38 citations · 63 across the 14 of their papers we have counts for
15 papers
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Youngrok Park, Sangmin Bae, Hojung Jung +6
Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This is particularly important for successive model generations and m…
Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness
Yongjin Yang, Euiin Yi, Jongwoo Ko +3
The remarkable growth in large language model (LLM) capabilities has spurred exploration into multi-agent systems, with debate frameworks emerging as a promising avenue for enhance…
Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
Jongwoo Ko, Sungnyun Kim, Sungwoo Cho +1
Human-generated reward signals are critical for aligning generative models with human preferences, guiding both training and inference-time evaluations. While large language models…
From Belief Entrenchment to Robust Reasoning in LLM Agents
Jihwan Oh, Minchan Jeong, Jongwoo Ko +1
Multi-Agent Debate (MAD) has emerged as a promising inference scaling method for Large Language Model (LLM) reasoning. However, it frequently suffers from belief entrenchment, wher…
DistiLLM: Towards Streamlined Distillation for Large Language Models
Jongwoo Ko, Sungnyun Kim, Tianyi Chen +1
Knowledge distillation (KD) is widely used for compressing a teacher model to a smaller student model, reducing its inference cost and memory footprint while preserving model capab…
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
Yongjin Yang, Jongwoo Ko, Se-Young Yun
Vision-language models (VLMs) like CLIP have demonstrated remarkable applicability across a variety of downstream tasks, including zero-shot image classification. Recently, the use…
Fine tuning Pre trained Models for Robustness Under Noisy Labels
Sumyeong Ahn, Sihyeon Kim, Jongwoo Ko +1
The presence of noisy labels in a training dataset can significantly impact the performance of machine learning models. To tackle this issue, researchers have explored methods for…
NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models
Jongwoo Ko, Seungjoon Park, Yujin Kim +4
Structured pruning methods have proven effective in reducing the model size and accelerating inference speed in various network architectures such as Transformers. Despite the vers…
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
Sangmin Bae, Jongwoo Ko, Hwanjun Song +1
To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation path…
CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition
Sumyeong Ahn, Jongwoo Ko, Se-Young Yun
Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets.…
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective
Jongwoo Ko, Seungjoon Park, Minchan Jeong +4
Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate…
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
Jaehoon Oh, Jongwoo Ko, Se-Young Yun
Translation has played a crucial role in improving the performance on multilingual tasks: (1) to generate the target language data from the source language data for training and (2…
A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
Jongwoo Ko, Bongsoo Yi, Se-Young Yun
As deep neural networks can easily overfit noisy labels, robust training in the presence of noisy labels is becoming an important challenge in modern deep learning. While existing…
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
Sangmin Bae, Sungnyun Kim, Jongwoo Ko +3
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The…
FINE Samples for Learning with Noisy Labels
Taehyeon Kim, Jongwoo Ko, Sangwook Cho +2
Modern deep neural networks (DNNs) become frail when the datasets contain noisy (incorrect) class labels. Robust techniques in the presence of noisy labels can be categorized into…