Lune

Profiles2020-2026

Steven Euijong Whang

Korea Advanced Institute of Science

16Papers
11Last author
13Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers16

  1. GradMix: Gradient-based Selective Mixup for Robust Data Augmentation in Class-Incremental LearningAuthor 3 of 3KDD 2026 · 1 citation
  2. DeFrame: Debiasing Large Language Models Against Framing EffectsAuthor 3 of 3ACL Findings 2026
  3. Fair Class-Incremental Learning using Sample WeightingAuthor 3 of 3KDD 2026
  4. Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMsAuthor 4 of 4ICLR 2026
  5. PFGuard: A Generative Framework with Privacy and Fairness SafeguardsAuthor 4 of 4ICLR 2025
  6. T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental LearningAuthor 3 of 3CVPR 2025
  7. Falcon: Fair Active Learning using Multi-armed BanditsAuthor 3 of 7VLDB 2024 · 7 citations
  8. RC-Mixup: A Data Augmentation Strategy against Noisy Data for Regression TasksAuthor 3 of 3KDD 2024 · 4 citations
  9. Improving Fair Training under Correlation ShiftsAuthor 3 of 4ICML 2023 · 22 citations
  10. iFlipper: Label Flipping for Individual FairnessAuthor 5 of 5SIGMOD 2023 · 12 citations
  11. XClusters: Explainability-First ClusteringAuthor 2 of 2AAAI 2023 · 8 citations
  12. FairBatch: Batch Selection for Model FairnessAuthor 3 of 4ICLR 2021 · 156 citations
  13. Sample Selection for Fair and Robust TrainingAuthor 3 of 4NeurIPS 2021 · 76 citations
  14. Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning ModelsAuthor 2 of 2SIGMOD 2021 · 31 citations
  15. Inspector Gadget: A Data Programming-based Labeling System for Industrial ImagesAuthor 5 of 5VLDB 2021 · 9 citations
  16. FR-Train: A Mutual Information-Based Approach to Fair and Robust TrainingAuthor 3 of 4ICML 2020 · 90 citations
Dusk over the sea between two cliffs drawn in fine vertical lines