{"list":"closest","total":56,"rows":[{"id":"2504.06838","title":"ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models","created":"2025-04-09","cited_by_count":4},{"id":"2503.13443","title":"DPC: Dual-Prompt Collaboration for Tuning Vision-Language Models","created":"2025-03-17","cited_by_count":18},{"id":"2503.12096","title":"O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models","created":"2025-03-15","cited_by_count":15},{"id":"2503.09248","title":"Bayesian Test-Time Adaptation for Vision-Language Models","created":"2025-03-12","cited_by_count":22},{"id":"2501.16404","title":"DynaPrompt: Dynamic Test-Time Prompt Tuning","created":"2025-01-27","cited_by_count":31},{"id":"2410.12790","title":"Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models","created":"2024-10-16","cited_by_count":38},{"id":"2408.02192","title":"Unsupervised Domain Adaption Harnessing Vision-Language Pre-training","created":"2024-08-05","cited_by_count":12},{"id":"2407.15913","title":"Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models","created":"2024-07-22","cited_by_count":17},{"id":"2407.15155","title":"Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification","created":"2024-07-21","cited_by_count":5},{"id":"2407.03056","title":"Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation","created":"2024-07-03","cited_by_count":18},{"id":"2406.13875","title":"WATT: Weight Average Test-Time Adaptation of CLIP","created":"2024-06-19","cited_by_count":33},{"id":"2406.12638","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","created":"2024-06-18","cited_by_count":2},{"id":"2406.09353","title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","created":"2024-06-13","cited_by_count":8},{"id":"2406.00345","title":"DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection","created":"2024-06-01","cited_by_count":14},{"id":"2405.02954","title":"Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training","created":"2024-05-05","cited_by_count":15},{"id":"2405.02586","title":"Enhancing Vision-Language Models Generalization via Diversity-Driven Novel Feature Synthesis","created":"2024-05-04","cited_by_count":1},{"id":"2405.02266","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","created":"2024-05-03","cited_by_count":67},{"id":"2405.00754","title":"CLIPArTT: Adaptation of CLIP to New Domains at Test Time","created":"2024-05-01","cited_by_count":14},{"id":"2404.19286","title":"Soft Prompt Generation for Domain Generalization","created":"2024-04-30","cited_by_count":24},{"id":"2404.09011","title":"PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization","created":"2024-04-13","cited_by_count":15},{"id":"2404.00860","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","created":"2024-04-01","cited_by_count":14},{"id":"2403.18293","title":"Efficient Test-Time Adaptation of Vision-Language Models","created":"2024-03-27","cited_by_count":141},{"id":"2403.17589","title":"Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models","created":"2024-03-26","cited_by_count":52},{"id":"2403.14119","title":"C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion","created":"2024-03-21","cited_by_count":83},{"id":"2403.09296","title":"Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models","created":"2024-03-14","cited_by_count":19},{"id":"2403.02781","title":"PromptKD: Unsupervised Prompt Distillation for Vision-Language Models","created":"2024-03-05","cited_by_count":72},{"id":"2401.15914","title":"Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization","created":"2024-01-29","cited_by_count":17},{"id":"2401.07457","title":"Concept-Guided Prompt Learning for Generalization in Vision-Language Models","created":"2024-01-15","cited_by_count":20},{"id":"2401.02418","title":"Learning to Prompt with Text Only Supervision for Vision-Language Models","created":"2024-01-04","cited_by_count":38},{"id":"2312.12730","title":"A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models","created":"2023-12-20","cited_by_count":67},{"id":"2312.09553","title":"Prompt-based Distribution Alignment for Unsupervised Domain Adaptation","created":"2023-12-15","cited_by_count":44},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35},{"id":"2311.01459","title":"Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization","created":"2023-11-02","cited_by_count":101},{"id":"2310.08255","title":"Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification","created":"2023-10-12","cited_by_count":41},{"id":"2309.12530","title":"A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance","created":"2023-09-21","cited_by_count":40},{"id":"2309.03406","title":"Distribution-Aware Prompt Tuning for Vision-Language Models","created":"2023-09-06","cited_by_count":35},{"id":"2308.12919","title":"Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization","created":"2023-08-24","cited_by_count":13},{"id":"2308.06038","title":"Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning","created":"2023-08-11","cited_by_count":154},{"id":"2308.03793","title":"ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation","created":"2023-08-04","cited_by_count":35},{"id":"2307.07397","title":"Improving Zero-Shot Generalization for CLIP with Synthesized Prompts","created":"2023-07-14","cited_by_count":51},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38},{"id":"2304.01752","title":"Black Box Few-Shot Adaptation for Vision-Language models","created":"2023-04-04","cited_by_count":39},{"id":"2303.13283","title":"Visual-Language Prompt Tuning with Knowledge-guided Context Optimization","created":"2023-03-23","cited_by_count":308},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","cited_by_count":300},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","cited_by_count":52},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281}],"next_cursor":null}