An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM

arXiv:2609.25961 · cs.RO · Submitted 2026-09-22 · Read on arXiv

cs.RO

Submitted: 2026-09-22

Updated: 2026-09-22

Project page: https://research.nvidia.com/labs/gear

Terminology

• Transformer — 28× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Generalization — 10× in this paper · explained in 13 episodes
• Foundation Model — 6× in this paper · explained in 3 episodes
• Latent Space — 5× in this paper · explained in 7 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Robustness — 4× in this paper · explained in 5 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Flow Matching — 3× in this paper · explained in 8 episodes
• LoRA Adapters — 3× in this paper · explained in 3 episodes
• Action Flow — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Tokenization — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Rectified Flow — 1× in this paper · explained in 3 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
• Masked Visual Actions for Unified World Modeling
• Qwen3-VL Technical Report
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing
• Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
• WorldVLA: Towards Autoregressive Action World Model
• Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis
• LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
• ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models
• GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
• Emu3.5: Native Multimodal Models are World Learners
• Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
• Emerging Properties in Unified Multimodal Pretraining
• AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps
• GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving