SOURCE-LINKED INTELLIGENCE

Sampling headroom is not selection gain: a compute-value audit of test-time scaling for video world models

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Test-time scaling (TTS) can improve generation only when additional compute produces better candidates and the system can reliably identify them. This distinction is especially important for video world models, where a wider sample pool may contain stronger rollouts without improving the output that is ultimately selected. We introduce the Compute-Value Audit (CVA), a sequential framework that asks whether extra sampling creates opportunity, observable signals provide a reliable state, that state supports a beneficial action, and the resulting gain exceeds the full entry fee of generation and

Read original source ↗ Open in workspace

recordType

paper

region

Global