Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now

• URL: http://arxiv.org/abs/2512.02016v1
• Date: Mon, 01 Dec 2025 18:59:56 GMT
• Title: Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
• Authors: Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan, Anand Bhattad,
• Abstract summary: Video generators are increasingly evaluated as potential world models.<n>We investigate their representation of a fundamental law: gravity.<n>A lightweight low-rank adaptor fine-tuned on only 100 single-ball clips raises $g_mathrmeff$ from $1.81,mathrmm/s2$ to $6.43,mathrmm/s2$ (reaching $65% of terrestrial gravity).
• Score: 10.272466104440381
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards [49.02795965814016]
  Video diffusion models can synthesize visually compelling clips, yet often violate basic physical laws-objects float, accelerations drift, and collisions behave inconsistently-revealing a persistent gap between visual realism and physical realism.<n>We propose $textttNewtonRewards$, the first physics-grounded post-training framework for video generation based on $textitverifiable rewards$.
  arXiv  Detail & Related papers  (2025-11-29T10:04:50Z)
• TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility [70.24211591214528]
  Video generative models produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morphing.<n>Existing Video-Language Models (VLMs) struggle to identify physics violations, exposing fundamental limitations in their temporal and causal reasoning.<n>We introduce TRAVL, a fine-tuning recipe that combines a balanced training dataset with a trajectory-aware attention module to improve motion encoding.<n>We propose ImplausiBench, a benchmark of 300 videos (150 real, 150 generated) that removes linguistic biases and isolates visual-temporal understanding.
  arXiv  Detail & Related papers  (2025-10-08T21:03:46Z)
• Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility [37.011366226968]
  Diffusion models can generate realistic videos, but existing methods rely on implicitly learning physical reasoning from large-scale text-video datasets.<n>We introduce a training-free framework that improves physical plausibility at inference time by explicitly reasoning about implausibility and guiding the generation away from it.
  arXiv  Detail & Related papers  (2025-09-29T12:32:54Z)
• Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation [54.42523027597904]
  We introduce a novel framework that integrates symbolic regression and trajectory-guided image-to-video (I2V) models for physics-grounded video forecasting.<n>Our approach extracts motion trajectories from input videos, uses a retrieval-based pre-training mechanism to enhance symbolic regression, and discovers equations of motion to forecast physically accurate future trajectories.
  arXiv  Detail & Related papers  (2025-07-09T13:28:42Z)
• The path towards measuring the gravitational field of proton bunches at accelerators [0.6530047924748278]
  The intense ultra-relativistic proton beam in the LHC storage ring offers the potential to test general relativity.<n>The present document summarizes the status of the theoretical studies in this direction.
  arXiv  Detail & Related papers  (2025-04-15T07:45:35Z)
• How Far is Video Generation from World Model: A Physical Law Perspective [101.24278831609249]
  OpenAI's Sora highlights the potential of video generation for developing world models that adhere to physical laws.<n>But the ability of video generation models to discover such laws purely from visual data without human priors can be questioned.<n>In this work, we evaluate across three key scenarios: in-distribution, out-of-distribution, and generalization.
  arXiv  Detail & Related papers  (2024-11-04T18:53:05Z)
• Testing the nonclassicality of gravity with the field of a single delocalized mass [55.2480439325792]
  A setup is proposed that is based on a single delocalized mass coupled to a harmonically trapped test mass. We investigate the in-principle feasibility of such an experiment, which turns out to crucially depend on the ability to tame Casimir-Polder forces.
  arXiv  Detail & Related papers  (2023-07-18T15:40:16Z)
• Probing Modified Gravity with Entanglement of Microspheres [2.097217735462665]
  We show that two nearby mesoscopic quantum masses accumulate significantly larger entanglement in modified gravity models. Our calculations include Casimir-Polder forces as well as tidal effects next to the surface of the earth.
  arXiv  Detail & Related papers  (2023-06-26T15:38:55Z)
• Machine-Learning Non-Conservative Dynamics for New-Physics Detection [69.45430691069974]
  Given a trajectory governed by unknown forces, our Neural New-Physics Detector (NNPhD) aims to detect new physics. We demonstrate that NNPhD successfully discovers new physics by decomposing the force field into conservative and non-conservative components. We also show how NNPhD coupled with an integrator outperforms previous methods for predicting the future of a damped double pendulum.
  arXiv  Detail & Related papers  (2021-05-31T18:00:10Z)
• Gravitational decoherence of photons [0.0]
  We generalize the gravitational decoherence model of Anastopoulos and Hu to photons. We find that interference experiments with long baselines, accessible in near-future experiments, can, in principle, lead to strong constraints in $Theta$.
  arXiv  Detail & Related papers  (2020-11-16T20:53:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.