Adapting Vision-Language Models Without Labels: A Comprehensive Survey (IJCV 2026) [](https://awesome.re)
July 27, 2026 · View on GitHub
This repository collects research papers on unsupervised learning methods with VLMs. The repository will be continuously updated to track the latest work in the community.
Keywords: unsupervised learning, test-time adaptation, vision-language models.
:fire: Update
- [Aug 7, 2025] Just finished the manuscript.
:page_with_curl: Overview
:sparkles: Contents
- Data-Free Transfer
- Unsupervised Domain Transfer
- Episodic Test-Time Adaptation
- Online Test-Time Adaptation
🤝 Citation
Please visit Adapting Vision-Language Models Without Labels: A Comprehensive Survey for more details and comprehensive information. If you find our paper and repo helpful, please consider citing it as follows:
@article{dong2025adapting,
title={Adapting Vision-Language Models Without Labels: A Comprehensive Survey},
author={Dong, Hao and Sheng, Lijun and Liang, Jian and He, Ran and Chatzi, Eleni and Fink, Olga},
journal={arXiv preprint arXiv:2508.05547},
year={2025}}
:collision: Selected Papers from Premier AI/ML Conferences
TPAMI-2026Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models
ICCV-2025FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
ICCV-2025Generate, Transduct, Adapt: Iterative Transduction with VLMsICCV-2025BATCLIP: Bimodal Online Test-Time Adaptation for CLIP
ICCV-2025Is Less More? Exploring Token Condensation as Training-free Test-time AdaptationICML-2025From Local Details to Global Context: Advancing Vision-Language Models with Attention-based Selection
ICML-2025GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
CVPR-2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
CVPR-2025TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models
CVPR-2025SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
CVPR-2025O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models
CVPR-2025R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
CVPR-2025Realistic Test-Time Adaptation of Vision-Language Models
CVPR-2025SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
CVPR-2025Free on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EMCVPR-2025Bayesian Test-Time Adaptation for Vision-Language ModelsCVPR-2025COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation
CVPR-2025Hierarchical Knowledge Prompt Tuning for Multi-task Test-Time AdaptationCVPR-2025On the Zero-shot Adversarial Robustness of Vision-Language Models: A Truly Zero-shot and Training-free ApproachICLR-2025RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models
ICLR-2025Noisy Test-Time Adaptation in Vision-Language Models
ICLR-2025Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
ICLR-2025DynaPrompt: Dynamic Test-Time Prompt Tuning
ICLR-2025Test-time Adaptation for Cross-modal Retrieval with Query Shift
AAAI-2025Learning to Prompt with Text Only Supervision for Vision-Language Models
AAAI-2025Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
WACV-2025Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation
WACV-2025Enhancing Visual Classification using Comparative Descriptors
WACV-2025DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language ModelsWACV-2025LATTECLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts
WACV-2025Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models
WACV-2025Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
WACV-2025Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentation WACV-2025CLIPArTT: Adaptation of CLIP to New Domains at Test Time
IJCV-2025Diffusion-Enhanced Test-time Adaptation with Text and Image Augmentation
TIP-2025Task-to-Instance Prompt Learning for Vision-Language Models at Test Time
PR-2025A Closer Look at the Explainability of Contrastive Language-Image Pre-training
PR-2025CTPT: Continual Test-time Prompt Tuning for Vision-Language ModelsNeurIPS-2024Boosting Vision-Language Models with Transduction
NeurIPS-2024OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
NeurIPS-2024Frustratingly Easy Test-Time Adaptation of Vision-Language Models
NeurIPS-2024AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
NeurIPS-2024WATT: Weight Average Test-Time Adaptation of CLIP
NeurIPS-2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
NeurIPS-2024BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping
NeurIPS-2024Historical Test-time Prompt Tuning for Vision Foundation ModelsACMMM-2024WaveDN: A Wavelet-based Training-free Zero-shot Enhancement for Vision-Language ModelsACMMM-2024Towards Robustness Prompt Tuning with Fully Test-Time Adaptation for CLIP’s Zero-Shot GeneralizationECCV-2024Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
ECCV-2024SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
ECCV-2024ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
ECCV-2024ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
ECCV-2024TAG: Text Prompt Augmentation for Zero-Shot Out-of-Distribution Detection
ECCV-2024Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation
ECCV-2024uCAP: An Unsupervised Prompting Method for Vision-Language ModelsECCV-2024Robust Calibration of Large Vision-Language Adapters
ECCV-2024Robust Calibration of Large Vision-Language Adapters ECCV-2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation
ECCV-2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation
ECCV-2024Online Zero-Shot Classification with CLIP
IJCAI-2024DTS-TPT: Dual Temporal-Sync Test-time Prompt Tuning for Zero-shot Activity Recognition
ICML-2024Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
ICML-2024Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
ICML-2024Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data
ICML-2024Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
ICML-2024Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
CVPR-2024Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
CVPR-2024The Neglected Tails in Vision-Language Models
CVPR-2024PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
CVPR-2024Label Propagation for Zero-shot Classification with Vision-Language Models
CVPR-2024Transductive Zero-Shot and Few-Shot CLIP
CVPR-2024On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?
CVPR-2024Test-Time Zero-Shot Temporal Action Localization
CVPR-2024Leveraging Cross-Modal Neighbor Representation for Improved CLIP Classification
CVPR-2024Grounding Everything: Emerging Localization Properties in Vision-Language Transformers CVPR-2024Efficient Test-Time Adaptation of Vision-Language Models
CVPR-2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models
CVPR-2024Improved Self-Training for Test-Time AdaptationCVPR-2024Any-Shift Prompting for Generalization over DistributionsICLR-2024Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
ICLR-2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
ICLR-2024PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
ICLR-2024Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
AAAI-2024Robust Test-Time Adaptation for Zero-Shot Prompt TuningAAAI-2024DART: Dual-Modal Adaptive Online Prompting and Knowledge Retention for Test-Time Adaptation
WACV-2024ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
WACV-2024CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free
WACV-2024DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification
NeurIPS-2023Neural Priming for Sample-Efficient Adaptation
NeurIPS-2023ChatGPT-Powered Hierarchical Comparisons for Image Classification
NeurIPS-2023Neural Priming for Sample-Efficient Adaptation NeurIPS-2023LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections
NeurIPS-2023Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning
NeurIPS-2023Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIPNeurIPS-2023SwapPrompt: Test-Time Prompt Adaptation for Vision-Language ModelsNeurIPS-2023Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
NeurIPS-2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
NeurIPS-2023SwapPrompt: Test-Time Prompt Adaptation for Vision-Language ModelsNeurIPS-2023Test-Time Distribution Normalization for Contrastively Learned Vision-language Models
ACMMM-2023VPA: Fully Test-Time Visual Prompt AdaptationICCV-2023What Does a Platypus Look Like? Generating Customized Prompts for Zero-Shot Image Classification
ICCV-2023SuS-X: Training-Free Name-Only Transfer of Vision-Language Models
ICCV-2023Waffling around for Performance: Visual Classification with Random Words and Broad Concepts
ICCV-2023Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning ICML-2023CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
ICML-2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image ModelsICML-2023POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models
CVPR-2023Texts as Images in Prompt Tuning for Multi-Label Image Recognition
CVPR-2023Improving Zero-shot Generalization and Robustness of Multi-modal Models
CVPR-2023Texts as Images in Prompt Tuning for Multi-Label Image Recognition ICLR-2023Visual Classification via Description from Large Language Models
ICLR-2023Masked Unsupervised Self-training for Label-free Image Classification
AAAI-2023CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention
NeurIPS-2022ReCo: Retrieve and Co-segment for Zero-shot Transfer
NeurIPS-2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
NeurIPS-2022ReCo: Retrieve and Co-segment for Zero-shot Transfer ECCV-2022Extract Free Dense Labels from CLIP
ICML-2021Learning Transferable Visual Models From Natural Language Supervision
