生成视频中的物体比看起来更慢：模型遭受次地球重力并目前还不知道伽利略原理...
Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
AI总结：
研究发现视频生成器在重力表示上存在偏差，通过针对性适配可提升其重力模拟精度。
摘要：
视频生成器正越来越多地被评估为潜在的世界模型，这要求它们能够编码和理解物理定律。我们研究了它们对一个基本定律：重力的表示。即开即用的视频生成器一致地生成物体以有效更慢的加速度下落。然而，这些物理测试常常被模糊的度量尺度所混淆。我们首先调查观察到的物理误差是否是这些模糊性（例如错误的帧率假设）的产物。我们发现即使时间重新缩放也无法纠正高方差的重力误差。为了严格隔离底层的物理表示这些干扰，我们引入了一个无单位、两物体协议，测试时间比率 t1²/t2² = h1/h2，一个与 g、焦距和尺度无关的关系。这种相对测试揭示了伽利略等价原理的违反。然后我们证明这种物理差距可以部分通过针对性的专业化来缓解。一个轻量级低秩适配器仅在100个单球视频上进行微调，将 g_eff 从 1.81 m/s² 提高到 6.43 m/s²（达到地球重力的65%）。这个专业适配器还能泛化到两球下落和斜面，提供了初步证据，表明特定的物理定律可以用少量数据进行修正。
英文摘要：
Video generators are increasingly evaluated as potential world models, which requires them to encode and understand physical laws. We investigate their representation of a fundamental law: gravity. Out-of-the-box video generators consistently generate objects falling at an effectively slower acceleration. However, these physical tests are often confounded by ambiguous metric scale. We first investigate if observed physical errors are artifacts of these ambiguities (e.g., incorrect frame rate assumptions). We find that even temporal rescaling cannot correct the high-variance gravity artifacts. To rigorously isolate the underlying physical representation from these confounds, we introduce a unit-free, two-object protocol that tests the timing ratio $t_1^2/t_2^2 = h_1/h_2$, a relationship independent of $g$, focal length, and scale. This relative test reveals violations of Galileo's equivalence principle. We then demonstrate that this physical gap can be partially mitigated with targeted specialization. A lightweight low-rank adaptor fine-tuned on only 100 single-ball clips raises $g_{\mathrm{eff}}$ from $1.81\,\mathrm{m/s^2}$ to $6.43\,\mathrm{m/s^2}$ (reaching $65\%$ of terrestrial gravity). This specialist adaptor also generalizes zero-shot to two-ball drops and inclined planes, offering initial evidence that specific physical laws can be corrected with minimal data.
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。
