Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach
Researchers introduce MergeMedBench, the first comprehensive benchmark for merging medical vision-language models (LVLMs), covering eight imaging modalities and diverse clinical tasks. They propose a winner-take-all merging method that retains only the most dominant parameters from expert models, avoiding the information dilution seen in averaging or alignment-based strategies. This hyperparameter-free approach consistently outperforms existing merging methods in their evaluations.
Why it matters: This work offers a practical and effective solution for consolidating multiple specialized medical LVLMs, potentially reducing deployment costs and complexity while maintaining strong performance.
Full story at: arXiv Computer Vision ↗