3 papers
cs.CV2026
Gaussian Core LoRA: Distribution-Aware Dynamic Adaptation for Broad Concept Erasure
Qinghui Gong, Xunlei Chen, Yu-Xuan Zhang +2
Concept erasure aims to suppress unsafe, privacy-sensitive, or undesirable generations in text-to-image diffusion models while preserving benign semantics, visual quality, and depl…
cs.AI2023
Data-driven Knowledge Fusion for Deep Multi-instance Learning
Yu-Xuan Zhang, Zhengchun Zhou, Xingxing He +2
Multi-instance learning (MIL) is a widely-applied technique in practical applications that involve complex data structures. MIL can be broadly categorized into two types: tradition…
cs.CV2022
Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations
Yu-Xuan Zhang, Hua Meng, Xue-Mei Cao +3
Multi-Instance Learning (MIL) is a recent machine learning paradigm which is immensely useful in various real-life applications, like image analysis, video anomaly detection, text…