# DIDO: Distilling Interaction-Centric Dynamics into One-Step Denoising for World Action Models

arXiv: https://arxiv.org/abs/2609.15570 · HTML: https://mlsanity.com/paper/2609.15570/

## Key facts

- Cited by 2 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 21 of its 55 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

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

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

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models](https://mlsanity.com/paper/2510.13626/) (2025)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [Motubrain: An Advanced World Action Model for Robot Control](https://mlsanity.com/paper/2604.27792/) (2026)
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026)
- [Flash-WAM: Modality-Aware Distillation for World Action Models](https://mlsanity.com/paper/2606.05254/) (2026)
- [Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models](https://mlsanity.com/paper/2608.04404/) (2026)
- [MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models](https://mlsanity.com/paper/2606.13515/) (2026)
- [Learning 4D Geometric Priors for Inference-Efficient World Action Models](https://mlsanity.com/paper/2607.05468/) (2026)
- [MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis](https://mlsanity.com/paper/2506.18897/) (2025)
- [GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch](https://mlsanity.com/paper/2607.13960/) (2026)
- [ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts](https://mlsanity.com/paper/2607.28993/) (2026)
- [PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing](https://mlsanity.com/paper/2603.21669/) (2026)
- [Faster-WAM: Do World Action Models Need Deep Action Modules?](https://mlsanity.com/paper/2608.02365/) (2026)
- [Orca: The World is in Your Mind](https://mlsanity.com/paper/2606.30534/) (2026)
- [SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models](https://mlsanity.com/paper/2607.25912/) (2026)

## Built on by (most cited first, 2 of 2)

- [Q-WAM: 4-Bit Quantization of World Action Models with Action-Subspace Protection](https://mlsanity.com/paper/2609.33269/) (2026)
- [CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight](https://mlsanity.com/paper/2610.00859/) (2026)

## Abstract (arXiv)

World Action Models (WAMs) use video generation models to predict future visual dynamics for robotic manipulation, but iterative denoising introduces additional latency for closed-loop control. We empirically find that visual content converges at different rates during denoising. Static background structure forms early, whereas the gripper and manipulated object remain blurry after the first step, with their interaction dynamics emerging only through subsequent denoising. Consequently, naively truncating a multi-step video model to one step preserves scene structure but loses the interaction-centric dynamics most critical for manipulation. To address this issue, we propose DIDO, which distills the converged dynamics of a multi-step video model into a single denoising step. DIDO combines distribution matching distillation with interaction-centric representation guidance. Beyond compressing multi-step generation into one forward pass, DIDO explicitly models the gripper, manipulated object, and their interaction using supervised bounding-box visual reasoning tokens. Additionally, DIDO aligns the target object's representations across multiple model layers with features from a pretrained DINOv3 encoder. This interaction-centric guidance helps the distilled model preserve both the relevant entities and their future dynamics in a single step, while substantially reducing inference latency. DIDO achieves an average success rate of 99.0% on LIBERO, 76.6% on LIBERO-Plus, and 92.0% on RoboTwin, while also demonstrating effective transfer to long-horizon and generalization tasks in real-world robotic manipulation.