Zobrazeno 1 - 10
of 7 766
pro vyhledávání: '"On, Jungmin"'
Systolic arrays have proven to be highly efficient for parallelized matrix-matrix multiplication (MMM), utilizing synchronized, heartbeat-like data flows across an array of processing elements. While optical structures such as waveguide crossbar arra
Externí odkaz:
http://arxiv.org/abs/2410.21671
Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results have shown t
Externí odkaz:
http://arxiv.org/abs/2410.20710
Autor:
Choi, Nayoung, Lee, Youngjune, Cho, Gyu-Hwung, Jeong, Haeyu, Kong, Jungmin, Kim, Saehun, Park, Keunchan, Choi, Jaeho, Cho, Sarah, Jeong, Inchang, Nam, Gyohee, Han, Sunghoon, Yang, Wonil
Large Language Models (LLMs) excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries. These queries are challenging for feedback-based rankings due to sparse user engagement and
Externí odkaz:
http://arxiv.org/abs/2410.18097
Weakly supervised semantic segmentation (WSSS) approaches typically rely on class activation maps (CAMs) for initial seed generation, which often fail to capture global context due to limited supervision from image-level labels. To address this issue
Externí odkaz:
http://arxiv.org/abs/2409.15801
The R package psvmSDR: A Unified Algorithm for Sufficient Dimension Reduction via Principal Machines
Sufficient dimension reduction (SDR), which seeks a lower-dimensional subspace of the predictors containing regression or classification information has been popular in a machine learning community. In this work, we present a new R software package p
Externí odkaz:
http://arxiv.org/abs/2409.01547
Domain generalizability is a crucial aspect of a deep learning model since it determines the capability of the model to perform well on data from unseen domains. However, research on the domain generalizability of deep learning models for vision-lang
Externí odkaz:
http://arxiv.org/abs/2407.19795
Autor:
Robbani, Irfan, Reisert, Paul, Inoue, Naoya, Pothong, Surawat, Guerraoui, Camélia, Wang, Wenzhi, Naito, Shoichi, Choi, Jungmin, Inui, Kentaro
Prior research in computational argumentation has mainly focused on scoring the quality of arguments, with less attention on explicating logical errors. In this work, we introduce four sets of explainable templates for common informal logical fallaci
Externí odkaz:
http://arxiv.org/abs/2406.12402
Real-world data often follow a long-tailed distribution with a high imbalance in the number of samples between classes. The problem with training from imbalanced data is that some background features, common to all classes, can be unobserved in class
Externí odkaz:
http://arxiv.org/abs/2406.02223
Transformer-based models have achieved dominant performance in numerous NLP tasks. Despite their remarkable successes, pre-trained transformers such as BERT suffer from a computationally expensive self-attention mechanism that interacts with all toke
Externí odkaz:
http://arxiv.org/abs/2406.01283
Autor:
Yun, Juyoung, Shin, Jungmin
Solar flares, especially C, M, and X class, pose significant risks to satellite operations, communication systems, and power grids. We present a novel approach for predicting extreme solar flares using HMI intensitygrams and magnetograms. By detectin
Externí odkaz:
http://arxiv.org/abs/2405.14750