{"total":106,"rows":[{"id":"2206.07550","title":"Evaluating and Inducing Personality in Pre-trained Language Models","created":"2022-05-20","cited_by_count":123,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2102.10717","title":"Abstraction and Analogy-Making in Artificial Intelligence","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2305.07141","title":"The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain","created":"2023-05-11","cited_by_count":101,"area":null},{"id":"2203.04571","title":"A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices","created":"2022-03-09","cited_by_count":64,"area":null},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59,"area":null},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","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":"2103.14230","title":"Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution","created":"2021-03-26","cited_by_count":43,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2103.14232","title":"ACRE: Abstract Causal REasoning Beyond Covariation","created":"2021-03-26","cited_by_count":30,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2502.00698","title":"MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models","created":"2025-02-02","cited_by_count":29,"area":null},{"id":"2104.08560","title":"Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments","created":"2021-04-17","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":"2206.05056","title":"On Neural Architecture Inductive Biases for Relational Tasks","created":"2022-06-09","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"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":"2401.01040","title":"Towards Cognitive AI Systems: a Survey and Prospective on Neuro-Symbolic AI","created":"2024-01-02","cited_by_count":24,"area":null},{"id":"2506.04633","title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","created":"2025-06-05","cited_by_count":21,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19,"area":null},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","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":"2206.14187","title":"Evaluating Understanding on Conceptual Abstraction Benchmarks","created":"2022-06-28","cited_by_count":13,"area":null},{"id":"2402.12370","title":"AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2103.03987","title":"Selective Replay Enhances Learning in Online Continual Analogical Reasoning","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2109.10011","title":"Unsupervised Abstract Reasoning for Raven's Problem Matrices","created":"2021-09-21","cited_by_count":12,"area":null},{"id":"2105.00421","title":"A survey on VQA_Datasets and Approaches","created":"2021-05-02","cited_by_count":11,"area":null},{"id":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","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":"2211.05052","title":"In-memory factorization of holographic perceptual representations","created":"2022-11-09","cited_by_count":10,"area":null},{"id":"2306.06094","title":"Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2312.11522","title":"Assessing SATNet's Ability to Solve the Symbol Grounding Problem","created":"2023-12-13","cited_by_count":10,"area":null},{"id":"2503.03562","title":"Towards Visual Discrimination and Reasoning of Real-World Physical Dynamics: Physics-Grounded Anomaly Detection","created":"2025-03-05","cited_by_count":10,"area":null},{"id":"2504.05089","title":"Climplicit: Climatic Implicit Embeddings for Global Ecological Tasks","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2103.12045","title":"Raven's Progressive Matrices Completion with Latent Gaussian Process Priors","created":"2021-03-22","cited_by_count":9,"area":null},{"id":"2306.11444","title":"Blackbird language matrices (BLM), a new task for rule-like generalization in neural networks: Motivations and Formal Specifications","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2406.10228","title":"VEGA: Learning Interleaved Image-Text Comprehension in Vision-Language Large Models","created":"2024-06-14","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2107.10493","title":"Abstract Reasoning via Logic-guided Generation","created":"2021-07-22","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":"2407.20806","title":"ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2409.13153","title":"Towards Efficient Neuro-Symbolic AI: From Workload Characterization to Hardware Architecture","created":"2024-09-20","cited_by_count":7,"area":null},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2509.26378","title":"MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval","created":"2025-09-30","cited_by_count":7,"area":null},{"id":"2103.01403","title":"A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics","created":"2021-03-02","cited_by_count":6,"area":null},{"id":"2104.03589","title":"PQA: Perceptual Question Answering","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","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":"2211.16663","title":"Geoclidean: Few-Shot Generalization in Euclidean Geometry","created":"2022-11-30","cited_by_count":6,"area":null},{"id":"2302.11978","title":"Does Deep Learning Learn to Abstract? A Systematic Probing Framework","created":"2023-02-23","cited_by_count":6,"area":null},{"id":"2307.03762","title":"Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2603.13372","title":"The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning","created":"2026-03-09","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":"2402.02547","title":"Integration of cognitive tasks into artificial general intelligence test for large models","created":"2024-02-04","cited_by_count":5,"area":null},{"id":"2402.17431","title":"The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2409.04053","title":"COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes","created":"2024-09-06","cited_by_count":5,"area":null},{"id":"2506.04461","title":"Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2603.02540","title":"A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities","created":"2026-03-03","cited_by_count":5,"area":null},{"id":"2206.02977","title":"DETR++: Taming Your Multi-Scale Detection Transformer","created":"2022-06-07","cited_by_count":4,"area":null},{"id":"2303.13957","title":"Factorizers for Distributed Sparse Block Codes","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2305.17262","title":"Im-Promptu: In-Context Composition from Image Prompts","created":"2023-05-26","cited_by_count":4,"area":null},{"id":"2309.10532","title":"A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processing","created":"2023-09-19","cited_by_count":4,"area":null},{"id":"2312.09890","title":"Grammatical information in BERT sentence embeddings as two-dimensional arrays","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2411.00264","title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2411.19451","title":"Learning Visual Abstract Reasoning through Dual-Stream Networks","created":"2024-11-29","cited_by_count":4,"area":null},{"id":"2211.11033","title":"On the Complexity of Bayesian Generalization","created":"2022-11-20","cited_by_count":3,"area":null},{"id":"2305.01928","title":"Visual Transformation Telling","created":"2023-05-03","cited_by_count":3,"area":null},{"id":"2309.03468","title":"Support-Set Context Matters for Bongard Problems","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2502.17382","title":"Unraveling the geometry of visual relational reasoning","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2608.12593","title":"DiG-bench: Discovery in Games","created":"2026-08-12","cited_by_count":3,"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":"2105.09848","title":"Flexible Compositional Learning of Structured Visual Concepts","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2110.11940","title":"Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2201.08450","title":"Automatic Item Generation of Figural Analogy Problems: A Review and Outlook","created":"2022-01-20","cited_by_count":2,"area":null},{"id":"2304.14986","title":"Interpreting Vision and Language Generative Models with Semantic Visual Priors","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2404.04173","title":"H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations","created":"2024-04-05","cited_by_count":2,"area":null},{"id":"2606.00188","title":"PaintBench: Deterministic Evaluation of Precise Visual Editing","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2104.13433","title":"Self-supervised Spatial Reasoning on Multi-View Line Drawings","created":"2021-04-27","cited_by_count":1,"area":null},{"id":"2109.13156","title":"DAReN: A Collaborative Approach Towards Reasoning And Disentangling","created":"2021-09-27","cited_by_count":1,"area":null},{"id":"2504.19323","title":"NSFlow: An End-to-End FPGA Framework with Scalable Dataflow Architecture for Neuro-Symbolic AI","created":"2025-04-27","cited_by_count":1,"area":null},{"id":"2507.12366","title":"FactorHD: A Hyperdimensional Computing Model for Multi-Object Multi-Class Representation and Factorization","created":"2025-07-16","cited_by_count":1,"area":null},{"id":"2608.00490","title":"Image-Space Rule Discovery","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2609.02864","title":"Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2103.15551","title":"Toward Building Science Discovery Machines","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2206.02019","title":"Symmetry as a Representation of Intuitive Geometry?","created":"2022-06-04","cited_by_count":0,"area":null},{"id":"2208.13841","title":"Visual-Imagery-Based Analogical Construction in Geometric Matrix Reasoning Task","created":"2022-08-29","cited_by_count":0,"area":null},{"id":"2210.12739","title":"Functional Indirection Neural Estimator for Better Out-of-distribution Generalization","created":"2022-10-23","cited_by_count":0,"area":null},{"id":"2302.07137","title":"Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Tasks","created":"2023-02-08","cited_by_count":0,"area":null},{"id":"2303.03340","title":"Symbolic Synthesis of Neural Networks","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2311.04474","title":"Emergent Communication for Rules Reasoning","created":"2023-11-08","cited_by_count":0,"area":null},{"id":"2311.12610","title":"VALUED -- Vision and Logical Understanding Evaluation Dataset","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2312.11272","title":"Disentangling continuous and discrete linguistic signals in transformer-based sentence embeddings","created":"2023-12-18","cited_by_count":0,"area":null}],"next_cursor":"100"}