UMR: Universal Manipulation Representation

arXiv:2609.34256 · cs.RO · Submitted 2026-09-28 · Read on arXiv

cs.RO

Submitted: 2026-09-28

Updated: 2026-10-03

Project page: https://umr-wepvla.github.io

Terminology

• Generalization — 10× in this paper · explained in 13 episodes
• Point Clouds — 10× in this paper · explained in 2 episodes
• Action Space — 7× in this paper · explained in 1 episode
• Benchmark — 6× in this paper · explained in 2 episodes
• Affordance — 5× in this paper · explained in 1 episode
• Universal Manipulation Representation — 5× in this paper
• Alignment — 4× in this paper · explained in 1 episode
• Data-Efficient Strategy — 4× in this paper
• Transformer — 3× in this paper · explained in 2 episodes
• 9D Pose — 2× in this paper · explained in 1 episode
• Foundation Model — 2× in this paper · explained in 3 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cross-Embodiment Transfer — 1× in this paper · explained in 2 episodes
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Flow Matching — 1× in this paper · explained in 8 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes

Sources

• OpenVLA: An Open-Source Vision-Language-Action Model
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• WorldVLA: Towards Autoregressive Action World Model
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models
• RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
• FastUMI-100K: Advancing Data-driven Robotic Manipulation with a Large-scale UMI-style Dataset
• HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
• PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies
• Ego4D: Around the World in 3,000 Hours of Egocentric Video
• Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
• EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
• EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
• Human Universal Grasping
• EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
• Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

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