# GAMR: A Guided Attention Model for (visual) Reasoning

arXiv: https://arxiv.org/abs/2206.04928 · HTML: https://mlsanity.com/paper/2206.04928/

## Key facts

- Cited by 12 papers in the map (data through 14 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.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [A simple neural network module for relational reasoning](https://mlsanity.com/paper/1706.01427/) (2017)
- [RAVEN: A Dataset for Relational and Analogical Visual rEasoNing](https://mlsanity.com/paper/1903.02741/) (2019)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [Measuring abstract reasoning in neural networks](https://mlsanity.com/paper/1807.04225/) (2018)
- [Long Short-Term Memory-Networks for Machine Reading](https://mlsanity.com/paper/1601.06733/) (2016)
- [Stratified Rule-Aware Network for Abstract Visual Reasoning](https://mlsanity.com/paper/2002.06838/) (2020)
- [Emergent Symbols through Binding in External Memory](https://mlsanity.com/paper/2012.14601/) (2020)
- [Attention on Abstract Visual Reasoning](https://mlsanity.com/paper/1911.05990/) (2019)
- [Understanding the computational demands underlying visual reasoning](https://mlsanity.com/paper/2108.03603/) (2021)
- [25 years of CNNs: Can we compare to human abstraction capabilities?](https://mlsanity.com/paper/1607.08366/) (2016)
- [Solving the Same-Different Task with Convolutional Neural Networks](https://mlsanity.com/paper/2101.09129/) (2021)
- [Evaluating the Progress of Deep Learning for Visual Relational Concepts](https://mlsanity.com/paper/2001.10857/) (2020)
- [Recurrent Vision Transformer for Solving Visual Reasoning Problems](https://mlsanity.com/paper/2111.14576/) (2021)
- [Program synthesis performance constrained by non-linear spatial relations in Synthetic Visual Reasoning Test](https://mlsanity.com/paper/1911.07721/) (2019)

## Built on by (most cited first, 12 of 12)

- [Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem](https://mlsanity.com/paper/2411.00238/) (2024)
- [Large Language Models are Visual Reasoning Coordinators](https://mlsanity.com/paper/2310.15166/) (2023)
- [The Relational Bottleneck as an Inductive Bias for Efficient Abstraction](https://mlsanity.com/paper/2309.06629/) (2023)
- [Systematic Visual Reasoning through Object-Centric Relational Abstraction](https://mlsanity.com/paper/2306.02500/) (2023)
- [Pix2Code: Learning to Compose Neural Visual Concepts as Programs](https://mlsanity.com/paper/2402.08280/) (2024)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs](https://mlsanity.com/paper/2501.13620/) (2025)
- [Evaluating Compositional Scene Understanding in Multimodal Generative Models](https://mlsanity.com/paper/2503.23125/) (2025)
- [Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach](https://mlsanity.com/paper/2402.12675/) (2024)
- [The role of object-centric representations, guided attention, and external memory on generalizing visual relations](https://mlsanity.com/paper/2304.07091/) (2023)
- [Beyond Transformers for Function Learning](https://mlsanity.com/paper/2304.09979/) (2023)
- [A Theoretical Analysis of Provable Compositional Generalization in Neural Networks: A Necessary and Sufficient Condition](https://mlsanity.com/paper/2505.02627/) (2025)

## 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.