6 papers
PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders
Man Jiang, Ouxiang Li, Weibao Xue +4
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations,…
SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding
Yuan Sheng, Yanbin Hao, Chenxu Li +2
Long video understanding remains challenging due to its complex, diverse, and temporally scattered content. Although video large language models (Video-LLMs) can process videos las…
Accelerating Diffusion Transformer via Gradient-Optimized Cache
Junxiang Qiu, Lin Liu, Shuo Wang +3
Feature caching has emerged as an effective strategy to accelerate diffusion transformer (DiT) sampling through temporal feature reuse. It is a challenging problem since (1) Progre…
Accelerating Diffusion Transformer via Error-Optimized Cache
Junxiang Qiu, Shuo Wang, Jinda Lu +4
Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time con…
Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
Ouxiang Li, Yanbin Hao, Zhicai Wang +4
Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MI…
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Xingyu Zhu, Beier Zhu, Yi Tan +3
Vision-language models, such as CLIP, have shown impressive generalization capacities when using appropriate text descriptions. While optimizing prompts on downstream labeled data…