MoVL:Exploring Fusion Strategies for the Domain-Adaptive Application of Pretrained Models in Medical Imaging Tasks

Documenti analoghi

• MedSG-Bench: A Benchmark for Medical Image Sequences Grounding
  di: Yue, Jingkun, et al.
  Pubblicazione: (2025)
• Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion
  di: Wang, Mengyu, et al.
  Pubblicazione: (2025)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning
  di: Hao, Zhiwei, et al.
  Pubblicazione: (2024)
• MedIQA: A Scalable Foundation Model for Prompt-Driven Medical Image Quality Assessment
  di: Xun, Siyi, et al.
  Pubblicazione: (2025)
• Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts
  di: Long, Jinqiang, et al.
  Pubblicazione: (2024)