Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Kim, Sihyeon"'
Despite the astonishing performance of recent Large Vision-Language Models (LVLMs), these models often generate inaccurate responses. To address this issue, previous studies have focused on mitigating hallucinations by employing contrastive decoding
Externí odkaz:
http://arxiv.org/abs/2408.05337
Incorporating unanswerable questions into EHR QA systems is crucial for testing the trustworthiness of a system, as providing non-existent responses can mislead doctors in their diagnoses. The EHRSQL dataset stands out as a promising benchmark becaus
Externí odkaz:
http://arxiv.org/abs/2405.01588
Recent studies have introduced a new class of generative models for synthesizing implicit neural representations (INRs) that capture arbitrary continuous signals in various domains. These models opened the door for domain-agnostic generative models,
Externí odkaz:
http://arxiv.org/abs/2401.12517
The task of assigning internationally accepted commodity codes (aka HS codes) to traded goods is a critical function of customs offices. Like court decisions made by judges, this task follows the doctrine of precedent and can be nontrivial even for e
Externí odkaz:
http://arxiv.org/abs/2311.10922
Bayesian optimization is a powerful method for optimizing black-box functions with limited function evaluations. Recent works have shown that optimization in a latent space through deep generative models such as variational autoencoders leads to effe
Externí odkaz:
http://arxiv.org/abs/2310.20258
The presence of noisy labels in a training dataset can significantly impact the performance of machine learning models. To tackle this issue, researchers have explored methods for Learning with Noisy Labels to identify clean samples and reduce the in
Externí odkaz:
http://arxiv.org/abs/2310.17668
Learning implicit templates as neural fields has recently shown impressive performance in unsupervised shape correspondence. Despite the success, we observe current approaches, which solely rely on geometric information, often learn suboptimal deform
Externí odkaz:
http://arxiv.org/abs/2308.11916
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to directly apply Transformers on point clouds due to their quadratic cos
Externí odkaz:
http://arxiv.org/abs/2303.16450
Autor:
Park, Hyeonjin, Lee, Seunghun, Kim, Sihyeon, Park, Jinyoung, Jeong, Jisu, Kim, Kyung-Min, Ha, Jung-Woo, Kim, Hyunwoo J.
Graph Neural Networks (GNNs) often suffer from weak-generalization due to sparsely labeled data despite their promising results on various graph-based tasks. Data augmentation is a prevalent remedy to improve the generalization ability of models in m
Externí odkaz:
http://arxiv.org/abs/2203.14082
Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less explored in
Externí odkaz:
http://arxiv.org/abs/2110.05379