mlsanityData to 14 Oct 2026

MINT: Memory-Infused Prompt Tuning at Test-time for CLIP

arXiv 2506.03190 ↗First posted 31 May 2025cs.CV cs.AIcited by 3

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

Abstract (arXiv)

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the model's internal knowledge, particularly in dynamically adapting to complex and hierarchical visual semantic information. In this paper, we propose Memory-Infused Prompt Tuning (MINT), a novel framework to address this issue. Inspired by human associative memory theory, MINT introduces a Memory Prompt Bank (MPB), which stores learnable key-value prompt pairs that work as a memory of previously seen samples. During the test time, relevant prompt pairs in the MPB are retrieved by the hierarchical visual features of test images to dynamically assemble Associative Prompts. The associative prompts are then injected into the image encoder for fine-grained, customized visual contextual guidance. MINT also utilizes learnable text prompts. MINT thus enables rapid, precise VLM adaptation at test time by leveraging this MPB-acquired memory, without source data or retraining. The code is available at https://github.com/Jamieyi2004/MINT.

Key facts. Cited by 3 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. First posted on arXiv 31 May 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Adapting Vision-Language Models Without Labels: A Comprehensive Surveycited by 7
  2. 2025PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attentioncited by 4
  3. 2026Towards In-Parameter Memory Augmentation for Large Language Modelscited 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. 2024In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model
  4. 2025A Closer Look at Conditional Prompt Tuning for Vision-Language Models
  5. 2026Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
  6. 2025Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
  7. 2024Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
  8. 2024Frustratingly Easy Test-Time Adaptation of Vision-Language Models