Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

著者: Liao, Yue, Zhou, Pengfei, Huang, Siyuan, Yang, Donglin, Chen, Shengcong, Jiang, Yuxin, Hu, Yue, Cai, Jingbin, Liu, Si, Luo, Jianlan, Chen, Liliang, Yan, Shuicheng, Yao, Maoqing, Ren, Guanghui - arXiv 2025 被引用: 83

We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-generative framework. At its core, GE-Base is a large-scale, instruction-conditioned video diffusion model that captures the spatial, temporal, and semantic dynamics of real-world robotic interactions in a structured latent space. Built upon this foundation, GE-Act maps latent representations to executable action trajectories through a lightweight, flow-matching decoder, enabling precise and generalizable policy inference across diverse embodiments with minimal supervision. To support scalable evaluation and training, GE-Sim serves as an action-conditioned neural simulator, producing high-fidelity rollouts for closed-loop policy development. The platform is further equipped with EWMBench, a standardized benchmark suite measuring visual fidelity, physical consistency, and instruction-action alignment. Together, these components establish Genie Envisioner as a scalable and practical foundation for instruction-driven, general-purpose embodied intelligence. All code, models, and benchmarks will be released publicly.