Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

Documenti analoghi

• UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
  di: Zhou, Hantao, et al.
  Pubblicazione: (2024)
• Unified Language-driven Zero-shot Domain Adaptation
  di: Yang, Senqiao, et al.
  Pubblicazione: (2024)
• VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
  di: Yang, Senqiao, et al.
  Pubblicazione: (2025)
• Scalable Language Model with Generalized Continual Learning
  di: Peng, Bohao, et al.
  Pubblicazione: (2024)
• VisionZip: Longer is Better but Not Necessary in Vision Language Models
  di: Yang, Senqiao, et al.
  Pubblicazione: (2024)