Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning

Documenti analoghi

• CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
  di: Zhang, Jihai, et al.
  Pubblicazione: (2024)
• Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning
  di: Yaras, Can, et al.
  Pubblicazione: (2024)
• ReLearn: Unlearning via Learning for Large Language Models
  di: Xu, Haoming, et al.
  Pubblicazione: (2025)
• LetheViT: Selective Machine Unlearning for Vision Transformers via Attention-Guided Contrastive Learning
  di: Tong, Yujia, et al.
  Pubblicazione: (2025)
• Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
  di: Deng, Ailin, et al.
  Pubblicazione: (2024)