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

arXiv:2609.15570 · cs.RO · Submitted 2026-09-14 · Read on arXiv

cs.RO

Submitted: 2026-09-14

Updated: 2026-10-08

Terminology

• Alignment — 24× in this paper · explained in 1 episode
• Distillation — 19× in this paper · explained in 2 episodes
• Transformer — 17× in this paper · explained in 2 episodes
• Generalization — 12× in this paper · explained in 13 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Distribution Matching — 8× in this paper · explained in 2 episodes
• Robustness — 8× in this paper · explained in 5 episodes
• World Model — 8× in this paper · explained in 7 episodes
• Distribution Shift — 6× in this paper · explained in 7 episodes
• Hyperparameters — 5× in this paper · explained in 2 episodes
• Closed-Loop Control — 4× in this paper · explained in 3 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Latent Dynamics — 2× in this paper · explained in 2 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Latent Representations — 2× in this paper · explained in 3 episodes
• Two-stage training — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Latent Reasoning — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes

Sources

• Flash-WAM: Modality-Aware Distillation for World Action Models
• eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing
• OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
• SAM3D-Guided Object-Centric Representation Alignment for Vision-Language-Action Models
• Faster-WAM: Do World Action Models Need Deep Action Modules?
• GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
• Motubrain: An Advanced World Action Model for Robot Control
• Wan: Open and Advanced Large-Scale Video Generative Models
• ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts
• Orca: The World is in Your Mind
• GigaWorld-Policy: An Efficient Action-Centered World--Action Model
• World Action Models are Zero-shot Policies
• MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Learning 4D Geometric Priors for Inference-Efficient World Action Models

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies