{"total":63,"rows":[{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382,"area":"mllm"},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2206.04301","title":"Unveiling Transformers with LEGO: a synthetic reasoning task","created":"2022-06-09","cited_by_count":106,"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":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43,"area":"lr"},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34,"area":"lr"},{"id":"2202.10284","title":"A Review of Emerging Research Directions in Abstract Visual Reasoning","created":"2022-02-21","cited_by_count":33,"area":"lr"},{"id":"2403.11793","title":"Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpus","created":"2024-03-18","cited_by_count":32,"area":"lr"},{"id":"2404.13591","title":"MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning","created":"2024-04-21","cited_by_count":30,"area":"lr"},{"id":"2107.12580","title":"Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization","created":"2021-07-27","cited_by_count":29,"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":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2109.08994","title":"ReaSCAN: Compositional Reasoning in Language Grounding","created":"2021-09-18","cited_by_count":19,"area":null},{"id":"2310.10207","title":"Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World","created":"2023-10-16","cited_by_count":18,"area":"lr"},{"id":"2306.00503","title":"MEWL: Few-shot multimodal word learning with referential uncertainty","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2410.19546","title":"Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?","created":"2024-10-25","cited_by_count":16,"area":"lr"},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"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":"2105.13351","title":"Tracking Without Re-recognition in Humans and Machines","created":"2021-05-27","cited_by_count":12,"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":"2306.07743","title":"V-LoL: A Diagnostic Dataset for Visual Logical Learning","created":"2023-06-13","cited_by_count":8,"area":"lr"},{"id":"2210.14914","title":"Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability","created":"2022-10-26","cited_by_count":7,"area":"lr"},{"id":"2508.12026","title":"Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems","created":"2025-08-16","cited_by_count":7,"area":"lr"},{"id":"2602.01541","title":"Toward Cognitive Supersensing in Multimodal Large Language Model","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2211.16663","title":"Geoclidean: Few-Shot Generalization in Euclidean Geometry","created":"2022-11-30","cited_by_count":6,"area":null},{"id":"2309.01256","title":"BDC-Adapter: Brownian Distance Covariance for Better Vision-Language Reasoning","created":"2023-09-03","cited_by_count":6,"area":"lr"},{"id":"2311.09064","title":"Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models","created":"2023-11-15","cited_by_count":6,"area":"wm"},{"id":"2312.09997","title":"One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems","created":"2023-12-15","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":"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":"2501.13620","title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","created":"2025-01-23","cited_by_count":5,"area":"lr"},{"id":"2505.21850","title":"Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2512.21329","title":"Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2206.07196","title":"Towards a Solution to Bongard Problems: A Causal Approach","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2312.15310","title":"Towards Generalization in Subitizing with Neuro-Symbolic Loss using Holographic Reduced Representations","created":"2023-12-23","cited_by_count":4,"area":null},{"id":"2406.11061","title":"A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning","created":"2024-06-16","cited_by_count":4,"area":"lr"},{"id":"2407.19666","title":"Take A Step Back: Rethinking the Two Stages in Visual Reasoning","created":"2024-07-29","cited_by_count":4,"area":"lr"},{"id":"2411.00264","title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2603.13856","title":"Can AI Understand the Language of Origami?","created":"2026-03-14","cited_by_count":4,"area":null},{"id":"2309.03468","title":"Support-Set Context Matters for Bongard Problems","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2410.02094","title":"Tracking objects that change in appearance with phase synchrony","created":"2024-10-02","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":"2105.09848","title":"Flexible Compositional Learning of Structured Visual Concepts","created":"2021-05-20","cited_by_count":2,"area":null},{"id":"2201.11105","title":"Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis","created":"2021-12-15","cited_by_count":2,"area":null},{"id":"2403.03190","title":"Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Ability","created":"2024-03-05","cited_by_count":2,"area":"lr"},{"id":"2411.15626","title":"Aligning Generalisation Between Humans and Machines","created":"2024-11-23","cited_by_count":2,"area":null},{"id":"2602.03038","title":"Bongards at the Boundary of Perception and Reasoning: Programs or Language?","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2606.00188","title":"PaintBench: Deterministic Evaluation of Precise Visual Editing","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2407.02688","title":"Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Ability","created":"2024-07-02","cited_by_count":1,"area":"lr"},{"id":"2607.08233","title":"Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2205.04545","title":"A Probabilistic Generative Model of Free Categories","created":"2022-05-09","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":"2312.03812","title":"Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities","created":"2023-12-06","cited_by_count":0,"area":null},{"id":"2403.03452","title":"D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Ability","created":"2024-03-06","cited_by_count":0,"area":"lr"},{"id":"2408.05894","title":"GlyphPattern: An Abstract Pattern Recognition Benchmark for Vision-Language Models","created":"2024-08-12","cited_by_count":0,"area":"mllm"},{"id":"2604.16054","title":"Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2606.00148","title":"StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual Reasoning","created":"2026-05-29","cited_by_count":0,"area":"lr"},{"id":"2608.04111","title":"GEB-Bench: Abstract Structures Told in Many Voices","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.32619","title":"Intuition vectors","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}