2 papers
cs.CY2026
Situating Vulnerability: An Ethical Governance Framework for Anthropomorphic AI Interaction
Hanhui Xu, Jiacheng Ji, Yuhan Wang +4
Large language models increasingly address users in the register of care: they remember personal details, adopt a first-person emotional voice, and sustain relationships across man…
cs.CV2026
Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Huilin Zhou, Ruoxi Cheng, Yuhang Wang +4
Diffusion models achieve strong performance in text-to-image generation, but they can still produce unsafe content. Training-free safety guidance offers a practical inference-time…