mlsanityData to 7 Oct 2026

DynaPrompt: Dynamic Test-Time Prompt Tuning

arXiv 2501.16404 ↗First posted 27 Jan 2025cs.LG cs.AI cs.CLcited by 31

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

Abstract (arXiv)

Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the relevant prompts for each test sample during tuning. Specifically, we introduce a dynamic prompt selection strategy based on two metrics: prediction entropy and probability difference. For unseen test data information, we develop dynamic prompt appending, which allows the buffer to append new prompts and delete the inactive ones. By doing so, the prompts are optimized to exploit beneficial information on specific test data, while alleviating error accumulation. Experiments on fourteen datasets demonstrate the effectiveness of dynamic test-time prompt tuning.

Key facts. Cited by 31 papers 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. First posted on arXiv 27 Jan 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 12; 2026: 19.

31 papers.

Sort:

By area:

  1. 2025UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokenscited by 55
  2. 2025FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Expertscited by 34
  3. 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Maskingcited by 21
  4. 2025Prompt-based Adaptation in Large-scale Vision Models: A Surveycited by 21
  5. 2026On-the-Fly VLA Adaptation via Test-Time Reinforcement Learningcited by 14
  6. 2026EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answeringcited by 13
  7. 2025CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanismscited by 11
  8. 2025Fly-CL: A Fly-Inspired Framework for Enhancing Efficient Decorrelation and Reduced Training Time in Pre-trained Model-based Continual Representation Learningcited by 10
  9. 2025Generalizing vision-language models to novel domains: A comprehensive surveycited by 6
  10. 2025Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignmentcited by 5
  11. 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learningcited by 5
  12. 2026Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learningcited by 4
19 more
  1. 2026Limited Reasoning Space: The cage of long-horizon reasoning in LLMscited by 3
  2. 2025D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Modelscited by 2
  3. 2026Adaptive Debiasing Tsallis Entropy for Test-Time Adaptationcited by 2
  4. 2026Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuningcited by 2
  5. 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Modelscited by 2
  6. 2026Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretrainingcited by 2
  7. 2025Progressive Scaling Visual Object Trackingcited by 1
  8. 2026ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Modelscited by 1
  9. 2025Doubly Debiased Test-Time Prompt Tuning for Vision-Language Modelscited by 0
  10. 2025Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Modelscited by 0
  11. 2026LiteEmbed: Adapting CLIP to Rare Classescited by 0
  12. 2026SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Modelscited by 0
  13. 2026Concept Alignment Contrast and Long-Short Prompt Memory for Test-Time Adaptation of SAM3 in Medical Image Segmentationcited by 0
  14. 2026Cross-device Collaborative Test-time Adaptation with Zeroth-order Optimization and Model Mergingcited by 0
  15. 2026From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Modelcited by 0
  16. 2026Fine-Tuning of Transformer models with Framescited by 0
  17. 2026Rethinking the Test-Time Prompt Tuning Objective from the Perspective of Calibrationcited by 0
  18. 2026Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuningcited by 0
  19. 2026You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
  2. 2025MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Models
  3. 2025MINT: Memory-Infused Prompt Tuning at Test-time for CLIP
  4. 2025Prompting without Panic: Attribute-aware, Zero-shot, Test-Time Calibration
  5. 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
  6. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
  7. 2024On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?
  8. 2026USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning