5 citations · 11 across the 10 of their papers we have counts for
10 papers
K-EXAONE 2.0 Technical Report
Eunbi Choi, Kibong Choi, Sehyun Chun +74
This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundatio…
EXAONE 4.5 Technical Report
Eunbi Choi, Kibong Choi, Sehyun Chun +55
This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual enc…
MolMole: Molecule Mining from Scientific Literature
LG AI Research, Sehyun Chun, Jiye Kim +31
The extraction of molecular structures and reaction data from scientific documents is challenging due to their varied, unstructured chemical formats and complex document layouts. T…
Universal Noise Annotation: Unveiling the Impact of Noisy annotation on Object Detection
Kwangrok Ryoo, Yeonsik Jo, Seungjun Lee +5
For object detection task with noisy labels, it is important to consider not only categorization noise, as in image classification, but also localization noise, missing annotations…
SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels
Daehwan Kim, Kwangrok Ryoo, Hansang Cho +1
Annotating the dataset with high-quality labels is crucial for performance of deep network, but in real world scenarios, the labels are often contaminated by noise. To address this…
3D GAN Inversion with Pose Optimization
Jaehoon Ko, Kyusun Cho, Daewon Choi +2
With the recent advances in NeRF-based 3D aware GANs quality, projecting an image into the latent space of these 3D-aware GANs has a natural advantage over 2D GAN inversion: not on…
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
Yunsung Lee, Gyuseong Lee, Kwangrok Ryoo +3
There are two de facto standard architectures in recent computer vision: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Strong inductive biases of convolution…
ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization
Jiwon Kim, Youngjo Min, Daehwan Kim +4
We present a novel semi-supervised learning framework that intelligently leverages the consistency regularization between the model's predictions from two strongly-augmented views…
Semi-Supervised Learning of Semantic Correspondence with Pseudo-Labels
Jiwon Kim, Kwangrok Ryoo, Junyoung Seo +4
Establishing dense correspondences across semantically similar images remains a challenging task due to the significant intra-class variations and background clutters. Traditionall…
AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning
Jiwon Kim, Kwangrok Ryoo, Gyuseong Lee +5
Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. C…