# A recurrent vision transformer shows signatures of primate visual attention

arXiv: https://arxiv.org/abs/2502.10955 · HTML: https://mlsanity.com/paper/2502.10955/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 123 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [xLSTM: Extended Long Short-Term Memory](https://mlsanity.com/paper/2405.04517/) (2024)
- [Recurrence is required to capture the representational dynamics of the human visual system](https://mlsanity.com/paper/1903.05946/) (2019)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [Deep Reinforcement Learning and its Neuroscientific Implications](https://mlsanity.com/paper/2007.03750/) (2020)
- [Offline Actor-Critic Reinforcement Learning Scales to Large Models](https://mlsanity.com/paper/2402.05546/) (2024)
- [Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention](https://mlsanity.com/paper/2303.01542/) (2023)
- [Trends, Applications, and Challenges in Human Attention Modelling](https://mlsanity.com/paper/2402.18673/) (2024)
- [Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models](https://mlsanity.com/paper/2305.03601/) (2023)
- [Emergence of Human-Like Attention in Self-Supervised Vision Transformers: an eye-tracking study](https://mlsanity.com/paper/2410.22768/) (2024)
- [Human Attention during Goal-directed Reading Comprehension Relies on Task Optimization](https://mlsanity.com/paper/2107.05799/) (2021)

## Abstract (arXiv)

Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates self-attention with recurrent memory, allowing both current inputs and stored information to guide attention allocation. Trained solely via sparse reward feedback on a spatially cued orientation change detection task, a paradigm used in primate studies, our model exhibits primate like signatures of attention, including improved accuracy and faster responses for cued stimuli that scale with cue validity. Analysis of self-attention maps reveals dynamic spatial prioritization with reactivation prior to expected changes, and targeted perturbations produce performance shifts similar to those observed in primate frontal eye fields and superior colliculus. These findings demonstrate that incorporating recurrent feedback into self attention can capture key aspects of primate visual attention.