Saehyung Lee
13 papers · 2020–2025 · 8 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (25)
π€
Dynamic Duo
(12)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(65)
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(10)
Learning Types Β· Machine Learning
(10)
Application Areas
(9)
Artificial Intelligence
(7)
Core AI Β· Artificial Intelligence
(7)
Deep Learning
(3)
Natural Language Processing
(3)
Computer Vision
(2)
Applications
(2)
Learning Types Β· Deep Learning
(2)
Analysis
(1)
Core AI Β· Computer Vision
(1)
Generation
(1)
Techniques
(1)
Keywords
adversarial training
(4)
vision-language model
(2)
large language model
(2)
data augmentation
(2)
out-of-distribution detection
(2)
cross-modal transfer
(1)
factual accuracy
(1)
feature learning
(1)
confidence calibration
(1)
multimodal learning
(1)
test-time adaptation
(1)
domain generalization
(1)
chain-of-thought reasoning
(1)
question generation
(1)
class imbalance
(1)
label smoothing
(1)
evaluation framework
(1)
visual attention
(1)
distribution shift
(1)
question answering
(1)
Papers
Regularizing Hard Examples Improves Adversarial Robustness
JMLR 2025
Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage
ICML 2025
Unleashing Multi-Hop Reasoning Potential in Large Language Models through Repetition of Misordered Context
NAACL 2025
Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
ICML 2025
DAFA: Distance-Aware Fair Adversarial Training
ICLR 2024
Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors
ICLR 2024
Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach
ACL 2024
Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection
NeurIPS 2024
Inducing Data Amplification Using Auxiliary Datasets in Adversarial Training
WACV 2023
On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection
NeurIPS 2023
Dataset Condensation with Contrastive Signals
ICML 2022
Removing Undesirable Feature Contributions Using Out-of-Distribution Data
ICLR 2021
Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization
CVPR 2020