Zobrazeno 1 - 10
of 202 482
pro vyhledávání: '"Yoon, P"'
To tackle the AVeriTeC shared task hosted by the FEVER-24, we introduce a system that only employs publicly available large language models (LLMs) for each step of automated fact-checking, dubbed the Herd of Open LLMs for verifying real-world claims
Externí odkaz:
http://arxiv.org/abs/2410.12377
Novel view synthesis (NVS) aims to generate images at arbitrary viewpoints using multi-view images, and recent insights from neural radiance fields (NeRF) have contributed to remarkable improvements. Recently, studies on generalizable NeRF (G-NeRF) h
Externí odkaz:
http://arxiv.org/abs/2410.00672
Diffusion based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
Autor:
Yoon, Suhee, Yoon, Sanghyu, Lee, Hankook, Sim, Ye Seul, Choi, Sungik, Lee, Kyungeun, Cho, Hye-Seung, Lim, Woohyung
Out-of-distribution (OOD) detection, which determines whether a given sample is part of the in-distribution (ID), has recently shown promising results through training with synthetic OOD datasets. Nonetheless, existing methods often produce outliers
Externí odkaz:
http://arxiv.org/abs/2408.14841
Autor:
Yoon, Hee Suk, Yoon, Eunseop, Tee, Joshua Tian Jin, Zhang, Kang, Heo, Yu-Jung, Chang, Du-Seong, Yoo, Chang D.
Multimodal Dialogue Response Generation (MDRG) is a recently proposed task where the model needs to generate responses in texts, images, or a blend of both based on the dialogue context. Due to the lack of a large-scale dataset specifically for this
Externí odkaz:
http://arxiv.org/abs/2408.05926
Test-Time Adaptation (TTA) has emerged as a crucial solution to the domain shift challenge, wherein the target environment diverges from the original training environment. A prime exemplification is TTA for Automatic Speech Recognition (ASR), which e
Externí odkaz:
http://arxiv.org/abs/2408.05769
Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount of data for adaptation. Recent TTA methods further restrict this by f
Externí odkaz:
http://arxiv.org/abs/2410.14178
This work proposes a novel approach beyond supervised learning for effective pathological image analysis, addressing the challenge of limited robust labeled data. Pathological diagnosis of diseases like cancer has conventionally relied on the evaluat
Externí odkaz:
http://arxiv.org/abs/2410.13621
Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe generation
Externí odkaz:
http://arxiv.org/abs/2410.12761
Recent Large Language Models (LLMs) have demonstrated strong performance in translation without needing to be finetuned on additional parallel corpora. However, they still underperform for low-resource language pairs. Previous works have focused on m
Externí odkaz:
http://arxiv.org/abs/2410.11693
Autor:
Napolitano, L., Castellano, M., Pentericci, L., Haro, P. Arrabal, Fontana, A., Treu, T., Bergamini, P., Calabro, A., Mascia, S., Morishita, T., Roberts-Borsani, G., Santini, P., Vanzella, E., Vulcani, B., Zakharova, D., Bakx, T., Dickinson, M., Grillo, C., Leethochawalit, N., Llerena, M., Merlin, E., Paris, D., Rojas-Ruiz, S., Rosati, P., Wang, X., Yoon, I., Zavala, J.
We present JWST/NIRSpec PRISM follow-up of candidate galaxies at z=9-11 selected from deep JWST/NIRCam photometry in GLASS-JWST Early Release Science data. We spectroscopically confirm six sources with secure redshifts at z = 9.52-10.43, each showing
Externí odkaz:
http://arxiv.org/abs/2410.10967