6 papers
GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions
Hongbo Wang, Zihan Lin, Wenkui Yang +5
Vision-language models (VLMs) can contradict themselves across views of the same spatial relation and fail to respond when that relation changes. Addressing these failures requires…
The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models
Dongsheng Liu, Chao Jin, Wenkui Yang +7
GUI World Models (GUI-WMs) are increasingly used to predict future states for agent planning and simulation, yet most existing formulations condition only on the current GUI observ…
Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
Wenkui Yang, Chao Jin, Haisu Zhu +7
Existing red-teaming studies on GUI agents face two fundamental limitations: adversarial perturbations require white-box access unavailable in commercial deployments, while prompt…
Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification
Wenkui Yang, Jie Cao, Junxian Duan +1
Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security r…
HAD: Hybrid Architecture Distillation Outperforms Teacher in Genomic Sequence Modeling
Hexiong Yang, Mingrui Chen, Huaibo Huang +4
Inspired by the great success of Masked Language Modeling (MLM) in the natural language domain, the paradigm of self-supervised pre-training and fine-tuning has also achieved remar…
Visual Watermarking in the Era of Diffusion Models: Advances and Challenges
Junxian Duan, Jiyang Guan, Wenkui Yang +1
As generative artificial intelligence technologies like Stable Diffusion advance, visual content becomes more vulnerable to misuse, raising concerns about copyright infringement. V…