Jongwoo Ko
Graduate student @ KAIST
ml: representation learning
reasoning
cross-lingual
large language models
logical reasoning
contrastive learning
overfitting
mixup
inference acceleration
machine learning (ml)
ml: classification and regression
ml: deep neural network algorithms
cv: representation learning for vision
ml: unsupervised & self-supervised learning
math qa
6
presentations
SHORT BIO
I am a Ph.D. student of the KAIST AI and a member of OSI Lab (Advisor: Se-young Yun, KAIST). My current research focuses on efficient Transformer models, particularly generative language models like T5 or LLaMA. Additionally, I am also interested in efficient Vision Transformer models or multi-modal models. I aim to enhance the efficiency of large Transformer models.
Until last year, my research interests revolved around developing new algorithms to address real-world challenges in the machine learning pipeline, such as noise label and class imbalance settings, while providing statistical or mathematical guarantees. I received a master's degree in the Department of Industrial and Systems Engineering from KAIST under the supervision of Prof. Heeyoung Kim.
Presentations
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
Yongjin Yang and 2 other authors
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
Sangmin Bae and 3 other authors
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective
Jongwoo Ko
A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
Jongwoo Ko and 2 other authors
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
Sangmin Bae and 5 other authors
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
Jaehoon Oh and 1 other author