# Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization

arXiv: https://arxiv.org/abs/2506.06196 · HTML: https://mlsanity.com/paper/2506.06196/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 30 of its 39 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 30)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation](https://mlsanity.com/paper/2410.07864/) (2024)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Robotic Control via Embodied Chain-of-Thought Reasoning](https://mlsanity.com/paper/2407.08693/) (2024)
- [Learning Latent Plans from Play](https://mlsanity.com/paper/1903.01973/) (2019)
- [RoboNet: Large-Scale Multi-Robot Learning](https://mlsanity.com/paper/1910.11215/) (2019)
- [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023)
- [Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics](https://mlsanity.com/paper/1703.09312/) (2017)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets](https://mlsanity.com/paper/2109.13396/) (2021)
- [EgoMimic: Scaling Imitation Learning via Egocentric Video](https://mlsanity.com/paper/2410.24221/) (2024)
- [Goal-conditioned Imitation Learning](https://mlsanity.com/paper/1906.05838/) (2019)
- [Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition](https://mlsanity.com/paper/2307.14535/) (2023)
- [ALOHA Unleashed: A Simple Recipe for Robot Dexterity](https://mlsanity.com/paper/2410.13126/) (2024)
- [RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches](https://mlsanity.com/paper/2311.01977/) (2023)
- [MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting](https://mlsanity.com/paper/2403.03174/) (2024)
- [Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2206.08686/) (2022)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Task-Embedded Control Networks for Few-Shot Imitation Learning](https://mlsanity.com/paper/1810.03237/) (2018)
- [KITE: Keypoint-Conditioned Policies for Semantic Manipulation](https://mlsanity.com/paper/2306.16605/) (2023)
- [Hierarchical Few-Shot Imitation with Skill Transition Models](https://mlsanity.com/paper/2107.08981/) (2021)
- [Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation](https://mlsanity.com/paper/2312.10807/) (2023)
- [Zero-shot Task Adaptation using Natural Language](https://mlsanity.com/paper/2106.02972/) (2021)

## Built on by (most cited first, 3 of 3)

- [MolmoPoint: Better Pointing for VLMs with Grounding Tokens](https://mlsanity.com/paper/2603.28069/) (2026)
- [MemCorr-DP: Counterfactual Correspondence Conditioning for a Diffusion Policy Guided by a Reference](https://mlsanity.com/paper/2609.06615/) (2026)
- [Training Generalist Navigation Policies via Action Self-Distillation](https://mlsanity.com/paper/2610.17593/) (2026)

## Abstract (arXiv)

In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as inputs to a diffusion policy to solve dexterous bimanual manipulation tasks in the real world. We propose a novel mixture-of-experts policy architecture that combines multiple specialized expert models, each trained on a distinct mid-level representation, to improve policy generalization. This method achieves an average success rate that is 11% higher than a language-grounded baseline and 24 percent higher than a standard diffusion policy baseline on our evaluation tasks. Furthermore, we find that leveraging mid-level representations as supervision signals for policy actions within a weighted imitation learning algorithm improves the precision with which the policy follows these representations, yielding an additional performance increase of 10%. Our findings highlight the importance of grounding robot policies not only with broad perceptual tasks but also with more granular, actionable representations. For further information and videos, please visit https://mid-level-moe.github.io.