# Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models

arXiv: https://arxiv.org/abs/2609.33701 · HTML: https://mlsanity.com/paper/2609.33701/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 7 of its 29 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 7 of 7)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [Lung and Colon Cancer Histopathological Image Dataset (LC25000)](https://mlsanity.com/paper/1912.12142/) (2019)
- [CLIP in Medical Imaging: A Survey](https://mlsanity.com/paper/2312.07353/) (2023)
- [Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation](https://mlsanity.com/paper/2506.17500/) (2025)
- [vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs](https://mlsanity.com/paper/2511.09540/) (2025)

## Abstract (arXiv)

Pretrained biomedical vision-language models achieve strong zero-shot performance in biomedical image classification. However, downstream biomedical classification often depends on subtle visual differences between classes that may not be fully captured by pretrained representations. Few-shot adaptation addresses this mismatch by optimizing a task-specific predictor on a small labeled support set. Because the selected examples capture only part of the visual variation within the target classes, the adapted predictions can depend strongly on their composition. We propose Prompt-Anchored Residual Adaptation (PARA), which retains the frozen prompt prediction as a support-invariant semantic anchor and incorporates a visual prediction learned from the support set through an anchor-relative residual. The residual step is computed in a closed form from frozen support embeddings using anchor discrepancy and support agreement. Support-set dependence also limits evaluation: comparisons are fair within a shared draw but remain conditional on its composition. To obtain more reliable comparisons, we introduce a repeated-support protocol that separates support-selection variation from optimization randomness and reports both average and worst-20% performance. PARA achieves state-of-the-art performance in both few-shot classification and base-to-novel generalization.