mlsanityData to 7 Oct 2026

MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models

arXiv 2512.12268 ↗First posted 13 Dec 2025cs.CVcited by 1

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Vision-language models (VLMs) such as CLIP exhibit strong zero-shot generalization but remain sensitive to domain shifts at test time. Test-time prompt tuning (TPT) mitigates this issue by adapting prompts with fixed augmentations, which may falter in more challenging settings. In this work, we propose Meta Test-Time Prompt Tuning (MetaTPT), a meta-learning framework that learns a self-supervised auxiliary task to guide test-time prompt tuning. The auxiliary task dynamically learns parameterized augmentations for each sample, enabling more expressive transformations that capture essential features in target domains. MetaTPT adopts a dual-loop optimization paradigm: an inner loop learns a self-supervised task that generates informative views, while the outer loop performs prompt tuning by enforcing consistency across these views. By coupling augmentation learning with prompt tuning, MetaTPT improves test-time adaptation under domain shifts. Extensive experiments demonstrate that MetaTPT achieves state-of-the-art performance on domain generalization and cross-dataset benchmarks.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 47 of its 68 references that are in the map. First posted on arXiv 13 Dec 2025.

Builds on

47 of 68 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping20 Oct
  2. 2024Prompt Learning via Meta-Regularization1 Apr
  3. 2024Efficient Test-Time Adaptation of Vision-Language Models27 Mar
  4. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization2 Nov
  5. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning11 Aug
  6. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models15 Sep
  7. 2022Conditional Prompt Learning for Vision-Language Models10 Mar
  8. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling6 Nov
  9. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapters9 Oct
  10. 2021Learning to Prompt for Vision-Language Models2 Sep

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2013Describing Textures in the Wildcited by 2,110
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  10. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  11. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  12. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
25 more
  1. 2019Natural Adversarial Examplescited by 1,401
  2. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  4. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  5. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  8. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  9. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  10. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  11. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  12. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
  13. 2018How to train your MAMLcited by 306
  14. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272
  15. 2017Meta Networkscited by 268
  16. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  17. 2020Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfercited by 173
  18. 2019Meta-Learning via Learned Losscited by 60
  19. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  20. 2020Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphscited by 38
  21. 2025MMRL: Multi-Modal Representation Learning for Vision-Language Modelscited by 38
  22. 2024Historical Test-time Prompt Tuning for Vision Foundation Modelscited by 21
  23. 2023MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Modelscited by 15
  24. 2021Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learningcited by 6
  25. 2023EMO: Episodic Memory Optimization for Few-Shot Meta-Learningcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive sciencecited by 8

Similar, not cited

Close in wording, no citation either way

  1. 2023Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models
  2. 2024On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?
  3. 2025MINT: Memory-Infused Prompt Tuning at Test-time for CLIP
  4. 2022Learning Domain Invariant Prompt for Vision-Language Models
  5. 2022Multitask Vision-Language Prompt Tuning
  6. 2025Doubly Debiased Test-Time Prompt Tuning for Vision-Language Models
  7. 2026Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
  8. 2024In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model