# Thousand-Brains Systems: Sensorimotor Intelligence for Rapid, Robust Learning and Inference

arXiv: https://arxiv.org/abs/2507.04494 · HTML: https://mlsanity.com/paper/2507.04494/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 107 references that are in the map.
- First posted on arXiv 6 Jul 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet](https://mlsanity.com/paper/1904.00760/) (2019)
- [Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots](https://mlsanity.com/paper/2310.13724/) (2023)
- [Partial success in closing the gap between human and machine vision](https://mlsanity.com/paper/2106.07411/) (2021)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Scaling Instructable Agents Across Many Simulated Worlds](https://mlsanity.com/paper/2404.10179/) (2024)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Can We Talk Models Into Seeing the World Differently?](https://mlsanity.com/paper/2403.09193/) (2024)
- [In Search of Forgotten Domain Generalization](https://mlsanity.com/paper/2410.08258/) (2024)
- [Sensitivity of Slot-Based Object-Centric Models to their Number of Slots](https://mlsanity.com/paper/2305.18890/) (2023)
- [The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2411.10175/) (2024)
- [Contour Integration Underlies Human-Like Vision](https://mlsanity.com/paper/2504.05253/) (2025)
- [Grid Cell Path Integration For Movement-Based Visual Object Recognition](https://mlsanity.com/paper/2102.09076/) (2021)
- [The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence](https://mlsanity.com/paper/2412.18354/) (2024)

## Built on by (most cited first, 4 of 4)

- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [The Thousand Brains Theory 2.0: An Extension for the Long-Range Connections of the Neocortical Heterarchy](https://mlsanity.com/paper/2507.05888/) (2025)
- [A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments](https://mlsanity.com/paper/2512.13517/) (2025)
- [Remapping and navigation of an embedding space via error minimization: a fundamental organizational principle of cognition in natural and artificial systems](https://mlsanity.com/paper/2601.14096/) (2026)

## Abstract (arXiv)

Current AI systems achieve impressive performance on many tasks, yet they lack core attributes of biological intelligence, including rapid, continual learning, representations grounded in sensorimotor interactions, and structured knowledge that enables efficient generalization. Neuroscience theory suggests that mammals evolved flexible intelligence through the replication of a semi-independent, sensorimotor module, a functional unit known as a cortical column. To address the disparity between biological and artificial intelligence, thousand-brains systems were proposed as a means of mirroring the architecture of cortical columns and their interactions. In the current work, we evaluate the unique properties of Monty, the first implementation of a thousand-brains system. We focus on 3D object perception, and in particular, the combined task of object recognition and pose estimation. Utilizing the YCB dataset of household objects, we first assess Monty's use of sensorimotor learning to build structured representations, finding that these enable robust generalization. These representations include an emphasis on classifying objects by their global shape, as well as a natural ability to detect object symmetries. We then explore Monty's use of model-free and model-based policies to enable rapid inference by supporting principled movements. We find that such policies complement Monty's modular architecture, a design that can accommodate communication between modules to further accelerate inference speed via a novel `voting' algorithm. Finally, we examine Monty's use of associative, Hebbian-like binding to enable rapid, continual, and computationally efficient learning, properties that compare favorably to current deep learning architectures. While Monty is still in a nascent stage of development, these findings support thousand-brains systems as a powerful and promising new approach to AI.