mlsanityData to 7 Oct 2026

Prompt learning and adaptation of CLIP

1,045 papers7 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: prompt, clip, vision-language, adaptation, methods

Key facts. Prompt learning and adaptation of CLIP: 1,045 papers on arXiv since 2021 (data through 7 Oct 2026). 308 of its 1,045 mapped papers (29%) cite “Learning to Prompt for Vision-Language Models” (2021, arXiv 2109.01134). 252 of its 1,045 mapped papers (24%) cite “Conditional Prompt Learning for Vision-Language Models” (2022, arXiv 2203.05557). 29 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

29 new papers, 17 Sep – 7 Oct; 7 this week.

  1. This week · 7
  2. Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models also fits: VLM benchmarks and visual reasoning
  3. FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification
  4. What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?
  5. Unsupervised Long-Tailed Adaptation of Vision-Language Models
  6. Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling also fits: Visual token pruning and efficiency
  7. Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning also fits: VLM benchmarks and visual reasoning
  8. Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts
  9. Earlier · 22
  10. RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation also fits: Visual token pruning and efficiency
  11. Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis also fits: Visual token pruning and efficiency
  12. SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning also fits: Visual token pruning and efficiency
All 29
  1. Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models
  2. Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model
  3. Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation also fits: MLLM jailbreaks and adversarial robustness
  4. Reprogramming Vision-Language Models via Structured Prompt Reparameterization
  5. VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-training also fits: Visual token pruning and efficiency
  6. One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models also fits: VLM benchmarks and visual reasoning
  7. ConvCue: Complementary Visual Inductive Biases for Vision-Language Models also fits: VLM benchmarks and visual reasoning
  8. Position Aware Layer Queries for Test Time Training in Vision Language Models also fits: Visual token pruning and efficiency
  9. Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models
  10. Kernel-Based Steering of CLIP with Vision-Language Model Preferences
  11. Open Vocabulary Domain Unlearning
  12. ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models
  13. Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models
  14. MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text Spotting also fits: Document understanding and multimodal RAG
  15. HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space
  16. Hierarchical Prompt Learning for Hyperbolic Vision-Language Models
  17. Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains also fits: VLM benchmarks and visual reasoning
  18. PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models
  19. Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction also fits: Visual token pruning and efficiency

Foundations

Most cited by papers here

  1. Learning to Prompt for Vision-Language Models2021cited by 308 here
  2. Conditional Prompt Learning for Vision-Language Models2022cited by 252 here
  3. CLIP-Adapter: Better Vision-Language Models with Feature Adapters2021cited by 175 here
  4. Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models2022cited by 117 here
  5. Prompt-aligned Gradient for Prompt Tuning2022cited by 102 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Learning to Prompt for Vision-Language Modelscited by 308 here
  2. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 175 here
  3. 2022Conditional Prompt Learning for Vision-Language Modelscited by 252 here
  4. 2022Unsupervised Prompt Learning for Vision-Language Modelscited by 42 here
  5. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 117 here
  6. 2024Efficient Test-Time Adaptation of Vision-Language Modelscited by 50 here
18 more it builds on, not in this chain
  1. 2021SimVLM: Simple Visual Language Model Pretraining with Weak Supervisioncited by 33 here
  2. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 72 here
  3. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 65 here
  4. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 121 here
  5. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 91 here
  6. 2022Prompt Distribution Learningcited by 87 here
  7. 2022Prompt-aligned Gradient for Prompt Tuningcited by 102 here
  8. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 86 here
  9. 2022When and why vision-language models behave like bags-of-words, and what to do about it?cited by 31 here
  10. 2022Visual Classification via Description from Large Language Modelscited by 49 here
  11. 2022Unified Vision and Language Prompt Learningcited by 37 here
  12. 2022Task Residual for Tuning Vision-Language Modelscited by 41 here
  13. 2023Visual-Language Prompt Tuning with Knowledge-guided Context Optimizationcited by 91 here
  14. 2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuningcited by 62 here
  15. 2023Improved Baselines with Visual Instruction Tuningcited by 32 here
  16. 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalizationcited by 39 here
  17. 2023TCP:Textual-based Class-aware Prompt tuning for Visual-Language Modelcited by 39 here
  18. 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersioncited by 38 here

The 24 most cited of 943.

Browse

30 of 1,045, ranked 6–35

  1. 6Visual-Language Prompt Tuning with Knowledge-guided Context Optimization202391
  2. 7Prompt Distribution Learning202287
  3. 8Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification202286
  4. 9Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling202172
  5. 10Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning202362
  6. 11Efficient Test-Time Adaptation of Vision-Language Models202450
  7. 12Visual Classification via Description from Large Language Models202249
  8. 13Unsupervised Prompt Learning for Vision-Language Models202242
  9. 14Task Residual for Tuning Vision-Language Models202241
  10. 15Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization202339
All 30
  1. 16TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model202339
  2. 17C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion202438
  3. 18Unified Vision and Language Prompt Learning202237
  4. 19Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models202331
  5. 20Consistency-guided Prompt Learning for Vision-Language Models202331
  6. 21When and why vision-language models behave like bags-of-words, and what to do about it?202231
  7. 22Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models202430
  8. 23PromptKD: Unsupervised Prompt Distillation for Vision-Language Models202429
  9. 24On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?202427
  10. 25Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters202424
  11. 26Waffling around for Performance: Visual Classification with Random Words and Broad Concepts202323
  12. 27Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models202421
  13. 28PLOT: Prompt Learning with Optimal Transport for Vision-Language Models202221
  14. 29SuS-X: Training-Free Name-Only Transfer of Vision-Language Models202221
  15. 30Negative Label Guided OOD Detection with Pretrained Vision-Language Models202420
  16. 31Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models202419
  17. 32Read-only Prompt Optimization for Vision-Language Few-shot Learning202319
  18. 33Frustratingly Easy Test-Time Adaptation of Vision-Language Models202418
  19. 34Low-Rank Few-Shot Adaptation of Vision-Language Models202418
  20. 35Black Box Few-Shot Adaptation for Vision-Language models202318