collaborators

7 papers

cs.LG2026

When Bits Break Recourse: Counterfactual-Faithful Quantization

Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui +1

Model quantization is widely used to reduce memory, latency, and deployment cost, and is typically judged by whether predictive accuracy is preserved. In decision systems that prov…

cs.LG2026

Drift-to-Action Controllers: Budgeted Interventions with Online Risk Certificates

Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui +2

Deployed machine learning systems face distribution drift, yet most monitoring pipelines stop at alarms and leave the response underspecified under labeling, compute, and latency c…

cs.LG2026

SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML

Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui +2

Reliable uncertainty estimation is a key missing piece for on-device monitoring in TinyML: microcontrollers must detect failures, distribution shift, or accuracy drops under strict…

cs.LG2026

Simplex-FEM Networks (SiFEN): Learning A Triangulated Function Approximator

Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui +2

We introduce Simplex-FEM Networks (SiFEN), a learned piecewise-polynomial predictor that represents f: R^d -> R^k as a globally C^r finite-element field on a learned simplicial mes…

cs.CL2026

T3C: Test-Time Tensor Compression with Consistency Guarantees

Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh +2

We present T3C, a train-once, test-time budget-conditioned compression framework that exposes rank and precision as a controllable deployment knob. T3C combines elastic tensor fact…

cs.LG2025

BayesQ: Uncertainty-Guided Bayesian Quantization

Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh +2

We present BayesQ, an uncertainty-guided post-training quantization framework that is the first to optimize quantization under the posterior expected loss. BayesQ fits a lightweigh…