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

Source: [BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation](<https://www.sota2.com/research/paper/6a0a9ce3dbc836b87d82b26c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-19T05:00:05.916Z

Authors: Huanyang Tong, Kai Liu, Fangjun Kuang, Huiling Chen

Published: 2026-05-15T08:45:57.000Z

## Abstract

Biomedical Vision--Language Models (VLMs) have shown remarkable promise in few-shot medical diagnosis but face a critical bottleneck: \\textit{fragility to prompt variations}.Existing adaptation frameworks typically optimize visual and textual prompts as independent streams, relying on ideal \`\`Golden Prompts''. In clinical reality, where descriptions are often noisy and heterogeneous, this modality isolation leads to unstable cross-modal alignment.   To address this, we propose BiomedAP, a vision-informed dual-anchor framework with gated cross-modal fusion.BiomedAP enforces synergistic alignment through two mechanisms: (1) Gated Cross-Modal Fusion, which enables layer-wise interaction between modalities, acting as a dynamic noise regulator to suppress irrelevant textual cues; and (2) a Dual-Anchor Constraint that regularizes learnable prompts toward stable semantic centroids derived from both expert templates (High Anchors) and few-shot visual prototypes (Low Anchors).   Extensive experiments across 11 benchmarks demonstrate that BiomedAP consistently surpasses baselines, achieving competitive few-shot accuracy and markedly enhanced robustness under prompt perturbations.   Our code is available at: https://github.com/tongdiedie/BiomedAP.   Keywords: Vision-Language Models; Prompt Learning; Parameter-Efficient Fine-Tuning; Few-shot Learning

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Biomedical Classification on 11 Biomedical Datasets Average (K-shot/Zero-shot)](<https://www.sota2.com/research/sota/biomedical-classification-on-11-biomedical-datasets-average-k-shot-zero-shot.md>): Biomedical Classification; 11 biomedical datasets Average; Accuracy (K=1): 63.57.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.15736>)

[PDF](<https://arxiv.org/pdf/2605.15736.pdf>)
