{"total":23,"rows":[{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31,"area":null},{"id":"2506.03448","title":"RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions","created":"2025-06-03","cited_by_count":10,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2602.05729","title":"Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2509.03897","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2510.26302","title":"Understanding Hardness of Vision-Language Compositionality from A Token-level Causal Lens","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.17178","title":"ABE-CLIP: Training-Free Attribute Binding Enhancement for Compositional Image-Text Matching","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2502.09645","title":"From No to Know: Taxonomy, Challenges, and Opportunities for Negation Understanding in Multimodal Foundation Models","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2503.18507","title":"Can Text-to-Video Generation help Video-Language Alignment?","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2505.22943","title":"Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.01959","title":"Structure-aware Contrastive Learning for Diagram Understanding of Multimodal Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2503.13021","title":"Dynamic Relation Inference via Verb Embeddings","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2505.05635","title":"Neural Catalog: Scaling Species Recognition with Catalog of Life-Augmented Generation","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2509.23770","title":"GenView++: Unifying Adaptive Generative Augmentation and Quality-Driven Supervision for Contrastive Representation Learning","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2511.20274","title":"SCLARO: A Dataset for Grounded Scenario-Level Scene Understanding and ScenarioCLIP for Benchmarking","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2602.23589","title":"Pseudo Contrastive Learning for Diagram Comprehension in Multimodal Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2602.23906","title":"Half-Truths Break Similarity-Based Retrieval","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.25722","title":"No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2605.17727","title":"GraSP-VL: Length as a Semantic Granularity Interface for Vision-Language Representations","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.09263","title":"Semantic Hardness Is Not Visual Hardness: Sign-Aware Hard Negative Mining for Sign Language Retrieval","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2608.29604","title":"RePair: Turning Retrieval Failures into Counterfactual Hard Pairs","created":"2026-08-30","cited_by_count":0,"area":null}],"next_cursor":null}