{"total":130,"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":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516,"area":"lr"},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356,"area":"lr"},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","cited_by_count":120,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79,"area":"agents"},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"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":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61,"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":"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":"2105.07878","title":"A Review on Explainability in Multimodal Deep Neural Nets","created":"2021-05-17","cited_by_count":46,"area":null},{"id":"2106.11053","title":"Leveraging Language to Learn Program Abstractions and Search Heuristics","created":"2021-06-18","cited_by_count":45,"area":null},{"id":"2312.02896","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","created":"2023-12-05","cited_by_count":41,"area":"lr"},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36,"area":null},{"id":"2110.13880","title":"Understanding Interlocking Dynamics of Cooperative Rationalization","created":"2021-10-26","cited_by_count":36,"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":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2309.06629","title":"The Relational Bottleneck as an Inductive Bias for Efficient Abstraction","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2412.10402","title":"TANGO: Training-free Embodied AI Agents for Open-world Tasks","created":"2024-12-05","cited_by_count":27,"area":"agents"},{"id":"2106.13156","title":"Learning by Planning: Language-Guided Global Image Editing","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2105.01119","title":"Iterated learning for emergent systematicity in VQA","created":"2021-05-03","cited_by_count":21,"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":"2203.16639","title":"FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations","created":"2022-03-30","cited_by_count":20,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","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":"2203.16071","title":"Learning Program Representations for Food Images and Cooking Recipes","created":"2022-03-30","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":"2106.08170","title":"How Modular Should Neural Module Networks Be for Systematic Generalization?","created":"2021-06-15","cited_by_count":15,"area":null},{"id":"2109.12243","title":"Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?","created":"2021-09-25","cited_by_count":15,"area":null},{"id":"2410.20883","title":"Improving Generalization in Visual Reasoning via Self-Ensemble","created":"2024-10-28","cited_by_count":15,"area":"lr"},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2106.00320","title":"Distribution Matching for Rationalization","created":"2021-06-01","cited_by_count":14,"area":null},{"id":"2109.06122","title":"Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question Answering","created":"2021-09-13","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":"2305.08522","title":"Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs","created":"2023-05-15","cited_by_count":14,"area":null},{"id":"2310.14687","title":"API-Assisted Code Generation for Question Answering on Varied Table Structures","created":"2023-10-23","cited_by_count":14,"area":null},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","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":"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":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","cited_by_count":11,"area":null},{"id":"2101.09129","title":"Solving the Same-Different Task with Convolutional Neural Networks","created":"2021-01-22","cited_by_count":10,"area":null},{"id":"2205.02671","title":"What is Right for Me is Not Yet Right for You: A Dataset for Grounding Relative Directions via Multi-Task Learning","created":"2022-05-05","cited_by_count":10,"area":null},{"id":"2206.04669","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2311.12890","title":"De-fine: Decomposing and Refining Visual Programs with Auto-Feedback","created":"2023-11-21","cited_by_count":10,"area":null},{"id":"2409.10262","title":"Hydra-SGG: Hybrid Relation Assignment for One-stage Scene Graph Generation","created":"2024-09-16","cited_by_count":10,"area":null},{"id":"2502.13372","title":"MoVer: Motion Verification for Motion Graphics Animations","created":"2025-02-19","cited_by_count":10,"area":"mllm"},{"id":"2501.18623","title":"VLMaterial: Procedural Material Generation with Large Vision-Language Models","created":"2025-01-27","cited_by_count":9,"area":"mllm"},{"id":"2308.01236","title":"Grounded Image Text Matching with Mismatched Relation Reasoning","created":"2023-08-02","cited_by_count":8,"area":null},{"id":"2310.01358","title":"NEUCORE: Neural Concept Reasoning for Composed Image Retrieval","created":"2023-10-02","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":"2509.25757","title":"NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2106.05597","title":"Supervising the Transfer of Reasoning Patterns in VQA","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2111.12301","title":"Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Prediction","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2311.06411","title":"Analyzing Modular Approaches for Visual Question Decomposition","created":"2023-11-10","cited_by_count":6,"area":null},{"id":"2404.04007","title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","created":"2024-04-05","cited_by_count":6,"area":"lr"},{"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":"2201.11316","title":"Transformer Module Networks for Systematic Generalization in Visual Question Answering","created":"2022-01-27","cited_by_count":5,"area":null},{"id":"2306.08641","title":"Towards AGI in Computer Vision: Lessons Learned from GPT and Large Language Models","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2310.17140","title":"Symbolic Planning and Code Generation for Grounded Dialogue","created":"2023-10-26","cited_by_count":5,"area":null},{"id":"2310.18046","title":"ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese","created":"2023-10-27","cited_by_count":5,"area":"lr"},{"id":"2401.06400","title":"Generalizing Visual Question Answering from Synthetic to Human-Written Questions via a Chain of QA with a Large Language Model","created":"2024-01-12","cited_by_count":5,"area":null},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"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":"2202.10251","title":"PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2304.03253","title":"ImageEye: Batch Image Processing Using Program Synthesis","created":"2023-04-06","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":"2404.15194","title":"Closed Loop Interactive Embodied Reasoning for Robot Manipulation","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2504.20020","title":"Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2506.07778","title":"A Neurosymbolic Agent System for Compositional Visual Reasoning","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2111.12197","title":"Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS","created":"2021-11-23","cited_by_count":3,"area":null},{"id":"2202.12162","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","created":"2022-02-24","cited_by_count":3,"area":"lr"},{"id":"2208.10353","title":"Neuro-Symbolic Visual Dialog","created":"2022-08-22","cited_by_count":3,"area":null},{"id":"2211.01994","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","created":"2022-11-03","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":"2311.08695","title":"Attribute Diversity Determines the Systematicity Gap in VQA","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2312.13219","title":"Interactive Visual Task Learning for Robots","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2410.09379","title":"Multi-granularity Contrastive Cross-modal Collaborative Generation for End-to-End Long-term Video Question Answering","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2412.08564","title":"Visual Program Distillation with Template-Based Augmentation","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2502.10060","title":"DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2503.09445","title":"Astrea: A MOE-based Visual Understanding Model with Progressive Alignment","created":"2025-03-12","cited_by_count":3,"area":"mllm"},{"id":"2503.14957","title":"Neuro Symbolic Knowledge Reasoning for Procedural Video Question Answering","created":"2025-03-19","cited_by_count":3,"area":"lr"},{"id":"2504.17261","title":"Symbolic Representation for Any-to-Any Generative Tasks","created":"2025-04-24","cited_by_count":3,"area":null}],"next_cursor":"100"}