3 papers
cs.LG2026
Whitening Inverts the Hierarchy: What the Norm of a Whitened Embedding Measures
Mohammed Ahnouch, Lotfi Elaachak
Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened coordinates often appear app…
cs.LG2026
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
Mohammed Ahnouch, Lotfi Elaachak
Counting equivalent pairs is a common way to report transformation-audit coverage, but it can substantially overstate the constraints imposed by an audit: pairs generated from the…
cs.LG2026
Spectral Rank Certification for Foundation Model Adapters
Mohammed Ahnouch, Lotfi Elaachak
Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity. This article develops a finite-sample framework for inferring effective ra…