Qianqian Xu

LinAJD: Scalable Gradient-Free Jailbreak Defense via Linearly Separable Embeddings

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

OpenworldAUC: Towards Unified Evaluation and Optimization for Open-world Prompt Tuning

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders

Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain

Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification

Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework