יום שישי, 31 ביולי 2026 LIVE
AI־INFO

כתבה arXiv cs.LG ·

Dynamic Parameterization Is Not Dynamic Inference

תקציר מקורי באנגליתarXiv:2607.26192v1 Announce Type: new Abstract: Input-dependent controller coefficients are often treated as evidence of dynamic inference or computational savings. This interpretation conflates three properties: coefficient variation, dependence of a frozen model on how coefficients are assigned to inputs, and conditional execution. We focus on the second property and formulate a general principle of frozen-controller auditing. We provide one concrete implementation, Frozen-Controller Auditing (FCA), which caches the complete coefficient tensor along an unperturbed trajectory, disables the controller, and replays the frozen model with cross-input reassignment, token shuffling, and static profiles estimated from an independent calibration set. Because the coefficients are cached before any
קרא במקור המקורי