{"total":17,"rows":[{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"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":"2507.03683","title":"On the rankability of visual embeddings","created":"2025-07-04","cited_by_count":4,"area":null},{"id":"2505.20291","title":"VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2604.17358","title":"Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions","created":"2026-04-19","cited_by_count":3,"area":null},{"id":"2510.15015","title":"DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models","created":"2025-10-16","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":"2507.07079","title":"Evaluating Attribute Confusion in Fashion Text-to-Image Generation","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.09852","title":"Perceptual Reality Transformer: What Must an Illustration Preserve?","created":"2025-08-13","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":"2605.31503","title":"How can embedding models bind concepts?","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.03976","title":"Formalizing the Binding Problem","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.00726","title":"Foveated Probes Recover Localized Binding Information in Vision Foundation Models","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.08886","title":"FRAME: Factored Retrieval via Attribute Readouts for Object-Centric Scene Memory","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.23717","title":"BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.30540","title":"Don't CLAP: Are Music-Text Models Bag-of-Words?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.37230","title":"Seeing Is Not Addressing: Auditing Linguistic Access to Frozen Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}