# RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation

arXiv: https://arxiv.org/abs/2510.09036 · HTML: https://mlsanity.com/paper/2510.09036/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 15 of its 52 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 15 of 15)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [Masked World Models for Visual Control](https://mlsanity.com/paper/2206.14244/) (2022)
- [CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models](https://mlsanity.com/paper/2411.18613/) (2024)
- [iVideoGPT: Interactive VideoGPTs are Scalable World Models](https://mlsanity.com/paper/2405.15223/) (2024)
- [IRASim: A Fine-Grained World Model for Robot Manipulation](https://mlsanity.com/paper/2406.14540/) (2024)
- [TesserAct: Learning 4D Embodied World Models](https://mlsanity.com/paper/2504.20995/) (2025)
- [GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction](https://mlsanity.com/paper/2412.10373/) (2024)
- [ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models](https://mlsanity.com/paper/2506.16211/) (2025)
- [GWM: Towards Scalable Gaussian World Models for Robotic Manipulation](https://mlsanity.com/paper/2508.17600/) (2025)
- [Playing with Transformer at 30+ FPS via Next-Frame Diffusion](https://mlsanity.com/paper/2506.01380/) (2025)
- [MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction](https://mlsanity.com/paper/2503.10604/) (2025)

## Built on by (most cited first, 7 of 7)

- [Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation](https://mlsanity.com/paper/2603.16669/) (2026)
- [GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation](https://mlsanity.com/paper/2605.22882/) (2026)
- [DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation](https://mlsanity.com/paper/2606.32028/) (2026)
- [UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair](https://mlsanity.com/paper/2603.19616/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)
- [Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models](https://mlsanity.com/paper/2609.03927/) (2026)
- [DepthWorld: 3D World Model for Robot Manipulation](https://mlsanity.com/paper/2610.08780/) (2026)

## Abstract (arXiv)

Learned world models hold significant potential as neural simulators for robotic manipulation. However, prevalent 2D video-based models inherently lack the spatial and kinematic reasoning crucial for physical interactions. We introduce RoDyn, a novel Robot-Dynamic 2.5D World Model that formulates environmental dynamics within a highly efficient, geometry-aware latent space. Through the proposed Robot-Dynamic Tokenizer, we explicitly couple semantic visual appearances with spatial and agent-centric priors via an RGB-dominated cross-attention mechanism and dynamic mask guidance. Furthermore, by injecting these mask priors directly into sequence transitions, our Mask-guided Autoregressive architecture drives the model to focus on active robot-object interaction regions. Extensive experiments demonstrate that RoDyn establishes SOTA generation fidelity across large-scale datasets. Crucially, it translates these predictive capabilities into substantial downstream gains, accelerating model-based reinforcement learning and achieving a 42% improvement in real-world imitation learning success rates over pure 2D baselines.