3 papers
cs.CV2025
FADE: Adversarial Concept Erasure in Flow Models
Zixuan Fu, Yan Ren, Finn Carter +5
Diffusion models have demonstrated remarkable image generation capabilities, but also pose risks in privacy and fairness by memorizing sensitive concepts or perpetuating biases. We…
cs.LG2025
Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
Yining Wang, Mi Zhang, Junjie Sun +6
Fusing visual understanding into language generation, Multi-modal Large Language Models (MLLMs) are revolutionizing visual-language applications. Yet, these models are often plague…
cs.CV2024
Navigate Beyond Shortcuts: Debiased Learning through the Lens of Neural Collapse
Yining Wang, Junjie Sun, Chenyue Wang +2
Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training…