IMPULSE：在V-JEPA 2特征空间中先推动再预测
IMPULSE: Push First, Then Predict in V-JEPA 2 Feature Space
AI总结：
IMPULSE为V-JEPA 2特征空间的预测器加入贝叶斯接触记忆等模块，在多组物体实验中显著降低特征预测误差，提升了潜在世界模型的物理感知能力。
摘要：
潜在世界模型（如V-JEPA 2）会在视频编码器的特征空间中进行预测，但仅观察物体无法得知其旋转难度、弹跳量或滑动量。人类通过尝试来获取这些信息：几次轻推就能揭示物体的响应特性。IMPULSE以其推断的脉冲响应命名，它为冻结的V-JEPA 2特征空间中的预测器赋予了相同的能力。该方法包含三个关键部分：贝叶斯接触记忆模块，用于汇总三次短暂的校准推动；预测的物体位姿，将其输入预测器；轻量级随机傅里叶位姿头，使预测器能够利用位姿信息。在512个新物体上，采用预先指定的保留确认集（模型在数据存在前已密封）的实验中，对于全部8个训练随机种子，该记忆模块使1秒特征预测误差相比无经验的相同预测器降低了11.6%-12.8%，95%的种子-物体区间不包含零值。该增益在128个物理特性超出范围的物体上同样成立（11.7%-14.0%），完整扩展版本的性能比普通预测器高出15.5%-16.6%。基于信息阶梯论证（对理想预测器精确成立）可知，物理特性仅通过运动传递到特征，因此我们测量该通路中位姿的帮助程度。在新物体上，傅里叶头使完美记忆相比普通位姿标记的增益大致增加两倍（2.8-3.2倍）。通过相同通路输入的原始推动测量值也能产生类似增益，说明贝叶斯汇总并非必需，其仅将试验浓缩为8个可解释的数值。该增益在接触开始时不存在，之后逐渐增长。
英文摘要：
Latent world models such as V-JEPA 2 forecast in the feature space of a video encoder, but one look at an object does not reveal how hard it is to rotate, how much it bounces or how much it slides. People find out by trying: a few pokes reveal how an object responds. IMPULSE, named after the impulse response it infers, gives a predictor in frozen V-JEPA 2 feature space the same ability. A Bayesian contact memory summarizes three short calibration pushes, a predicted object pose carries it into the predictor, and a lightweight random-Fourier pose head lets the predictor use the pose. On 512 fresh objects, in a pre-specified held-out confirmation with models sealed before the data existed, the memory lowers the 1-second feature-forecast error by 11.6-12.8% relative to the same predictor without experience, for all 8 training seeds, with a 95% seed-and-object interval excluding zero. The gain also holds for 128 objects with out-of-range physics (11.7-14.0%), and the full extension beats a plain predictor by 15.5-16.6%. An information-ladder argument, exact for ideal predictors, shows that physics reaches the features only through motion, so we measure how much the pathway lets pose help. On fresh objects, the Fourier head roughly triples the gain of a perfect memory over plain pose tokens (2.8-3.2 times). Raw push measurements fed through the same pathway give a similar gain, so the Bayesian summary is not required; it condenses the trials into eight interpretable numbers. The gain is absent at contact onset and grows afterwards.
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。
