# BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs

arXiv: https://arxiv.org/abs/2604.17629 · HTML: https://mlsanity.com/paper/2604.17629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 19 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [Quilt-1M: One Million Image-Text Pairs for Histopathology](https://mlsanity.com/paper/2306.11207/) (2023)
- [Lung and Colon Cancer Histopathological Image Dataset (LC25000)](https://mlsanity.com/paper/1912.12142/) (2019)
- [Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?](https://mlsanity.com/paper/2112.13906/) (2021)
- [Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports](https://mlsanity.com/paper/2111.03452/) (2021)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP](https://mlsanity.com/paper/2404.02285/) (2024)
- [COVID-19 Infection Localization and Severity Grading from Chest X-ray Images](https://mlsanity.com/paper/2103.07985/) (2021)
- [StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization](https://mlsanity.com/paper/2302.09251/) (2023)
- [BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning](https://mlsanity.com/paper/2408.07440/) (2024)
- [COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptation](https://mlsanity.com/paper/2409.00397/) (2024)
- [FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2504.20860/) (2025)
- [CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation](https://mlsanity.com/paper/2602.20409/) (2026)

## Abstract (arXiv)

Pretrained biomedical vision-language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and acquisition-specific variations are pronounced, especially under few-shot supervision and when modality priors differ from pretraining corpora substantially. We propose BioVLM, a prompt-learning framework that improves cross-domain generalization without extensive backbone fine-tuning. BioVLM learns a diverse prompt bank and introduces dynamic prompt selection: for each input, it selects the most discriminative prompts via a low-entropy criterion on the predictive distribution, effectively coupling sparse few-shot evidence with rich LLM semantic priors. To strengthen this coupling, we distill high-confidence LLM-derived attributes and enforce robust knowledge transfer through strong/weak augmentation consistency. At test time, BioVLM adapts by choosing modality-appropriate prompts, enabling transfer to unseen categories and domains, while keeping training lightweight and inference efficient. On 11 MedMNIST+ 2D datasets, BioVLM achieves new state of the art across three distinct generalization settings. Codes are available at https://github.com/mainaksingha01/BioVLM.