2 citations · 6 across the 13 of their papers we have counts for
15 papers
KOMBO: Korean Character Representations Based on the Combination Rules of Subcharacters
SungHo Kim, Juhyeong Park, Yeachan Kim +1
The Korean writing system, \textit{Hangeul}, has a unique character representation rigidly following the invention principles recorded in \textit{Hunminjeongeum}.\footnote{\textit{…
Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
Hyuntae Park, Yeachan Kim, SangKeun Lee
Recent advancements in zero-shot commonsense reasoning have empowered Pre-trained Language Models (PLMs) to acquire extensive commonsense knowledge without requiring task-specific…
Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment
Hyuntae Park, Yeachan Kim, SangKeun Lee
Molecule and text representation learning has gained increasing interest due to its potential for enhancing the understanding of chemical information. However, existing models ofte…
C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning
Yeachan Kim, Junho Kim, Wing-Lam Mok +2
Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the traini…
CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning
Yeachan Kim, Junho Kim, SangKeun Lee
Parameter-efficient fine-tuning (PEFT) has enabled the efficient optimization of cumbersome language models in real-world settings. However, as datasets in such environments often…
MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science
Junho Kim, Yeachan Kim, Jun-Hyung Park +3
We introduce a novel continued pre-training method, MELT (MatEriaLs-aware continued pre-Training), specifically designed to efficiently adapt the pre-trained language models (PLMs)…
Zero-shot Commonsense Reasoning over Machine Imagination
Hyuntae Park, Yeachan Kim, Jun-Hyung Park +1
Recent approaches to zero-shot commonsense reasoning have enabled Pre-trained Language Models (PLMs) to learn a broad range of commonsense knowledge without being tailored to speci…
MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction
Jun-Hyung Park, Yeachan Kim, Mingyu Lee +2
Chemical representation learning has gained increasing interest due to the limited availability of supervised data in fields such as drug and materials design. This interest partic…
Improving Bias Mitigation through Bias Experts in Natural Language Understanding
Eojin Jeon, Mingyu Lee, Juhyeong Park +3
Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental e…
Learning From Drift: Federated Learning on Non-IID Data via Drift Regularization
Yeachan Kim, Bonggun Shin
Federated learning algorithms perform reasonably well on independent and identically distributed (IID) data. They, on the other hand, suffer greatly from heterogeneous environments…
Dynamic Structure Pruning for Compressing CNNs
Jun-Hyung Park, Yeachan Kim, Junho Kim +2
Structure pruning is an effective method to compress and accelerate neural networks. While filter and channel pruning are preferable to other structure pruning methods in terms of…
Phase-shifted Adversarial Training
Yeachan Kim, Seongyeon Kim, Ihyeok Seo +1
Adversarial training has been considered an imperative component for safely deploying neural network-based applications to the real world. To achieve stronger robustness, existing…
In Defense of Core-set: A Density-aware Core-set Selection for Active Learning
Yeachan Kim, Bonggun Shin
Active learning enables the efficient construction of a labeled dataset by labeling informative samples from an unlabeled dataset. In a real-world active learning scenario, conside…
Context-based Virtual Adversarial Training for Text Classification with Noisy Labels
Do-Myoung Lee, Yeachan Kim, Chang-gyun Seo
Deep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization, unfortunately, leads to performance degra…
An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention
Yeachan Kim, Bonggun Shin
In silico prediction of drug-target interactions (DTI) is significant for drug discovery because it can largely reduce timelines and costs in the drug development process. Specific…