUTHOR) achoi@chungbuk.ac.kr, Mun, Joung Hwan1 (AUTHOR) achoi@chungbuk.ac.kr
Publikováno v:
Bioengineering (Basel). Sep2024, Vol. 11 Issue 9, p941. 21p.
