发表机构
Tel Aviv University; Meta AI（特拉维夫大学; Meta AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对线缆动力学预测问题，提出带物理注意力偏置的学习型模拟器，通过对比不同偏置设置，发现将弧长与欧氏距离分配给不同注意力头的方案表现最优，可提升未见过线缆的预测精度。
AI 中文摘要
针对线缆等可变形线性物体（DLO）的学习型模拟器，需预测未训练过的线缆运动并在长序列滚动中保持稳定，其误差多出现于线缆与自身或地面接触处。对所有线缆段对施加注意力可表示沿线缆长度方向相距较远的部件间接触，但注意力缺乏几何概念。线缆存在两种成对距离，仅在其伸直时一致：沿线缆的弧长距离（决定弹性力）与空间欧氏距离（决定接触）。我们添加物理注意力偏置——注意力 logits 上的附加项，带有学习得到的比率，并探究其应使用哪种距离。我们对比无偏置、单独使用每种距离、以及在不相交的注意力头集合上使用两种距离的情况，其余模型与训练协议保持固定。物理偏置可提升对未见过线缆的预测效果，当注意力是连接远距段的唯一机制时，提升最大：此时弧长偏置可将预测误差降低15%以上，并将段长漂移减半以上；单独使用欧氏偏置的表现接近无偏置注意力；而在我们报告的所有指标上，将两种距离分配给不同注意力头的表现最佳或接近最佳。代码与各次运行记录见：this https URL。
英文摘要
Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of their error occurs where the cable touches itself or the floor. Attention over all pairs of cable segments can represent contact between parts of the cable that are far apart along its length, but attention has no notion of geometry. A cable has two pairwise distances, which agree only while it is straight: the arc-length distance along the cable, which governs elastic forces, and the Euclidean distance in space, which governs contact. We add a physical attention bias, an additive term on the attention logits with a learned rate, and ask which distance it should use. We compare no bias, each distance alone, and both distances on disjoint sets of heads, keeping the rest of the model and the training protocol fixed. A physical bias improves prediction on unseen cables. The gain is largest when attention is the only mechanism that connects distant segments: there, the arc-length bias reduces prediction error by 15% and more than halves the drift in segment length. The Euclidean bias alone stays close to unbiased attention, while assigning both distances across heads is best or near-best on every metric we report. Code and per-run records: https://github.com/avihaig/dlogps.
Journal refNeurIPS 2026 Workshop - Symmetry and Geometry in Neural Representations
