ConfAL-WM：面向动作条件世界模型的置信度引导主动学习框架

View PDF HTML (experimental)

Abstract:Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors under new task and scene distributions are often concentrated in localized spatiotemporal regions such as robot arms, manipulated objects, contact areas, and occluded objects. This paper presents ConfAL-WM, a confidence-guided active learning framework for post-training embodied world models. Building upon EnerVerse-AC (EVAC), we attach a lightweight confidence probe to UNet decoder features and predict dense confidence maps in the latent space. These maps are aggregated into task-, frame-, and patch-level scores, enabling data-budget allocation and localized training enhancement. Our pipeline trains the probe and warms up EVAC on a small target-domain subset. EVAC-v1 then supplies task-level acquisition and optional frame/patch weighting signals; all selected-data models are initialized from the original pretrained EVAC checkpoint for retraining. Experiments on RoboTwin2.0 at the default 40% data budget show that confidence-guided selection improves post-training quality, while dense frame and patch weighting offers complementary reconstruction and semantic gains compared with scalar reward, progress, and judge-based scoring baselines. A quick visual overview of this work is available at this https URL.

Comments:	Project page: this https URL
Subjects:	Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2608.25572 [cs.RO]
	(or arXiv:2608.25572v2 [cs.RO] for this version)
	https://doi.org/10.48550/arXiv.2608.25572 arXiv-issued DOI via DataCite

Submission history

From: Xiang Liu [view email]
[v1] Wed, 26 Aug 2026 09:29:08 UTC (5,411 KB)
[v2] Fri, 2 Oct 2026 06:33:57 UTC (6,331 KB)