Xiaoqian Wang

Rethinking Pareto Frontier: On the Optimal Trade-offs in Fair Classification

Adaptive Logit Adjustment for Debiasing Multimodal Language Models

Understanding Subpopulation Shifts through a Unified Lens of Separability

Beyond Chunking: Efficient Global Pooling for Holistic Long-Document Representation

Fair Diffusion Sampling without Demographics

Agree to Disagree: Demystifying Homogeneous Deep Ensembles through Distributional Equivalence

Adversarial Latent Feature Augmentation for Fairness

Mitigating Spurious Correlations in Zero-Shot Multimodal Models

SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning

Reliable Image Quality Evaluation and Mitigating Quality Bias in Generative Models

Reliable Image Quality Evaluation and Mitigation of Quality Bias in Generative Models

Learning Disentangled Representations for Fairness with Limited Demographics

On the Alignment between Fairness and Accuracy: from the Perspective of Adversarial Robustness

Adaptive Logit Adjustment for Debiasing Multimodal Language Models