Jaehoon Oh
9 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (6) π Cross-Pollinator (12) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (22)
π£
Hot Topic Early Bird
Conferences
EMNLP (3)
ICLR (2)
CVPR (1)
ICML (1)
IJCAI (1)
NIPS (1)
Top co-authors
Keywords
continual learning
(2)
model compression
(2)
catastrophic forgetting
(1)
transfer learning
(1)
text classification
(1)
knowledge distillation
(1)
machine translation
(1)
data augmentation
(1)
kl divergence
(1)
cross-lingual transfer
(1)
preference optimization
(1)
supervised contrastive learning
(1)
model alignment
(1)
gradient descent
(1)
kullback-leibler divergence
(1)
mean squared error
(1)
proximal optimization
(1)
data heterogeneity
(1)
client heterogeneity
(1)
mixup augmentation
(1)
Papers
Beyond Fixed-Length Calibration for Post-Training Compression of LLMs
EMNLP 2025
OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference
ICML 2025
FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning
CVPR 2024
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
EMNLP 2024
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
NIPS 2022
Synergy with Translation Artifacts for Training and Inference in Multilingual Tasks
EMNLP 2022
FedBABU: Toward Enhanced Representation for Federated Image Classification
ICLR 2022
BOIL: Towards Representation Change for Few-shot Learning
ICLR 2021
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation
IJCAI 2021