用因果潜空间建模，让机器人任务学习更高效、泛化更强。
DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
- 用DINOv3特征分离交互语义与视觉噪声，提升鲁棒性。
- 内存恒定在O(1)，推理延迟降低50%以上。
- 适合做机器人操控的高效训练与真实世界部署。
将生成式世界-动作模型用于操作任务时，受限于冗余的像素级重建、随时间线性增长的内存开销以及序列化推理延迟。我们提出因果潜空间世界模型（CLWM），采用DINOv3特征作为生成目标，分离交互语义与视觉噪声，实现高度鲁棒的域泛化。为解决内存扩展问题，引入双状态测试时训练（TTT）记忆机制，保证长时程任务下严格O(1)内存占用。为降低部署延迟，提出推测异步推理（SAI），将部分扩散去噪过程隐藏于物理执行之后，使阻塞延迟减少约50%。为提升策略可扩展性，提出EmbodiChain在线框架，通过注入无限量物理可信轨迹建立效率定律。大量实验表明，CLWM在复杂双臂仿真中达到当前最优性能，并在真实机器人上实现前所未有的零样本仿真到现实迁移，优于显式在真实数据上微调的基线方法。
原文摘要 · Abstract (English)
Deploying generative World-Action Models for manipulation is severely bottlenecked by redundant pixel-level reconstruction, $\mathcal{O}(T)$ memory scaling, and sequential inference latency. We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise, yielding highly robust domain generalization. To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $\mathcal{O}(1)$ footprint for long-horizon tasks. To overcome deployment latency, we propose Speculative Asynchronous Inference (SAI) to mask partial diffusion denoising behind physical execution, cutting blocking latency by about $50\%$. To scale robust policies, we present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training. Extensive experiments validate that CLWM achieves state-of-the-art performance in complex dual-arm simulation and unprecedented zero-shot sim-to-real transfer on physical robots, outperforming baselines explicitly finetuned on real-world data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。