6 papers
Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization
Qinghui He, Haifeng Zhang, Xiuli Bi +3
The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniq…
Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation
ZeBin Ji, Yang Hu, Xiuli Bi +2
It is essential for understanding neural network decisions to interpret the functionality (also known as concepts) of neurons. Existing approaches describe neuron concepts by gener…
TGDD: Trajectory Guided Dataset Distillation with Balanced Distribution
Fengli Ran, Xiao Pu, Bo Liu +2
Dataset distillation compresses large datasets into compact synthetic ones to reduce storage and computational costs. Among various approaches, distribution matching (DM)-based met…
ZeroPur: Succinct Training-Free Adversarial Purification
Erhu Liu, Zonglin Yang, Bo Liu +4
Adversarial purification is a kind of defense technique that can defend against various unseen adversarial attacks without modifying the victim classifier. Existing methods often d…
Mobius: Text to Seamless Looping Video Generation via Latent Shift
Xiuli Bi, Jianfei Yuan, Bo Liu +4
We present Mobius, a novel method to generate seamlessly looping videos from text descriptions directly without any user annotations, thereby creating new visual materials for the…
CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training
Xiuli Bi, Jian Lu, Bo Liu +4
Benefiting from large-scale pre-training of text-video pairs, current text-to-video (T2V) diffusion models can generate high-quality videos from the text description. Besides, give…