The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models

Documenti analoghi

• Quantified Task Misalignment to Inform PEFT: An Exploration of Domain Generalization and Catastrophic Forgetting in CLIP
  di: Niss, Laura, et al.
  Pubblicazione: (2024)
• MoIIE: Mixture of Intra- and Inter-Modality Experts for Large Vision Language Models
  di: Wang, Dianyi, et al.
  Pubblicazione: (2025)
• Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap
  di: Liao, Christopher, et al.
  Pubblicazione: (2024)
• Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning
  di: Liao, Christopher, et al.
  Pubblicazione: (2023)
• MERGETUNE: Continued Fine-Tuning of Vision-Language Models
  di: Wang, Wenqing, et al.
  Pubblicazione: (2026)