Publications

Random Is Hard to Beat: Active Selection in Online DPO with Modern LLMs

Giyeong Oh, Junghyun Lee, Jaehyun Park, Youngjae Yu, Wonho Bae*, Junhyug Noh*
PDF

Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

J. Wang, Wonho Bae, J. Chen, W. Wang, Junhyug Noh
PDF

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation

J. Kim, Wonho Bae, Y.L. Han, Giyeong Oh, Y. Yu, D.J. Sutherland, Junhyug Noh
PDF

SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation

PDF

Uncertainty Herding: One Active Learning Method for All Label Budgets

PDF

Generalized Coverage for More Robust Low-Budget Active Learning

PDF

Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling

PDF

What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Context

PDF

A fast, well-founded approximation to the empirical neural tangent kernel

PDF

Meta Temporal Point Processes

PDF

How to Prepare Your Task Head for Finetuning

PDF

Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels

PDF

Object Discovery via Contrastive Learning for Weakly Supervised Object Detection

PDF

One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model

PDF

Prediction of the mortality risk in peritoneal dialysis patients using machine learning models: a nation-wide prospective cohort in Korea

PDF

Rethinking class activation mapping for weakly supervised object localization

PDF

Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection

PDF