{"total":113,"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":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603,"area":"lr"},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334,"area":"lr"},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183,"area":"mllm"},{"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":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110,"area":"mllm"},{"id":"2212.00959","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","created":"2022-12-02","cited_by_count":103,"area":"lr"},{"id":"2101.03737","title":"Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97,"area":null},{"id":"2105.11644","title":"A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions","created":"2021-05-25","cited_by_count":78,"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":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64,"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":"2304.14068","title":"Interpretable Neural-Symbolic Concept Reasoning","created":"2023-04-27","cited_by_count":57,"area":null},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52,"area":null},{"id":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43,"area":"mllm"},{"id":"2111.08164","title":"A Survey on Neural-symbolic Learning Systems","created":"2021-11-10","cited_by_count":39,"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":"2310.16035","title":"What's Left? Concept Grounding with Logic-Enhanced Foundation Models","created":"2023-10-24","cited_by_count":33,"area":"lr"},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2111.12990","title":"Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning","created":"2021-11-25","cited_by_count":27,"area":null},{"id":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25,"area":null},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25,"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":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"area":null},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2401.00158","title":"ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph","created":"2023-12-30","cited_by_count":23,"area":"lr"},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2101.05479","title":"Understanding the Role of Scene Graphs in Visual Question Answering","created":"2021-01-14","cited_by_count":20,"area":null},{"id":"2103.07829","title":"SemVLP: Vision-Language Pre-training by Aligning Semantics at Multiple Levels","created":"2021-03-14","cited_by_count":19,"area":"mllm"},{"id":"2112.05892","title":"COMPOSER: Compositional Reasoning of Group Activity in Videos with Keypoint-Only Modality","created":"2021-12-11","cited_by_count":19,"area":null},{"id":"2110.08797","title":"Towards Language-guided Visual Recognition via Dynamic Convolutions","created":"2021-10-17","cited_by_count":17,"area":null},{"id":"2112.11691","title":"Comprehensive Visual Question Answering on Point Clouds through Compositional Scene Manipulation","created":"2021-12-22","cited_by_count":17,"area":null},{"id":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17,"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":"2204.02380","title":"CLEVR-X: A Visual Reasoning Dataset for Natural Language Explanations","created":"2022-04-05","cited_by_count":16,"area":"lr"},{"id":"2210.13650","title":"ReaRev: Adaptive Reasoning for Question Answering over Knowledge Graphs","created":"2022-10-24","cited_by_count":16,"area":null},{"id":"2311.17365","title":"Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning","created":"2023-11-29","cited_by_count":16,"area":"lr"},{"id":"2104.00170","title":"Are Bias Mitigation Techniques for Deep Learning Effective?","created":"2021-04-01","cited_by_count":14,"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":"2212.13296","title":"VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges","created":"2022-12-26","cited_by_count":14,"area":"lr"},{"id":"2306.08397","title":"Scalable Neural-Probabilistic Answer Set Programming","created":"2023-06-14","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":"2111.09276","title":"Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval","created":"2021-11-17","cited_by_count":13,"area":null},{"id":"2205.04188","title":"Joint learning of object graph and relation graph for visual question answering","created":"2022-05-09","cited_by_count":13,"area":null},{"id":"2103.10574","title":"Hopper: Multi-hop Transformer for Spatiotemporal Reasoning","created":"2021-03-19","cited_by_count":12,"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":"2203.06107","title":"REX: Reasoning-aware and Grounded Explanation","created":"2022-03-11","cited_by_count":12,"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":"2205.09710","title":"Voxel-informed Language Grounding","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2311.17331","title":"Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering","created":"2023-11-29","cited_by_count":11,"area":"lr"},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","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":"2109.13392","title":"The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding","created":"2021-09-27","cited_by_count":8,"area":null},{"id":"2110.03395","title":"SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2208.04215","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2404.19696","title":"Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners","created":"2024-04-30","cited_by_count":8,"area":null},{"id":"2411.11150","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","created":"2024-11-17","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":"2110.12679","title":"Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2205.12616","title":"Guiding Visual Question Answering with Attention Priors","created":"2022-05-25","cited_by_count":7,"area":"lr"},{"id":"2403.12026","title":"FlexCap: Describe Anything in Images in Controllable Detail","created":"2024-03-18","cited_by_count":7,"area":"mllm"},{"id":"2111.08531","title":"Language bias in Visual Question Answering: A Survey and Taxonomy","created":"2021-11-16","cited_by_count":6,"area":null},{"id":"2209.09543","title":"FACT: Learning Governing Abstractions Behind Integer Sequences","created":"2022-09-20","cited_by_count":6,"area":null},{"id":"2210.13591","title":"Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision","created":"2022-10-24","cited_by_count":6,"area":"mllm"},{"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":"2103.00519","title":"KANDINSKYPatterns -- An experimental exploration environment for Pattern Analysis and Machine Intelligence","created":"2021-02-28","cited_by_count":5,"area":null},{"id":"2303.05342","title":"Knowledge-augmented Few-shot Visual Relation Detection","created":"2023-03-09","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":"2407.01983","title":"SADL: An Effective In-Context Learning Method for Compositional Visual QA","created":"2024-07-02","cited_by_count":5,"area":"mllm"},{"id":"2503.18213","title":"A Study on Neuro-Symbolic Artificial Intelligence: Healthcare Perspectives","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2104.06365","title":"Neuro-Symbolic VQA: A review from the perspective of AGI desiderata","created":"2021-04-13","cited_by_count":4,"area":null},{"id":"2303.10482","title":"Divide and Conquer: Answering Questions with Object Factorization and Compositional Reasoning","created":"2023-03-18","cited_by_count":4,"area":null},{"id":"2306.03175","title":"Infusing Lattice Symmetry Priors in Attention Mechanisms for Sample-Efficient Abstract Geometric Reasoning","created":"2023-06-05","cited_by_count":4,"area":"lr"},{"id":"2306.10490","title":"Rapid Image Labeling via Neuro-Symbolic Learning","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2407.14562","title":"Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought","created":"2024-07-18","cited_by_count":4,"area":"lr"},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2207.01916","title":"Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models","created":"2022-07-05","cited_by_count":3,"area":"lr"},{"id":"2211.08086","title":"Visually Grounded VQA by Lattice-based Retrieval","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2303.10944","title":"Location-Free Scene Graph Generation","created":"2023-03-20","cited_by_count":3,"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":"2312.16012","title":"Detection-based Intermediate Supervision for Visual Question Answering","created":"2023-12-26","cited_by_count":3,"area":"lr"},{"id":"2408.12674","title":"One-shot Video Imitation via Parameterized Symbolic Abstraction Graphs","created":"2024-08-22","cited_by_count":3,"area":null},{"id":"2503.14957","title":"Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering","created":"2025-03-19","cited_by_count":3,"area":"lr"},{"id":"2103.11537","title":"How to Design Sample and Computationally Efficient VQA Models","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2201.10656","title":"MGA-VQA: Multi-Granularity Alignment for Visual Question Answering","created":"2022-01-25","cited_by_count":2,"area":null},{"id":"2207.13242","title":"Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2212.08283","title":"SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2408.13499","title":"R2G: Reasoning to Ground in 3D Scenes","created":"2024-08-24","cited_by_count":2,"area":null},{"id":"2202.06858","title":"An experimental study of the vision-bottleneck in VQA","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2210.00858","title":"Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach","created":"2022-10-03","cited_by_count":1,"area":"lr"},{"id":"2311.06386","title":"Towards A Unified Neural Architecture for Visual Recognition and Reasoning","created":"2023-11-10","cited_by_count":1,"area":"lr"},{"id":"2403.17647","title":"Intrinsic Subgraph Generation for Interpretable Graph based Visual Question Answering","created":"2024-03-26","cited_by_count":1,"area":null},{"id":"2507.22933","title":"Augmented Vision-Language Models: A Systematic Review","created":"2025-07-24","cited_by_count":1,"area":"mllm"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"}],"next_cursor":"100"}