Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing

Nov-14-2025, 02:54:35 GMT–Neural Information Processing Systems

Recent advancements in vision-language-to-image (VL2I) diffusion generation have made significant progress.

large language model, machine learning, unsafe concept, (17 more...)

Neural Information Processing Systems

Nov-14-2025, 02:54:35 GMT

Conferences PDF

Country:
- Asia > China
  - Guangdong Province > Guangzhou (0.04)
  - Hong Kong (0.04)

Genre:
- Research Report > Experimental Study (0.93)

Industry:
- Law (1.00)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.46)
    - Natural Language > Large Language Model (0.94)
    - Representation & Reasoning (1.00)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (0.95)