7 papers
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
Di Wu, Yixin Wan, Kai-Wei Chang
Text-to-image retrieval (T2I retrieval) remains challenging because cross-modal embeddings often behave as bags of concepts, underrepresenting structured visual relationships such…
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
Yixin Wan, Lei Ke, Wenhao Yu +2
We introduce MotionEdit, a novel dataset for motion-centric image editing-the task of modifying subject actions and interactions while preserving identity, structure, and physical…
Where Fact Ends and Fairness Begins: Redefining AI Bias Evaluation through Cognitive Biases
Jen-tse Huang, Yuhang Yan, Linqi Liu +4
Recent failures such as Google Gemini generating people of color in Nazi-era uniforms illustrate how AI outputs can be factually plausible yet socially harmful. AI models are incre…
The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects
Yixin Wan, Kai-Wei Chang
Recent large-scale T2I models like DALLE-3 have made progress in reducing gender stereotypes when generating single-person images. However, significant biases remain when generatin…
Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
Yixin Wan, Anil Ramakrishna, Kai-Wei Chang +2
Large Language Model (LLM) unlearning has recently gained significant attention, driven by the need to remove unwanted information, such as private, sensitive, or copyrighted conte…
White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs
Yixin Wan, Kai-Wei Chang
Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous wo…