most citedMicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2025★ 1 cited

MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

Amaan Izhar, Nurul Japar, Norisma Idris +1

Medical image reporting (MIR) aims to generate structured clinical descriptions from radiological images. Existing methods struggle with fine-grained feature extraction, multimodal…