GeoPhys: The Geometry of Physical Plausibility

C Internò, A Pondaven, H Issa, F Pizzati, F Pinto, M Olhofer, I Laptev, P Torr, E P Simoncelli, B Hammer and D Klindt.

arXiv.org e-prints, Technical Report , Jun 2026.

DOI: 10.48550/arXiv.2606.20707

This paper has been superseded by:
GeoPhys: The Geometry of Physical Plausibility
C Internò, A Pondaven, H Issa, F Pizzati, F Pinto, M Olhofer, I Laptev, P Torr, E P Simoncelli, B Hammer and D Klindt.
Adv. Neural Information Processing (NeurIPS), vol.39 Dec 2026. To appear


Download:

  • Reprint (pdf)
    • While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either rely on external multimodal-LLM judges or require ad-hoc modifications to the training procedure. In this work, we argue that indicators of physical plausibility are implicitly captured by five geometric properties of the per-frame embeddings produced by frozen image encoders. In aggregate, we call them GEOPHYS. First, we show that these signals correlate with human EEG responses to two forms of object-permanence violations. Second, GEOPHYS robustly discriminates physically implausible videos from realistic ones, achieving state-of-the-art physics-violation detection: 98.3% on LikePhys and 93.3% on IntPhys2, whereas V-JEPA 2, GPT-4o, Gemini, and twelve modern video diffusion models perform near chance. Third, used as a best-of-N verifier for physical alignment during video generation, GEOPHYS lifts MAGI-1 24B from 50.01% to 64.50% on PhysicsIQ at 1.5x lower wall-clock and 4.65x lower memory than the V-JEPA 2 world-model verifier. Ultimately, GEOPHYS demonstrates that physical plausibility in videos can be assessed by leveraging the emergent geometric properties of temporal features extracted from image encoders.
  • Listing of all publications