SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models

Ähnliche Einträge

• Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
  von: Zheng, Weijie, et al.
  Veröffentlicht: (2024)
• Demographic User Modeling for Social Robotics with Multimodal Pre-trained Models
  von: Rahimi, Hamed, et al.
  Veröffentlicht: (2025)
• A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
  von: Zheng, Haonan, et al.
  Veröffentlicht: (2024)
• Do Pre-trained Vision-Language Models Encode Object States?
  von: Newman, Kaleb, et al.
  Veröffentlicht: (2024)
• Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
  von: Ye, Wei, et al.
  Veröffentlicht: (2024)