Spatial-UMI-Dream: Scaling World Action Models with Metric Geometry for UMI Manipulation
cs.RO
Submitted: 2026-11-04
Updated: 2026-11-04
Project page: https://weiduoyuan.com/spatial-umi-dream
Terminology
Sources
- Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- $\Psi_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation
- RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
- OpenVLA: An Open-Source Vision-Language-Action Model
- World Action Models are Zero-shot Policies
- Cosmos 3: Omnimodal World Models for Physical AI
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
- ${\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities
- DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models
- ForeAct: Steering Your VLA with Efficient Visual Foresight Planning
- 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
- ICLR: In-Context Imitation Learning with Visual Reasoning
- 3D-VLA: A 3D Vision-Language-Action Generative World Model
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
- ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
- Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
- SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation