Dongbin Na
5 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (21) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (2)
ACL (1)
EACL (1)
NIPS (1)
Top co-authors
Research topics
Keywords
confidence calibration
(3)
text classification
(2)
out-of-distribution detection
(2)
uncertainty quantification
(1)
data augmentation
(1)
privacy preservation
(1)
semantic representation
(1)
machine unlearning
(1)
label complexity
(1)
uncertainty sampling
(1)
image inpainting
(1)
semantic similarity
(1)
deep neural network
(1)
ensemble method
(1)
model utility
(1)
pretrained transformer
(1)
background feature
(1)
pretrained language model
(1)
pool-based learning
(1)
outlier exposure
(1)
Papers
Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
AAAI 2025
Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detection
AAAI 2023
Pseudo Outlier Exposure for Out-of-Distribution Detection using Pretrained Transformers
ACL 2023
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers
EACL 2023
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
NIPS 2022