# Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning

arXiv: https://arxiv.org/abs/2605.26292 · HTML: https://mlsanity.com/paper/2605.26292/

## 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 29 of its 48 references that are in the map.
- First posted on arXiv 25 May 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, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [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)
- [LoRA vs Full Fine-tuning: An Illusion of Equivalence](https://mlsanity.com/paper/2410.21228/) (2024)
- [Low-Rank Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18541/) (2024)
- [LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP](https://mlsanity.com/paper/2404.02285/) (2024)
- [A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation](https://mlsanity.com/paper/2402.04087/) (2024)
- [Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning](https://mlsanity.com/paper/2206.06122/) (2022)
- [COVID-19 Infection Localization and Severity Grading from Chest X-ray Images](https://mlsanity.com/paper/2103.07985/) (2021)
- [MedCLIP-SAMv2: Towards Universal Text-Driven Medical Image Segmentation](https://mlsanity.com/paper/2409.19483/) (2024)
- [MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.20253/) (2024)
- [BiomedCoOp: Learning to Prompt for Biomedical Vision-Language Models](https://mlsanity.com/paper/2411.15232/) (2024)
- [BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification](https://mlsanity.com/paper/2506.14318/) (2025)
- [TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Pancreatic Tumor in Endoscopic Ultrasound](https://mlsanity.com/paper/2507.18082/) (2025)
- [Medical Knowledge Intervention Prompt Tuning for Medical Image Classification](https://mlsanity.com/paper/2511.12639/) (2025)
- [MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2602.20423/) (2026)
- [Grounding DINO-US-SAM: Text-Prompted Multi-Organ Segmentation in Ultrasound with LoRA-Tuned Vision-Language Models](https://mlsanity.com/paper/2506.23903/) (2025)
- [CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values](https://mlsanity.com/paper/2509.03740/) (2025)
- [Sparse Spectral LoRA: Routed Experts for Medical VLMs](https://mlsanity.com/paper/2604.01310/) (2026)

## Abstract (arXiv)

Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing methods remain deterministic and often struggle under domain shift or ambiguous image-text alignment. This limitation is particularly critical in the clinic, where models should remain robust in low-data regimes and domain shifts. We present Evi-Steer, an evidential cross-modal low-dimensional steering framework for BiomedCLIP that enables uncertainty-aware parameter-efficient fine-tuning while updating only 0.11% of total model parameters. Our approach performs lightweight low-dimensional token updates in both vision and text encoders while simultaneously estimating epistemic uncertainty. These uncertainty estimates update gate residuals, allowing the model to adapt conservatively when evidence is weak. Furthermore, we introduce cross-modal confidence fusion based on Dempster-Shafer theory, enabling visual adaptation to be conditioned on textual confidence and suppressing conflicting or uncertain cross-modal updates. We conduct a comprehensive evaluation on 15 biomedical imaging datasets spanning 8 organs and 8 imaging modalities under few-shot learning and domain generalization settings. Evi-Steer consistently outperforms state-of-the-art methods under few-shot learning and domain shift settings, demonstrating a practical and robust pathway for deploying vision-language models in real-world clinical settings. Code is available at https://github.com/HealthX-Lab/Evi-Steer.