Abstract
We present a vision-action policy that won 1st place in the 2025 BEHAVIOR Challenge - a large-scale benchmark featuring 50 diverse long-horizon household tasks in photo-realistic simulation, requiring bimanual manipulation, navigation, and context-aware decision making. Building on the Pi0.5 architecture, we introduce several innovations. Our primary contribution is correlated noise for flow matching, which improves training efficiency and enables correlation-aware inpainting for smooth action sequences. We also apply learnable mixed-layer attention and System 2 stage tracking for ambiguity resolution. Training employs multi-sample flow matching to reduce variance, while inference uses action compression and challenge-specific correction rules. Our approach achieves 26% q-score across all 50 tasks on both public and private leaderboards.
Abstract (translated)
我们提出了一种视觉动作策略，该策略在2025年BEHAVIOR挑战赛中荣获第一名。这项大型基准测试包括了50个多样化的长期家庭任务，在高度逼真的模拟环境中进行，需要双手操作、导航以及情境感知决策能力。基于Pi0.5架构，我们引入了几项创新： 我们的主要贡献是相关噪声的流量匹配技术，这提高了训练效率，并且使情境感知插值成为可能，从而产生了流畅的动作序列。此外，我们还应用了可学习混合层注意力和System 2阶段跟踪来解决模棱两可的情况。 在训练过程中，我们采用多样本流匹配以减少方差，而在推理时则使用动作压缩以及特定挑战的校正规则。我们的方法在公开和私有排行榜的所有50个任务中都获得了26%的q-score分数。
URL
https://arxiv.org/abs/2512.06951
