# Embodied Representation Alignment with Mirror Neurons

arXiv: https://arxiv.org/abs/2509.21136 · HTML: https://mlsanity.com/paper/2509.21136/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation](https://mlsanity.com/paper/2209.05451/) (2022)
- [BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning](https://mlsanity.com/paper/2202.02005/) (2022)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [RVT: Robotic View Transformer for 3D Object Manipulation](https://mlsanity.com/paper/2306.14896/) (2023)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2306.17817/) (2023)
- [RVT-2: Learning Precise Manipulation from Few Demonstrations](https://mlsanity.com/paper/2406.08545/) (2024)
- [Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation](https://mlsanity.com/paper/2106.12534/) (2021)
- [Instruction-driven history-aware policies for robotic manipulations](https://mlsanity.com/paper/2209.04899/) (2022)
- [PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation](https://mlsanity.com/paper/2309.15596/) (2023)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [Assessing and Learning Alignment of Unimodal Vision and Language Models](https://mlsanity.com/paper/2412.04616/) (2024)
- [Autoregressive Action Sequence Learning for Robotic Manipulation](https://mlsanity.com/paper/2410.03132/) (2024)
- [Imitation and Mirror Systems in Robots through Deep Modality Blending Networks](https://mlsanity.com/paper/2106.08422/) (2021)

## Built on by (most cited first, 1 of 1)

- [Semantic Anchoring for Robotic Action Representations](https://mlsanity.com/paper/2607.13597/) (2026)

## Abstract (arXiv)

Mirror neurons are a class of neurons that activate both when an individual observes an action and when they perform the same action. This mechanism reveals a fundamental interplay between action understanding and embodied execution, suggesting that these two abilities are inherently connected. Nonetheless, existing machine learning methods largely overlook this interplay, treating these abilities as separate tasks. In this study, we provide a unified perspective in modeling them through the lens of representation learning. We first observe that their intermediate representations spontaneously align. Inspired by mirror neurons, we further introduce an approach that explicitly aligns the representations of observed and executed actions. Specifically, we employ two linear layers to map the representations to a shared latent space, where contrastive learning enforces the alignment of corresponding representations, effectively maximizing their mutual information. Experiments demonstrate that this simple approach fosters mutual synergy between the two tasks, effectively improving representation quality and generalization.