# Bayesian Principles Improve Prompt Learning In Vision-Language Models

arXiv: https://arxiv.org/abs/2504.14123 · HTML: https://mlsanity.com/paper/2504.14123/

## Key facts

- Cited by 4 papers in the map (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 24 of its 34 references that are in the map.
- First posted on arXiv 19 Apr 2025.

## 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, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (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)
- [Bayesian Prompt Learning for Image-Language Model Generalization](https://mlsanity.com/paper/2210.02390/) (2022)
- [Softmax is not Enough (for Sharp Size Generalisation)](https://mlsanity.com/paper/2410.01104/) (2024)
- [Towards Calibrated Robust Fine-Tuning of Vision-Language Models](https://mlsanity.com/paper/2311.01723/) (2023)
- [Bayesian Few-Shot Classification with One-vs-Each P'olya-Gamma Augmented Gaussian Processes](https://mlsanity.com/paper/2007.10417/) (2020)
- [Dependent Multinomial Models Made Easy: Stick Breaking with the P'olya-Gamma Augmentation](https://mlsanity.com/paper/1506.05843/) (2015)
- [Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?](https://mlsanity.com/paper/2307.11978/) (2023)
- [One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities](https://mlsanity.com/paper/1609.07410/) (2016)
- [Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior](https://mlsanity.com/paper/2401.06799/) (2024)

## Built on by (most cited first, 4 of 4)

- [ReBaPL: Repulsive Bayesian Prompt Learning](https://mlsanity.com/paper/2511.17339/) (2025)
- [FEAT: Fashion Editing and Try-On from Any Design](https://mlsanity.com/paper/2605.02393/) (2026)
- [BiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language Adaptation](https://mlsanity.com/paper/2605.15736/) (2026)
- [BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models](https://mlsanity.com/paper/2610.12907/) (2026)

## Abstract (arXiv)

Prompt learning is a popular fine-tuning method for vision-language models due to its efficiency. It requires a small number of additional learnable parameters while significantly enhancing performance on target tasks. However, most existing methods suffer from overfitting to fine-tuning data, yielding poor generalizability. To address this, we propose a new training objective function based on a Bayesian learning principle to balance adaptability and generalizability. We derive a prior over the logits, where the mean function is parameterized by the pre-trained model, while the posterior corresponds to the fine-tuned model. This objective establishes a balance by allowing the fine-tuned model to adapt to downstream tasks while remaining close to the pre-trained model.