{"total":17,"rows":[{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2506.04870","title":"Aligning Multimodal Representations through an Information Bottleneck","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2412.14384","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2509.18552","title":"Global Minimizers of Sigmoid Contrastive Loss","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2601.18525","title":"Closing the Modality Gap Aligns Group-Wise Semantics","created":"2026-01-26","cited_by_count":5,"area":null},{"id":"2507.03683","title":"On the rankability of visual embeddings","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2508.04987","title":"Unified modality separation: A vision-language framework for unsupervised domain adaptation","created":"2025-08-07","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":"2506.04376","title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2602.03098","title":"TextME: Bridging Unseen Modalities Through Text Descriptions","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2602.20046","title":"Closing the gap in multimodal medical representation alignment","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2510.09435","title":"Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","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":"2609.01103","title":"When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}