{"total":14,"rows":[{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2403.05110","title":"Efficient Data Collection for Robotic Manipulation via Compositional Generalization","created":"2024-03-08","cited_by_count":37,"area":null},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2401.00094","title":"Generating Enhanced Negatives for Training Language-Based Object Detectors","created":"2023-12-29","cited_by_count":11,"area":null},{"id":"2203.08445","title":"Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation","created":"2022-03-16","cited_by_count":8,"area":null},{"id":"2602.24188","title":"MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games","created":"2026-02-27","cited_by_count":8,"area":null},{"id":"2210.15037","title":"Generalization Differences between End-to-End and Neuro-Symbolic Vision-Language Reasoning Systems","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2312.02249","title":"Recursive Visual Programming","created":"2023-12-04","cited_by_count":6,"area":null},{"id":"2311.08695","title":"Attribute Diversity Determines the Systematicity Gap in VQA","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2309.07624","title":"Dynamic MOdularized Reasoning for Compositional Structured Explanation Generation","created":"2023-09-14","cited_by_count":1,"area":null},{"id":"2404.12013","title":"Sequential Compositional Generalization in Multimodal Models","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2605.06157","title":"HNC: Leveraging Hard Negative Captions towards Models with Fine-Grained Visual-Linguistic Comprehension Capabilities","created":"2026-05-06","cited_by_count":1,"area":null}],"next_cursor":null}