mlsanityData to 7 Oct 2026

GAMR: A Guided Attention Model for (visual) Reasoning

arXiv 2206.04928 ↗First posted 10 Jun 2022cs.AI cs.LG cs.NEcited by 12

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

Humans continue to outperform modern AI systems in their ability to flexibly parse and understand complex visual scenes. Here, we present a novel module for visual reasoning, the Guided Attention Model for (visual) Reasoning (GAMR), which instantiates an active vision theory -- positing that the brain solves complex visual reasoning problems dynamically -- via sequences of attention shifts to select and route task-relevant visual information into memory. Experiments on an array of visual reasoning tasks and datasets demonstrate GAMR's ability to learn visual routines in a robust and sample-efficient manner. In addition, GAMR is shown to be capable of zero-shot generalization on completely novel reasoning tasks. Overall, our work provides computational support for cognitive theories that postulate the need for a critical interplay between attention and memory to dynamically maintain and manipulate task-relevant visual information to solve complex visual reasoning tasks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 29 of its 51 references that are in the map. First posted on arXiv 10 Jun 2022.

Builds on

29 of 51 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2016Layer Normalizationcited by 5,579
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  8. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  11. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  12. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
17 more
  1. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  2. 2019Attention Augmented Convolutional Networkscited by 363
  3. 2017A simple neural network module for relational reasoningcited by 345
  4. 2014Recurrent Models of Visual Attentioncited by 344
  5. 2019RAVEN: A Dataset for Relational and Analogical Visual rEasoNingcited by 225
  6. 2016A Decomposable Attention Model for Natural Language Inferencecited by 214
  7. 2018Measuring abstract reasoning in neural networkscited by 165
  8. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  9. 2020Stratified Rule-Aware Network for Abstract Visual Reasoningcited by 72
  10. 2020Emergent Symbols through Binding in External Memorycited by 47
  11. 2019Attention on Abstract Visual Reasoningcited by 15
  12. 2021Understanding the computational demands underlying visual reasoningcited by 13
  13. 201625 years of CNNs: Can we compare to human abstraction capabilities?cited by 10
  14. 2021Solving the Same-Different Task with Convolutional Neural Networkscited by 10
  15. 2020Evaluating the Progress of Deep Learning for Visual Relational Conceptscited by 9
  16. 2021Recurrent Vision Transformer for Solving Visual Reasoning Problemscited by 9
  17. 2019Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Testcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 4; 2025: 3.

12 papers.

  1. 2024Understanding the Limits of Vision Language Models Through the Lens of the Binding Problemcited by 71
  2. 2023Large Language Models are Visual Reasoning Coordinatorscited by 58
  3. 2023The Relational Bottleneck as an Inductive Bias for Efficient Abstractioncited by 26
  4. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
  5. 2024Pix2Code: Learning to Compose Neural Visual Concepts as Programscited by 18
  6. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
  7. 2025A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMscited by 5
  8. 2025Evaluating Compositional Scene Understanding in Multimodal Generative Modelscited by 5
  9. 2024Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approachcited by 1
  10. 2023The role of object-centric representations, guided attention, and external memory on generalizing visual relationscited by 0
  11. 2023Beyond Transformers for Function Learningcited by 0
  12. 2025A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Conditioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture
  2. 2025DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
  3. 2026ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory
  4. 2026ViThinker: Active Vision-Language Reasoning via Dynamic Perceptual Querying
  5. 2025Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
  6. 2026GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
  7. 2023Towards A Unified Neural Architecture for Visual Recognition and Reasoning
  8. 2026Dual-Latent Memory Routing for Vision-Language Reasoning