collaborators

10 papers

cs.LG2026

Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications

Julien Brandoit, Arthur Fyon, Damien Ernst +1

Sequence learning is dominated by Transformers and parallelizable recurrent neural networks (RNNs) such as state-space models, yet learning long-term dependencies remains challengi…

cs.NE2026

Energy-Efficient Implementation of Spiking Recurrent Cells on FPGA

Pascal Harmeling, Florent De Geeter, Guillaume Drion

Spiking Neural Networks (SNNs) can reduce energy consumption compared to conventional Artificial Neural Networks (ANNs) when spiking activity is sparse and the neuron model is hard…

cs.AR2026

Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations

Arthur Fyon, Julien Brandoit, Loris Mendolia +3

Always-on AI applications, from environmental sensors to biomedical implants, require ultra-low power consumption. Analog circuits offer a path to sub-microwatt inference, yet exis…

eess.SP2026

A Fully Tunable Ultra-Low Power Current-Mode Memory Cell in Standard CMOS Technology

Arthur Fyon, Loris Mendolia, Jean-Michel Redouté +2

This work introduces a fully tunable, ultra-low power unipolar memory cell inspired by the Schmitt-trigger comparator and designed in CMOS using only nine transistors. The proposed…

cs.LG2026

Context-dependent manifold learning: A neuromodulated constrained autoencoder approach

Jérôme Adriaens, Gustave Bainier, Guillaume Drion +1

Many physical systems exhibit a low-dimensional structure that varies with external parameters: link lengths in a robot, forcing constants in a fluid, or Reynolds numbers in a flow…

cs.LG2026

Parallelizable memory recurrent units

Florent De Geeter, Gaspard Lambrechts, Damien Ernst +1

With the emergence of massively parallel processing units, parallelization has become a desirable property for new sequence models. The ability to parallelize the processing of seq…