{"total":22,"rows":[{"id":"2503.08723","title":"Is CLIP ideal? No. Can we fix it? Yes!","created":"2025-03-10","cited_by_count":21,"area":null},{"id":"2505.06934","title":"Whitened CLIP as a Likelihood Surrogate of Images and Captions","created":"2025-05-11","cited_by_count":16,"area":null},{"id":"2602.24012","title":"InfoNCE Induces Gaussian Distribution","created":"2026-02-27","cited_by_count":16,"area":null},{"id":"2412.18645","title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","created":"2024-12-24","cited_by_count":15,"area":null},{"id":"2603.15026","title":"Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2507.03683","title":"On the rankability of visual embeddings","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2511.04247","title":"On the Brittleness of CLIP Text Encoders","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2602.03098","title":"TextME: Bridging Unseen Modalities Through Text Descriptions","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.03282","title":"Global Geometry Is Not Enough for Vision Representations","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.19367","title":"Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spaces","created":"2026-02-22","cited_by_count":2,"area":null},{"id":"2606.11190","title":"When to Align, When to Predict: A Phase Diagram for Multimodal Learning","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2506.22881","title":"CLIP-like Model as a Foundational Density Ratio Estimator","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2602.07154","title":"Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.14610","title":"Make it SING: Analyzing Semantic Invariants in Classifiers","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2606.30342","title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.30625","title":"Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.10698","title":"On the modality gap and the contrastive loss in multi-modal representation learning","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.13660","title":"The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.22148","title":"dRAE: Representation Autoencoder with Hyper-Spherical Codes","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.02044","title":"D\\'ej\\`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.23117","title":"Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}