mlsanityData to 7 Oct 2026

A Review of Emerging Research Directions in Abstract Visual Reasoning

arXiv 2202.10284 ↗First posted 21 Feb 2022cs.AI cs.CV cs.LGcited by 33

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Abstract Visual Reasoning (AVR) problems are commonly used to approximate human intelligence. They test the ability of applying previously gained knowledge, experience and skills in a completely new setting, which makes them particularly well-suited for this task. Recently, the AVR problems have become popular as a proxy to study machine intelligence, which has led to emergence of new distinct types of problems and multiple benchmark sets. In this work we review this emerging AVR research and propose a taxonomy to categorise the AVR tasks along 5 dimensions: input shapes, hidden rules, target task, cognitive function, and main challenge. The perspective taken in this survey allows to characterise AVR problems with respect to their shared and distinct properties, provides a unified view on the existing approaches for solving AVR tasks, shows how the AVR problems relate to practical applications, and outlines promising directions for future work. One of them refers to the observation that in the machine learning literature different tasks are considered in isolation, which is in the stark contrast with the way the AVR tasks are used to measure human intelligence, where multiple types of problems are combined within a single IQ test.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 92 of its 206 references that are in the map. First posted on arXiv 21 Feb 2022.

Builds on

92 of 206 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices28 Jan

Other references · 91

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016Layer Normalizationcited by 5,579
  7. 2013Auto-Encoding Variational Bayescited by 3,980
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,646
  11. 2015VQA: Visual Question Answeringcited by 2,489
  12. 2016Modeling Context in Referring Expressionscited by 1,054
38 more
  1. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  2. 2018From Recognition to Cognition: Visual Commonsense Reasoningcited by 553
  3. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  4. 2018A Corpus for Reasoning About Natural Language Grounded in Photographscited by 457
  5. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  6. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  7. 2017A simple neural network module for relational reasoningcited by 345
  8. 2019Analysing Mathematical Reasoning Abilities of Neural Modelscited by 331
  9. 2017FigureQA: An Annotated Figure Dataset for Visual Reasoningcited by 314
  10. 2019Deep Learning for Symbolic Mathematicscited by 266
  11. 2019Visual Entailment: A Novel Task for Fine-Grained Image Understandingcited by 250
  12. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
  13. 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
  14. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 211
  15. 2017Learning Explanatory Rules from Noisy Datacited by 210
  16. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  17. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  18. 2020The Next Decade in AI: Four Steps Towards Robust Artificial Intelligencecited by 194
  19. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  20. 2018Measuring abstract reasoning in neural networkscited by 165
  21. 2019Neural Logic Machinescited by 144
  22. 2019PHYRE: A New Benchmark for Physical Reasoningcited by 137
  23. 2021From Show to Tell: A Survey on Deep Learning-based Image Captioningcited by 137
  24. 2016Visual Question Answering: A Survey of Methods and Datasetscited by 123
  25. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  26. 2017Building machines that adapt and compute like brainscited by 99
  27. 2020A Survey on Generative Adversarial Networks: Variants, Applications, and Trainingcited by 97
  28. 2018Actor-Centric Relation Networkcited by 87
  29. 2019CoPhy: Counterfactual Learning of Physical Dynamicscited by 80
  30. 2018IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoningcited by 72
  31. 2020Stratified Rule-Aware Network for Abstract Visual Reasoningcited by 72
  32. 2016Tagger: Deep Unsupervised Perceptual Groupingcited by 69
  33. 2020Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoningcited by 63
  34. 2020Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sensecited by 62
  35. 2019Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoningcited by 60
  36. 2020Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoningcited by 58
  37. 2019Learning Perceptual Inference by Contrastingcited by 57
  38. 2016Visual Question Answering: Datasets, Algorithms, and Future Challengescited by 56

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 15; 2025: 5; 2026: 3.

33 papers.

Sort:

By area:

  1. 2024LLaVA-CoT: Let Vision Language Models Reason Step-by-Stepcited by 446
  2. 2023The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domaincited by 97
  3. 2023Large Language Models are Visual Reasoning Coordinatorscited by 58
  4. 2024Reasoning Abilities of Large Language Models: In-Depth Analysis on the Abstraction and Reasoning Corpuscited by 32
  5. 2024MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learningcited by 30
  6. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  7. 2025MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Modelscited by 28
  8. 2022Are Deep Neural Networks SMARTer than Second Graders?cited by 24
  9. 2023Learning Differentiable Logic Programs for Abstract Visual Reasoningcited by 12
  10. 2024Generalized Planning for the Abstraction and Reasoning Corpuscited by 10
  11. 2022SAViR-T: Spatially Attentive Visual Reasoning with Transformerscited by 9
  12. 2024Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objectscited by 9
21 more
  1. 2023Solving ARC visual analogies with neural embeddings and vector arithmetic: A generalized methodcited by 8
  2. 2023Benchmarks for Physical Reasoning AIcited by 8
  3. 2024ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learningcited by 7
  4. 2025Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problemscited by 7
  5. 2023One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problemscited by 6
  6. 2024Text-to-Image Cross-Modal Generation: A Systematic Reviewcited by 5
  7. 2024COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSescited by 5
  8. 2023A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processingcited by 4
  9. 2024A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoningcited by 4
  10. 2024Navigating Hallucinations for Reasoning of Unintentional Activitiescited by 3
  11. 2023A Survey on Interpretable Cross-modal Reasoningcited by 2
  12. 2024Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selectioncited by 2
  13. 2024Position: Do Not Explain Vision Models Without Contextcited by 2
  14. 2024Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RLcited by 2
  15. 2025From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC Benchmarkcited by 2
  16. 2024Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approachcited by 1
  17. 2025Advancing Generalization Across a Variety of Abstract Visual Reasoning Taskscited by 0
  18. 2025Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoningcited by 0
  19. 2026Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relationscited by 0
  20. 2026DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENscited by 0
  21. 2026ChronoVision: Temporal Reasoning via Latent State Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Unified View of Abstract Visual Reasoning Problems
  2. 2025On Data Synthesis and Post-training for Visual Abstract Reasoning
  3. 2026Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
  4. 2025Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
  5. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoning
  6. 2025A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs
  7. 2022Abstract Visual Reasoning with Tangram Shapes
  8. 2024Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?