SyncAI.news, a Varaisys broadcasting
What One Sample Cannot See: Why Fewer Denoising Steps Can Score Higher on Physics Benchmarks
YL

Yutao Li, Chen Wang

· 1 min read

ResearcharXiv cs.CV

What One Sample Cannot See: Why Fewer Denoising Steps Can Score Higher on Physics Benchmarks

arXiv:2611.25632v1 Announce Type: new Abstract: When a storm can head north or south, a forecast down the middle may score better under squared error than either plausible path. The same paradox appears when video generators are tested as world models: fewer denoising steps can raise physics scores even as videos blur or stop moving early. Why? Physics-IQ compares each generated video with one recording, although a scene can have multiple valid futures. An exact decomposition shows its scores can reward reduced variation among generated futures, even when their distribution becomes less accurate. We introduce Kernel Physics-IQ to remove this incentive in expectation, needing only two independent samples per condition. Two-step sampling lowers Kernel Physics-IQ in all five image-to-video models. For CogVideoX, the official score rises by 0.055 while ours falls by 0.131. Changing the sampling schedule reveals further differences official scores miss. In controlled physical systems with known outcome probabilities, our metric favors the true distribution over collapsed predictions. In short, a world model should be judged not only by how closely one video matches what happened, but by how faithfully its predictions represent what could have happened.

Original source

This story was published by arXiv cs.CV and written by Yutao Li, Chen Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News