Taeuk Jang
Social Sciences · Purdue University West Lafayette
Publications
11
Citations
84
Est. group size
—
Recurring co-author estimate
Active years
20
Publishing since 2006
Taeuk Jang works on making machine learning systems fairer and less biased, particularly in vision-language models (systems that connect images and text) and other AI applications. Their research develops methods to detect and reduce unwanted bias related to sensitive attributes, while also touching on data privacy and robustness against adversarial attacks. This work is relevant to students interested in the ethical and technical challenges of building trustworthy AI systems.
Publication output has grown since 2021, with activity increasing notably in 2024 after a slower period in earlier years of the decade.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Target Bias Is All You Need: Zero-Shot Debiasing of Vision-Language Models With Bias Corpus
2025
- Adversarial Fairness Network
Proceedings of the AAAI Conference on Artificial Intelligence · 2024
- FADES: Fair Disentanglement with Sensitive Relevance
2024
- A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
2024
- A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
arXiv (Cornell University) · 2024
- Difficulty-Based Sampling for Debiased Contrastive Representation Learning
2023
- Constructing a Fair Classifier with Generated Fair Data
Proceedings of the AAAI Conference on Artificial Intelligence · 2021
- Proceedings of the AAAI Conference on Artificial Intelligence×3
- arXiv (Cornell University)×2
- Xueru Zhang
Social Sciences · The Ohio State University
- João Marinotti
Social Sciences · Indiana University
- Eamon Duede
Social Sciences · Purdue University West Lafayette
- Daniel Schiff
Social Sciences · Purdue University West Lafayette
- Dennis D. Hirsch
Social Sciences · The Ohio State University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile