WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning

arXiv:2607.18840 · cs.RO · Submitted 2026-07-21 · Read on arXiv

cs.RO

Submitted: 2026-07-21

Updated: 2026-09-20

Project page: https://manifoldai-research.github.io/WorldScape-Policy

Terminology

• Benchmark — 19× in this paper · explained in 2 episodes
• Adaptation — 12× in this paper · explained in 1 episode
• World Action Model — 12× in this paper
• Grounding — 11× in this paper · explained in 3 episodes
• World Model — 10× in this paper · explained in 7 episodes
• Cross-Embodiment Transfer — 6× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Generalization — 5× in this paper · explained in 13 episodes
• Latent Reasoning — 5× in this paper · explained in 2 episodes
• Trace — 5× in this paper · explained in 2 episodes
• In-Context Learning — 4× in this paper · explained in 4 episodes
• Action Space — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Computer Vision and Pattern Recognition — 3× in this paper
• Flow Matching — 3× in this paper · explained in 7 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Multimodal Dataset — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Action Decoder — 2× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptive Planning — 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
• Core — 1× in this paper · explained in 2 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Distillation — 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 Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• KV cache — 1× in this paper · explained in 3 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes
• World Action Model (WAM) — 1× in this paper · explained in 3 episodes

Sources

• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
• ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
• Fast-WAM: Do World Action Models Need Test-time Future Imagination?
• Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
• GigaWorld-Policy: An Efficient Action-Centered World--Action Model
• World Action Models are Zero-shot Policies
• MemoryWAM: Efficient World Action Modeling with Persistent Memory
• Vidar: Embodied Video Diffusion Model for Generalist Manipulation
• TSI: Temporal Saliency Integration for Video Action Recognition
• Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
• Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
• DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• GigaWorld-0: World Models as Data Engine to Empower Embodied AI
• OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
• MEM: Multi-Scale Embodied Memory for Vision Language Action Models
• Long-Horizon Manipulation via Trace-Conditioned VLA Planning
• Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
• DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation
• NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planning

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