Paper page - World Value Models for Robotic Manipulation

Source: https://huggingface.co/papers/2606.24742

Abstract

World Value Model combines world models with value estimation to provide accurate task progression assessment and improve robotic policy learning from mixed-quality data.

Generalist value models play a pivotal role in scalingrobotic policy learningfrom large-scale, mixed-quality data. Mathematically, accuratevalue estimationdemands deep temporal understanding, requiring models to both ground the current belief using historical context and plan over future outcomes. However, most existing robotic value models are built onVision-Language Model(VLM) backbones that are pretrained primarily on static or temporally sparse visual observations, lacking the requisitetemporal modelingcapabilities forvalue estimation. Unlike VLMs,world modelsnaturally excel attemporal modelingand future planning, making them ideal foundations for learning generalizablevalue functions. Driven by this insight, we marryworld modelswithvalue estimationto construct a new generalist robotic value model, World Value Model (WVM), that offers accurate task progressions to assess data quality. On standard benchmarks, WVM delivers state-of-the-art (SOTA)Value-Order Correlation(VOC) results. Complementing standard evaluation suites that contains only expert data, we further introduceSuboptimal-Value-Bench, a multi-embodiment benchmark consisting of 800 suboptimal trajectories with high-fidelity, human-labeled frame annotations. Our evaluations show that WVM maintains its SOTA performance onSuboptimal-Value-Bench, establishing its robustness in handling both expert and suboptimal data. When deployed forpolicy learning, WVM improves manipulation performance across various policy extraction approaches in both simulated and real-world deployment, providing robust guidance for learning from mixed-quality data.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.24742 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.24742 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.24742 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.