DriftWorld 能让机器人快速想象动作结果，比扩散模型快 17 倍，还能离线评估策略，性能强又省时。
DriftWorld 是一种动作条件的世界模型，通过训练中学习动作条件漂移，在单个前向传播中生成未来帧，速度达 30+ fps。相比扩散模型基线，平均推理速度提升 17 倍。在 Bridge-V2、RT-1、Language Table、Push-T、Robomimic 等机器人操控基准上，DriftWorld 以更少推理时间实现 SOTA 决策性能。它还可作为离线模拟器，用于排序真实机器人策略，滚动得分与真实结果相关性高达 0.99。
DriftWorld: Fast World Modeling through Drifting
Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world models: multistep sampling makes each rollout expensive, limiting large-scale action search at inference time. We introduce DriftWorld, an action-conditioned world model based on drifting generative models. Rather than denoising iteratively at inference, DriftWorld learns an action-conditioned drift during training, allowing it to generate future frames from the current observation and a candidate action sequence in a single forward pass at 30+ fps, which is 17x faster on average than diffusion based baselines. We evaluate DriftWorld on standard vision-based robotic manipulation benchmarks, including Bridge-V2, RT-1, Language Table, Push-T, and Robomimic. By producing rollouts that are both accurate and fast, DriftWorld achieves state-of-the-art decision-making performance with far less inference time than diffusion-based world model baselines. Beyond online control, DriftWorld can also serve as an offline simulator for ranking real-world robot policies, with rollout-based scores correlating with ground truth at up to 0.99. These results show that drifting models are a strong fit for robot world modeling, where fast, high-quality imagination directly supports planning and policy evaluation.