Skip to content

UMR: Universal Manipulation Representation

Sep 2026 · arXiv.org · Vol abs/2609.34256 · 0 citations · 45 references
Computer Science

TL;DR

This work introduces Universal Manipulation Representation (UMR), a unified action representation that enables zero-shot skill transfer from human demonstrations to heterogeneous robots and complements it with a Data-Efficient Strategy (DES) that diversifies object configurations through stage-aware point-cloud editing while preserving demonstrated contact geometry.

Abstract

General-purpose embodied manipulation hinges on a unified action representation that generalizes across embodiments and scales readily. Yet existing policies rely on embodiment-specific action spaces, making cross-embodiment demonstrations difficult to leverage at scale and limiting transfer to new embodiments and spatial variations. To this end, we introduce Universal Manipulation Representation (UMR), a unified action representation that enables zero-shot skill transfer from human demonstrations to heterogeneous robots. UMR decomposes manipulation into two functionally distinct yet geometrically linked components: embodiment-agnostic World Flow, which describes task-relevant object motion in the world frame, and Ego Trajectory, which represents end-effector motion relative to the current pose. We instantiate UMR as World--Ego Point VLA (WEPVLA), a compact 0.5B-parameter policy that learns in the unified geometric action space through a dual-stream Point Action Adapter and a unified Point Action Expert, with an $SE(3)$ conjugation coupling the two components. To improve data efficiency, we complement UMR with a Data-Efficient Strategy (DES) that diversifies object configurations through stage-aware point-cloud editing while preserving demonstrated contact geometry. In simulation, WEPVLA achieves average success rates of 97.5\% on LIBERO and 85.7\% on the 10-task RLBench benchmark. In real-world experiments, a single policy trained on human demonstrations augmented by DES transfers zero-shot to diverse deployment conditions. With about 10 minutes of collected human demonstrations per task and no robot demonstrations, it achieves 91.7\% average success across six evaluation settings, compared with 60.8\% for HumanEgo. Code and additional materials are available at https://umr-wepvla.github.io/.

View source

Similar papers

Sep 2026

SkelWAM: A Skeleton-Guided World-Action Model for Zero-Shot Cross-Embodiment Manipulation

This work presents SkelWAM, a skeleton-guided world-action model that couples perception and control through one explicit geometric representation for single-source cross-embodiment manipulation, and introduces LIBERO-Cross10, a source-only cross-embodiment transfer benchmark covering ten tasks and ten target embodimen...

Pengbo Niu, Yu-Jia Xie, Rui Peng et al. · 0 citations
Sep 2026

UMI-Bridge: Action-Anchored Latent Alignment across Human and Robot Manipulation Data

UMI-Bridge, which uses UMI as an intermediate domain to align representations according to action equivalence rather than pixel similarity, supports action-anchored latent alignment for data-efficient robot learning and UMI-to-robot task transfer.

Hai-Yi Liu, Jin-Ming Ma, Ke Rui et al. · 0 citations
Preprint Nov 2026

CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation

Robot demonstrations contain reusable manipulation knowledge, but transferring this knowledge across embodiments requires representations that bridge differences in control interfaces. Action reconstruction alone does not ensure that similar behaviors across robots share a representation. To address this gap, we introd...

Choo Sin Wai, Da-Ke Zhong, Jing-Ye Zhang et al. · 0 citations
Preprint Oct 2026

Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

World models enable embodied agents to anticipate action consequences, yet jointly modeling locomotion and manipulation across diverse embodiments remains challenging due to heterogeneous action spaces and limited multimodal supervision. We present Ropedia W0, the first egocentric loco-manipulation world foundation mod...

Tian-Qi Liu, Han-Fei Zhao, Qin Liang et al. · 0 citations
Preprint Oct 2026

EXE: Egocentric Cross-Embodiment Pretraining via Factorized Latent Actions for VLA Models

Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos offer an abundant, diverse, and semantically-rich alternative that inherently captures manipulation intent. However, the embodiment gap makes it difficult to extract action-relevant representations f...

Qing-Yuan Cai, Bo Zhang, Yong-Zhen Huang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.