Opinion: Learning Intuitive Physics May Require More than Visual Data

• URL: http://arxiv.org/abs/2512.06232v1
• Date: Sat, 06 Dec 2025 00:49:41 GMT
• Title: Opinion: Learning Intuitive Physics May Require More than Visual Data
• Authors: Ellen Su, Solim Legris, Todd M. Gureckis, Mengye Ren,
• Abstract summary: State-of-the-art deep learning models still fall short of human-level performance on intuitive physics benchmarks.<n>We pretrain a Video Joint Embedding Predictive Architecture (V-JEPA) model on SAYCam, a developmentally realistic, egocentric video dataset.<n>We find that training on this dataset, which represents 0.01% of the data volume used to train SOTA models, does not lead to significant performance improvements on the IntPhys2 benchmark.
• Score: 9.35132037029056
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet video data, state-of-the-art deep learning models still fall short of human-level performance on intuitive physics benchmarks. This work investigates whether data distribution, rather than volume, is the key to learning these principles. We pretrain a Video Joint Embedding Predictive Architecture (V-JEPA) model on SAYCam, a developmentally realistic, egocentric video dataset partially capturing three children's everyday visual experiences. We find that training on this dataset, which represents 0.01% of the data volume used to train SOTA models, does not lead to significant performance improvements on the IntPhys2 benchmark. Our results suggest that merely training on a developmentally realistic dataset is insufficient for current architectures to learn representations that support intuitive physics. We conclude that varying visual data volume and distribution alone may not be sufficient for building systems with artificial intuitive physics.

Related papers

• PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis [52.905353023326306]
  We propose PhysWorld, a framework that synthesizes physically plausible and diverse demonstrations to learn efficient world models.<n>Experiments show that PhysWorld has competitive performance while enabling inference speeds 47 times faster than the recent state-of-the-art method, i.e., PhysTwin.
  arXiv  Detail & Related papers  (2025-10-24T13:25:39Z)
• LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference [57.086932851733145]
  We introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models.<n>We benchmark intuitive physics understanding in current video diffusion models.<n> Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.
  arXiv  Detail & Related papers  (2025-10-13T15:19:07Z)
• PhysiX: A Foundation Model for Physics Simulations [27.359872113159405]
  We introduce PhysiX, the first large-scale foundation model for physics simulation.<n>We show that PhysiX effectively addresses the data bottleneck, outperforming task-specific baselines.<n>Our results indicate that knowledge learned from natural videos can be successfully transferred to physics simulation.
  arXiv  Detail & Related papers  (2025-06-21T18:10:12Z)
• FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity [15.375932203870594]
  We aim to model 3D scene geometry, appearance, and the underlying physics purely from multi-view videos.<n>In this paper, we propose FreeGave to learn the physics of complex dynamic 3D scenes without needing any object priors.
  arXiv  Detail & Related papers  (2025-06-09T15:31:25Z)
• Scaling Physical Reasoning with the PHYSICS Dataset [39.960500815534836]
  PHYSICS is a dataset containing 16,568 high-quality physics problems spanning subjects and difficulty levels.<n>It covers five major physics domains: Mechanics, Electromagnetism, Thermodynamics, Optics, and Modern Physics.<n>It also spans a wide range of difficulty levels, from high school to graduate-level physics courses.
  arXiv  Detail & Related papers  (2025-05-21T17:06:28Z)
• The Sound of Water: Inferring Physical Properties from Pouring Liquids [85.30865788636386]
  We study the connection between audio-visual observations and the underlying physics of pouring liquids.<n>Our objective is to automatically infer physical properties such as the liquid level, the shape and size of the container, the pouring rate and the time to fill.
  arXiv  Detail & Related papers  (2024-11-18T01:19:37Z)
• Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video [58.043569985784806]
  We introduce latent intuitive physics, a transfer learning framework for physics simulation. It can infer hidden properties of fluids from a single 3D video and simulate the observed fluid in novel scenes. We validate our model in three ways: (i) novel scene simulation with the learned visual-world physics, (ii) future prediction of the observed fluid dynamics, and (iii) supervised particle simulation.
  arXiv  Detail & Related papers  (2024-06-18T16:37:44Z)
• 3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes [68.66237114509264]
  We present a framework capable of learning 3D-grounded visual intuitive physics models from videos of complex scenes with fluids. We show our model can make long-horizon future predictions by learning from raw images and significantly outperforms models that do not employ an explicit 3D representation space.
  arXiv  Detail & Related papers  (2023-04-22T19:28:49Z)
• Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language [92.7638697243969]
  We propose a unified framework that can jointly learn visual concepts and infer physics models of objects from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
  arXiv  Detail & Related papers  (2021-10-28T17:59:13Z)

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.