{"total":16,"rows":[{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"area":null},{"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":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2601.14706","title":"LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval","created":"2026-01-21","cited_by_count":7,"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":"2503.17794","title":"Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models","created":"2025-03-22","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":"2602.02220","title":"LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2601.17666","title":"Training-Free Text-to-Image Compositional Food Generation via Prompt Grafting","created":"2026-01-25","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":"2608.21713","title":"The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation","created":"2026-08-22","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}