Jae Oh Woo
5 papers · 2023–2026 · 5 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
active learning
(1)
policy optimization
(1)
uncertainty quantification
(1)
direct preference optimization
(1)
self-supervised learning
(1)
source-free domain adaptation
(1)
pseudo labeling
(1)
instruction following
(1)
mutual information
(1)
distribution shift
(1)
batch selection
(1)
convolutional neural network
(1)
adversarial perturbation
(1)
supervised fine-tuning
(1)
bayesian neural network
(1)
bayesian approximation
(1)
contrastive representation learning
(1)
iterative training
(1)
arithmetic reasoning
(1)
preference dataset
(1)
Papers
Reflect, Rewrite, Repeat: How Simple Arithmetic Enables Advanced Reasoning in Small Language Models
EACL 2026
Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
ICML 2024
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
ICLR 2023
Unsupervised Accuracy Estimation of Deep Visual Models using Domain-Adaptive Adversarial Perturbation without Source Samples
ICCV 2023
Unsupervised Contrastive Representation Learning for 3D Mesh Segmentation (Student Abstract)
AAAI 2023