BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation

Documenti analoghi

• Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models
  di: Peng, Wei, et al.
  Pubblicazione: (2025)
• BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
  di: Xiang, Sike, et al.
  Pubblicazione: (2025)
• Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models
  di: Mishra, Shambhavi, et al.
  Pubblicazione: (2024)
• Anchor-based Robust Finetuning of Vision-Language Models
  di: Han, Jinwei, et al.
  Pubblicazione: (2024)
• MultiMedVision: Multi-Modal Medical Vision Framework
  di: Li, Frank, et al.
  Pubblicazione: (2026)