Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models
Xiang Liu, Sen Cui, Changshui Zhang
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 dist…
cs.RO2026
Scene2Demo: Self-Evolving Embodied Data Generation via Object-Action Graph
Xiang Liu, Sen Cui, Guocai Yao +4
We present Scene2Demo, a self-evolving framework for offline embodied data generation. Given a single real-world RGB image and a user query, Scene2Demo constructs an interactive si…