EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields

arXiv:2605.06192 · cs.CV, cs.AI, cs.RO · Submitted 2026-05-07 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-05-07

Updated: 2026-09-23

Code: https://github.com/Wan-Video/Wan2.2

Terminology

• World Model — 31× in this paper · explained in 7 episodes
• Accuracy — 22× in this paper · explained in 1 episode
• Consistency — 11× in this paper · explained in 3 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Alignment — 6× in this paper · explained in 1 episode
• Benchmark — 5× in this paper · explained in 2 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 5× in this paper · explained in 6 episodes
• Action Space — 4× in this paper · explained in 1 episode
• Generative Model — 4× in this paper · explained in 2 episodes
• Latent Space — 4× in this paper · explained in 7 episodes
• Event-Difference Latent Supervision — 3× in this paper
• Fidelity — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Inverse Problem — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes

Sources

• Cosmos World Foundation Model Platform for Physical AI
• Lumiere: A Space-Time Diffusion Model for Video Generation
• Motus: A Unified Latent Action World Model
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Wan-S2V: Audio-Driven Cinematic Video Generation
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models
• Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
• SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy
• Unified Video Action Model
• WorldEval: World Model as Real-World Robot Policies Evaluator
• Video Generators are Robot Policies
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• WorldGym: World Model as An Environment for Policy Evaluation
• AVID: Adapting Video Diffusion Models to World Models
• ViPRA: Video Prediction for Robot Actions
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
• Generative Image as Action Models
• World Guidance: World Modeling in Condition Space for Action Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models