# Prompt learning and adaptation of CLIP Area: [Multimodal LLMs / vision-language models](https://mlsanity.com/mllm/index.md). HTML: https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/ ## 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. ## Most cited here - [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021), cited by 308 papers here - [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022), cited by 252 papers here - [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021), cited by 175 papers here - [Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models](https://mlsanity.com/paper/2209.07511/) (2022), cited by 117 papers here - [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022), cited by 102 papers here - [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023), cited by 91 papers here - [Prompt Distribution Learning](https://mlsanity.com/paper/2205.03340/) (2022), cited by 87 papers here - [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022), cited by 86 papers here - [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021), cited by 72 papers here - [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023), cited by 62 papers here ## New (17 Sep–7 Oct) - [Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models](https://mlsanity.com/paper/2610.10526/) (2026-10-07) - [FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification](https://mlsanity.com/paper/2610.09907/) (2026-10-07) - [What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?](https://mlsanity.com/paper/2610.09700/) (2026-10-07) - [Unsupervised Long-Tailed Adaptation of Vision-Language Models](https://mlsanity.com/paper/2610.07903/) (2026-10-06) - [Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling](https://mlsanity.com/paper/2610.07689/) (2026-10-06) - [Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning](https://mlsanity.com/paper/2610.07385/) (2026-10-05) - [Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts](https://mlsanity.com/paper/2610.06147/) (2026-10-05) - [RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation](https://mlsanity.com/paper/2610.06932/) (2026-10-03) - [Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis](https://mlsanity.com/paper/2610.02718/) (2026-10-02) - [SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning](https://mlsanity.com/paper/2610.01962/) (2026-10-01) - [Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models](https://mlsanity.com/paper/2610.01625/) (2026-10-01) - [Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model](https://mlsanity.com/paper/2609.37638/) (2026-09-30) - [Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation](https://mlsanity.com/paper/2609.38282/) (2026-09-29) - [Reprogramming Vision-Language Models via Structured Prompt Reparameterization](https://mlsanity.com/paper/2609.36680/) (2026-09-29) - [VLM4Cluster: Benchmarking Deep Clustering In the Era of Vision-Language Pre-training](https://mlsanity.com/paper/2609.36648/) (2026-09-29) - [One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models](https://mlsanity.com/paper/2609.36101/) (2026-09-28) - [ConvCue: Complementary Visual Inductive Biases for Vision-Language Models](https://mlsanity.com/paper/2609.34196/) (2026-09-28) - [Position Aware Layer Queries for Test Time Training in Vision Language Models](https://mlsanity.com/paper/2609.34021/) (2026-09-27) - [Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models](https://mlsanity.com/paper/2609.33701/) (2026-09-27) - [Kernel-Based Steering of CLIP with Vision-Language Model Preferences](https://mlsanity.com/paper/2609.32203/) (2026-09-26) - [Open Vocabulary Domain Unlearning](https://mlsanity.com/paper/2609.31356/) (2026-09-25) - [ProCAP: Probabilistic Cross-Attentive Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2609.30434/) (2026-09-24) - [Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models](https://mlsanity.com/paper/2609.29358/) (2026-09-24) - [MEVL-STP: Multi-Encoder and Vision Language Model for Arbitrarily Shaped Scene Text Spotting](https://mlsanity.com/paper/2609.28857/) (2026-09-23) - [HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space](https://mlsanity.com/paper/2609.24564/) (2026-09-21) - [Hierarchical Prompt Learning for Hyperbolic Vision-Language Models](https://mlsanity.com/paper/2609.24276/) (2026-09-21) - [Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains](https://mlsanity.com/paper/2609.23655/) (2026-09-20) - [PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models](https://mlsanity.com/paper/2609.23600/) (2026-09-20) - [Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction](https://mlsanity.com/paper/2609.31697/) (2026-09-18)