11 papers
Continual Visual Learning under Evolving Semantic Concept Shift
Ismail Lamaakal, Chaymae Yahyati, Yassine Maleh +2
Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed.…
Provenance Guided Incremental Learning Under Evolving Concept Definitions
Ismail Lamaakal
Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that generate their prediction tar…
Motion-Compensated Weight Compression
Ismail Lamaakal
Neural network weights are increasingly a bottleneck for deployment, yet most compression pipelines treat layers independently and overlook cross-layer redundancy induced by functi…
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…
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…
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…