Universal Adversarial Perturbations for Vision-Language Pre-trained Models

Documenti analoghi

• Surrealistic-like Image Generation with Vision-Language Models
  di: Ayten, Elif, et al.
  Pubblicazione: (2024)
• VACoDe: Visual Augmented Contrastive Decoding
  di: Kim, Sihyeon, et al.
  Pubblicazione: (2024)
• Effective and Robust Adversarial Training against Data and Label Corruptions
  di: Zhang, Peng-Fei, et al.
  Pubblicazione: (2024)
• Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos
  di: Zhang, Junbin, et al.
  Pubblicazione: (2022)
• From Language Models to Practical Self-Improving Computer Agents
  di: Sheng, Alex
  Pubblicazione: (2024)