research
A Plausible Motion Still Used the Wrong Physics
GAUGE measures simulators and video world models against calibrated trajectories instead of judging whether their output merely looks right.
Summary
GAUGE measures simulators and video world models against calibrated trajectories instead of judging whether their output merely looks right.
GAUGE collects 22 controlled task families spanning rigid bodies, cables, textiles and volumetric deformable objects. Tests of three physics engines found no uniformly faithful system, with the largest gaps in impulsive contact, fast textile motion and volumetric deformation; six image-to-video models sometimes reproduced the expected equation form while recovering wrong acceleration, momentum transfer or oscillation timing. The results are benchmark diagnostics, not a ranking of every simulator or world model.
Why it matters
GAUGE measures simulators and video world models against calibrated trajectories instead of judging whether their output merely looks right.
Limits and context
- The results are benchmark diagnostics, not a ranking of every simulator or world model.
Key claims
GAUGE measures simulators and video world models against calibrated trajectories instead of judging whether their output merely looks right.
Qualification: The results are benchmark diagnostics, not a ranking of every simulator or world model.
Evidence: source-2026-08-07-004
Sources
- arXiv preprint 2608.05948arXiv · primary research
Corrections
No corrections have been recorded for this story.