# Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining

arXiv: https://arxiv.org/abs/2604.27715 · HTML: https://mlsanity.com/paper/2604.27715/

## Key facts

- Cited by 2 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 40 of its 50 references that are in the map.
- First posted on arXiv 30 Apr 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, 30 of 40)

- [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)
- [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)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [MaPLe: Multi-modal Prompt Learning](https://mlsanity.com/paper/2210.03117/) (2022)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [Sharp Minima Can Generalize For Deep Nets](https://mlsanity.com/paper/1703.04933/) (2017)
- [Measuring Calibration in Deep Learning](https://mlsanity.com/paper/1904.01685/) (2019)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Surrogate Gap Minimization Improves Sharpness-Aware Training](https://mlsanity.com/paper/2203.08065/) (2022)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Efficient Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2403.18293/) (2024)
- [Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning](https://mlsanity.com/paper/2010.05627/) (2020)
- [Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers](https://mlsanity.com/paper/1805.08206/) (2018)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [Fisher-Rao Metric, Geometry, and Complexity of Neural Networks](https://mlsanity.com/paper/1711.01530/) (2017)
- [Soft Calibration Objectives for Neural Networks](https://mlsanity.com/paper/2108.00106/) (2021)
- [The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration](https://mlsanity.com/paper/2111.15430/) (2021)
- [C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion](https://mlsanity.com/paper/2403.14119/) (2024)
- [SoTTA: Robust Test-Time Adaptation on Noisy Data Streams](https://mlsanity.com/paper/2310.10074/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Test-time Actor-Critic Approach to News Images Generation](https://mlsanity.com/paper/2606.21304/) (2026)
- [Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibration](https://mlsanity.com/paper/2608.30230/) (2026)

## Abstract (arXiv)

Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data. However, prior studies have observed that TPT often produces poorly calibrated models, raising concerns about the reliability of their predictions. Recent works address this issue by incorporating additional regularization terms that constrain model outputs, which improve calibration but often degrade performance. In this work, we reveal that these regularization strategies implicitly encourage optimization toward flatter minima, and that the sharpness of the loss landscape around adapted prompts is a key factor governing calibration quality. Motivated by this observation, we introduce Flatness-aware Prompt Pretraining (FPP), a simple yet effective pretraining framework for TPT that initializes prompts within flatter regions of the loss landscape prior to adaptation. We show that simply replacing the initialization in existing TPT pipelines--without modifying any other components--is sufficient to improve both calibration and performance. Notably, FPP requires no labeled data and incurs no additional computational costs during test-time tuning, making it highly practical for real-world deployment. The code is available at: https://github.com/YonseiML/fpp.