{"total":27,"rows":[{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819,"area":null},{"id":"2303.13483","title":"NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations","created":"2023-03-23","cited_by_count":57,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2110.02526","title":"Coarse-to-Fine Reasoning for Visual Question Answering","created":"2021-10-06","cited_by_count":25,"area":null},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2104.03656","title":"How Transferable are Reasoning Patterns in VQA?","created":"2021-04-08","cited_by_count":16,"area":null},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15,"area":null},{"id":"2110.00519","title":"Calibrating Concepts and Operations: Towards Symbolic Reasoning on Real Images","created":"2021-10-01","cited_by_count":14,"area":null},{"id":"2107.06325","title":"Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering","created":"2021-07-13","cited_by_count":13,"area":null},{"id":"2109.01934","title":"Weakly Supervised Relative Spatial Reasoning for Visual Question Answering","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2107.11576","title":"X-GGM: Graph Generative Modeling for Out-of-Distribution Generalization in Visual Question Answering","created":"2021-07-24","cited_by_count":10,"area":null},{"id":"2205.02456","title":"Declaration-based Prompt Tuning for Visual Question Answering","created":"2022-05-05","cited_by_count":9,"area":null},{"id":"2401.07803","title":"Uncovering the Full Potential of Visual Grounding Methods in VQA","created":"2024-01-15","cited_by_count":9,"area":null},{"id":"2305.15015","title":"Measuring Faithful and Plausible Visual Grounding in VQA","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2106.05597","title":"Supervising the Transfer of Reasoning Patterns in VQA","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2201.11316","title":"Transformer Module Networks for Systematic Generalization in Visual Question Answering","created":"2022-01-27","cited_by_count":5,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2508.01984","title":"IMoRe: Implicit Program-Guided Reasoning for Human Motion Q&A","created":"2025-08-04","cited_by_count":5,"area":null},{"id":"2206.12533","title":"From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering","created":"2022-06-25","cited_by_count":3,"area":null},{"id":"2211.08086","title":"Visually Grounded VQA by Lattice-based Retrieval","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2412.13636","title":"Consistency of Compositional Generalization across Multiple Levels","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2405.03852","title":"VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2505.23045","title":"Multi-Sourced Compositional Generalization in Visual Question Answering","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2606.02168","title":"Disentanglement-Based Equivariant Learning for Compositional VQA","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}