cs.AI, cs.CR, cs.CV

When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm

arXiv:2603.24079v1 Announce Type: cross
Abstract: Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for sem…