CUTEPKQ / NEWTON

What it does

Video generation models produce visually compelling results but systematically violate physical commonsense — on VideoPhy-2, the best model achieves only 32.6% joint accuracy. We identify a specification bottleneck: text prompts are a lossy compression of the physical world, omitting the parameters that fully determine dynamics, and no amount of model scaling can recover what was never specified. From this diagnosis we derive three properties that physics conditioning must satisfy — sufficiency, dynamism, and verifiability — and show that no existing approach satisfies all three.