clip

CAPT: Confusion-Aware Prompt Tuning for Reducing Vision-Language Misalignment CVPR 2026 Reconstructing CLIP for Open-Vocabulary Dense Perception CVPR 2026 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting ICLR 2025 A Closer Look at Backdoor Attacks on CLIP ICML 2025 Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection ICML 2025 BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition ICML 2025 Boosting the visual interpretability of CLIP via adversarial fine-tuning ICLR 2025 CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models NeurIPS 2025 Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development ICML 2025 Enhancing Foundation Models with Federated Domain Knowledge Infusion ICML 2025 Interpreting CLIP with Hierarchical Sparse Autoencoders ICML 2025 Kernel-based Unsupervised Embedding Alignment for Enhanced Visual Representation in Vision-language Models ICML 2025 LADA: Scalable Label-Specific CLIP Adapter for Continual Learning ICML 2025 LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D ICML 2025 Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws ICML 2025 Refining CLIP's Spatial Awareness: A Visual-Centric Perspective ICLR 2025 Targeted Unlearning with Single Layer Unlearning Gradient ICML 2025 Test-Time Multimodal Backdoor Detection by Contrastive Prompting ICML 2025 The Double-Ellipsoid Geometry of CLIP ICML 2025 Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models ICML 2025 Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts ICML 2025 When and How Does CLIP Enable Domain and Compositional Generalization? ICML 2025 Whitened CLIP as a Likelihood Surrogate of Images and Captions ICML 2025 Adversarial Robustification via Text-to-Image Diffusion Models ECCV 2024 Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks ICML 2024