链式世界：潜在运动中的世界模型思维
Chain of World: World Model Thinking in Latent Motion
AI总结：
CoWVLA通过统一世界模型的时间推理与解耦的潜在运动表示，提升视觉-运动学习效率。
摘要：
视觉-语言-动作（VLA）模型是实现具身智能的一种有前途的路径，但它们常常忽视了视觉动态背后的预测性和时间因果结构。世界模型VLA通过预测未来帧来解决这个问题，但浪费容量去重建冗余的背景。潜在动作VLA将帧到帧的转换紧凑地编码，但缺乏时间连续的动态建模和世界知识。为了克服这些限制，我们引入了CoWVLA（链式世界VLA），一种新的“链式世界”范式，它统一了世界模型的时间推理与解耦的潜在运动表示。首先，一个预训练的视频VAE用作潜在运动提取器，明确将视频片段分解为结构和运动潜在因素。然后，在预训练过程中，VLA从指令和初始帧推断出连续的潜在运动链并预测片段的终端帧。最后，在联合微调过程中，这种潜在动态通过联合建模稀疏关键帧和动作序列在一个统一的自回归解码器中与离散动作预测对齐。这种设计保留了世界模型的时间推理和世界知识的优势，同时保留了潜在动作的紧凑性和可解释性，使视觉-运动学习更加高效。在机器人仿真基准上的广泛实验表明，CoWVLA在现有世界模型和潜在动作方法上表现更优，并且实现了中等计算效率，突显了其作为更有效的VLA预训练范式的潜力。项目网站可以在https://fx-hit.github.io/cowvla-io找到。
英文摘要：
Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future frames, but waste capacity reconstructing redundant backgrounds. Latent-action VLAs encode frame-to-frame transitions compactly, but lack temporally continuous dynamic modeling and world knowledge. To overcome these limitations, we introduce CoWVLA (Chain-of-World VLA), a new "Chain of World" paradigm that unifies world-model temporal reasoning with a disentangled latent motion representation. First, a pretrained video VAE serves as a latent motion extractor, explicitly factorizing video segments into structure and motion latents. Then, during pre-training, the VLA learns from an instruction and an initial frame to infer a continuous latent motion chain and predict the segment's terminal frame. Finally, during co-fine-tuning, this latent dynamic is aligned with discrete action prediction by jointly modeling sparse keyframes and action sequences in a unified autoregressive decoder. This design preserves the world-model benefits of temporal reasoning and world knowledge while retaining the compactness and interpretability of latent actions, enabling efficient visuomotor learning. Extensive experiments on robotic simulation benchmarks show that CoWVLA outperforms existing world-model and latent-action approaches and achieves moderate computational efficiency, highlighting its potential as a more effective VLA pretraining paradigm. The project website can be found at https://fx-hit.github.io/cowvla-io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
