Can routing signatures learned from few-shot prompts on NLVR2 and SNLI-VE generalize to out-of-distribution co

Abstract

Abstract: Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing medical foundation models and their zero-shot transfer to downstream tasks, the popular few-shot setting remains relatively unexplored. Following on from the currently strong emergence of this setting in computer vision, we introduce the first structured benchmark for adapting medical vision-language models (VLMs) in a strict few-shot regime and investigate v

Research Question

Can routing signatures learned from few-shot prompts on NLVR2 and SNLI-VE generalize to out-of-distribution compositional reasoning tasks (e.g., Winoground, VCR) without retraining, and does this transfer maintain higher accuracy than fixed-ratio MoE baselines?

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance