AI 中文总结
研究针对世界动作模型依赖像素级视频生成的瓶颈，提出LeapBot-WA，通过预测性潜在对齐建立新范式，引入ISAE弥合模态差距，设计MoT架构，在多数据集上表现出色，实现高效强大的潜在中心范式及零样本鲁棒性和现实世界迁移。
AI 中文摘要
世界动作模型（WAMs）已成为具身智能的强大范式，但对像素级视频生成的普遍依赖造成了根本瓶颈。强迫模型重建与任务无关的视觉细节会消耗表征能力，使策略易受视觉干扰。本文提出LeapBot-WA，通过将联合嵌入预测架构（JEPA）作为世界锚定来建立一种新的预测性潜在范式。它将世界建模核心转向预测语义对齐，在潜在基础空间中直接提取抽象物理动力学。为弥合非高斯预测特征与扩散先验之间的模态差距，引入各向同性语义自动编码器（ISAE）。还设计了非对称混合变压器（MoT）架构。训练时，锚定扩散变压器指导动作扩散变压器；推理时修剪重动力学分支。LeapBot-WA在LIBERO上的预测模型中取得了领先性能，在RoboTwin 2.0上与顶级生成式WAMs相当，无需大规模轨迹预训练，还展示了对未知环境的卓越零样本鲁棒性和成功的现实世界迁移，为可扩展机器人控制建立了高效且强大的以潜在为中心的范式。
英文摘要
World Action Models (WAMs) have emerged as a powerful paradigm for embodied intelligence, yet the prevailing reliance on pixel-level video generation creates a fundamental bottleneck. Forcing models to reconstruct task-irrelevant visual details dissipates representational capacity and renders policies vulnerable to visual distractors. In this paper, we propose LeapBot-WA, which establishes a novel Predictive-Latent paradigm for WAMs by operationalizing the Joint-Embedding Predictive Architecture (JEPA) as a World-Anchor. Departing from the traditional reliance on visual synthesis, LeapBot-WA shifts the core of world modeling to Predictive Semantic Alignment, extracting abstract physical dynamics directly within a latent foundation space. To bridge the modality gap between non-Gaussian predictive features and diffusion priors, we introduce the Isotropic Semantic Autoencoder (ISAE), which reshapes the anchor's latent space into a diffusion-friendly manifold to prevent off-manifold drift. Furthermore, we design an Asymmetric Mixture-of-Transformers (MoT) architecture. During training, an Anchor Diffusion Transformer acts as a privileged dynamics expert to guide the Action Diffusion Transformer; at inference, this heavy dynamics branch is pruned, enabling zero-overhead execution. LeapBot-WA achieves state-of-the-art performance among predictive models on LIBERO and matches top-tier generative WAMs on RoboTwin 2.0 without requiring large-scale trajectory pre-training. It further demonstrates superior zero-shot robustness to unseen environments and successful real-world transfer, establishing a highly efficient and robust latent-centric paradigm for scalable robotic control. Code: https://github.com/LeapWM/leapbot-wa.
