contrastive language-image pretraining

Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment AAAI 2026 Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning AAAI 2026 Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge AAAI 2026 GaussianVision: Vision-Language Alignment from Compressed Image Representations using 2D Gaussian Splatting CVPR 2026 Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation CVPR 2026 Role-SynthCLIP: A Role-Play Driven Diverse Synthetic Data Approach CVPR 2026 SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts CVPR 2026 Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training CVPR 2025 BATCLIP: Bimodal Online Test-Time Adaptation for CLIP ICCV 2025 CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation ICCV 2025 Contrastive Patient-level Pretraining Enables Longitudinal and Multimodal Fusion for Lung Cancer Risk Prediction MIDL 2025 CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology CVPR 2025 DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data ICCV 2025 Diffusion Feedback Helps CLIP See Better ICLR 2025 Enhancing SAM with Efficient Prompting and Preference Optimization for Semi-supervised Medical Image Segmentation CVPR 2025 Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation CVPR 2025 FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs CVPR 2025 GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers ICCV 2025 I0T: Embedding Standardization Method Towards Zero Modality Gap ACL 2025 Is CLIP ideal? No. Can we fix it? Yes! ICCV 2025 Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP ICCV 2025 Leveraging CLIP Encoder for Multimodal Emotion Recognition WACV 2025 Mitigate the Gap: Improving Cross-Modal Alignment in CLIP ICLR 2025 MobileViCLIP: An Efficient Video-Text Model for Mobile Devices ICCV 2025 Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws ICML 2025