Kaixin Shen — accepted AI-conference papers

2026

TarPro: Targeted Protection Against Malicious Image Editing

Kaixin Shen, Ruijie Quan, Jiaxu Miao, Jun Xiao

AAAI 2026technical

The rapid advancement of diffusion-based image editing has enabled highly controllable visual content generation but has also raised serious concerns about the misuse of generative models for producing Not-Safe-for-Work (NSFW) content. Existing protection strategies inject adversarial perturbations

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection

Yucheng Suo, Fan Ma, Kaixin Shen, Linchao Zhu, Yi Yang

ICLR 2025poster

Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of images using text-to-image models without considering the context of previous steps results in inconsistent images, increa…

Cited by 0 Source ↗PDF ↗Scholar ↗