Eunju Lee
6 papers · 2024–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
vision-language model
(2)
shortcut learning
(1)
continual learning
(1)
semantic segmentation
(1)
weakly supervised learning
(1)
data augmentation
(1)
data annotation
(1)
multimodal learning
(1)
machine unlearning
(1)
model forgetting
(1)
feature disentanglement
(1)
loss landscape
(1)
gradient descent
(1)
mahalanobis distance
(1)
low-resource language
(1)
bias mitigation
(1)
spurious correlation
(1)
few-shot class-incremental learning
(1)
prototype calibration
(1)
gradient reweighting
(1)
Papers
Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under Bias
AAAI 2026
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
CVPR 2026
See-Saw Modality Balance: See Gradient, and Sew Impaired Vision-Language Balance to Mitigate Dominant Modality Bias
NAACL 2025
DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
ECCV 2024
GPTs Are Multilingual Annotators for Sequence Generation Tasks
EACL 2024
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
WACV 2024