{"total":32,"rows":[{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2105.05330","title":"Neuro-Symbolic Artificial Intelligence: Current Trends","created":"2021-05-11","cited_by_count":54,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"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":"2112.13418","title":"Neuro-Symbolic Hierarchical Rule Induction","created":"2021-12-26","cited_by_count":23,"area":null},{"id":"2104.10283","title":"GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2110.09383","title":"Neuro-Symbolic Forward Reasoning","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2404.04308","title":"Visual Knowledge in the Big Model Era: Retrospect and Prospect","created":"2024-04-05","cited_by_count":16,"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":"2110.09741","title":"Trajectory Prediction with Linguistic Representations","created":"2021-10-19","cited_by_count":13,"area":null},{"id":"2103.15974","title":"Domain-robust VQA with diverse datasets and methods but no target labels","created":"2021-03-29","cited_by_count":11,"area":null},{"id":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2505.06191","title":"Building Intelligent Agents with Neuro-Symbolic Concepts","created":"2025-05-09","cited_by_count":10,"area":null},{"id":"2402.14123","title":"DeiSAM: Segment Anything with Deictic Prompting","created":"2024-02-21","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":"2506.08553","title":"From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge","created":"2025-06-10","cited_by_count":6,"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":"2503.18213","title":"A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2111.14547","title":"LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2306.10490","title":"Rapid Image Labeling via Neuro-Symbolic Learning","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2211.08086","title":"Visually Grounded VQA by Lattice-based Retrieval","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2101.06644","title":"HySTER: A Hybrid Spatio-Temporal Event Reasoner","created":"2021-01-17","cited_by_count":2,"area":null},{"id":"2103.05222","title":"Data augmentation by morphological mixup for solving Raven's Progressive Matrices","created":"2021-03-09","cited_by_count":2,"area":null},{"id":"2106.04066","title":"Semantically Adversarial Scenario Generation with Explicit Knowledge Guidance","created":"2021-06-08","cited_by_count":1,"area":null},{"id":"2211.15566","title":"Neuro-Symbolic Spatio-Temporal Reasoning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2407.00252","title":"Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review","created":"2024-06-28","cited_by_count":0,"area":null},{"id":"2501.14346","title":"HorNets: Learning from Discrete and Continuous Signals with Routing Neural Networks","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2609.32198","title":"Agents as Software: A Programming Languages Agenda for Agent Reliability","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}