7 papers
Fast Linear Reservoirs via Diagonalization
Romain de Coudenhove, Yannis Bendi-Ouis, Anthony Strock +1
We introduce a diagonalization-based optimization for Linear Echo State Networks (ESNs) that reduces the per-step computational complexity of reservoir state updates from quadratic…
CogScale: Scalable Benchmark for Sequence Processing
Yannis Bendi-Ouis, Romain de Coudenhove, Xavier Hinaut
The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models have achieved remarkable succ…
Echo State Transformer: Attention Over Finite Memories
Yannis Bendi-Ouis, Xavier Hinaut
While Large Language Models and their underlying Transformer architecture are remarkably efficient, they do not reflect how our brain processes and learns a diversity of cognitive…
Software Engineering Agents for Embodied Controller Generation : A Study in Minigrid Environments
Timothé Boulet, Xavier Hinaut, Clément Moulin-Frier
Software Engineering Agents (SWE-Agents) have proven effective for traditional software engineering tasks with accessible codebases, but their performance for embodied tasks requir…
ReservoirChat: Interactive Documentation Enhanced with LLM and Knowledge Graph for ReservoirPy
Virgile Boraud, Yannis Bendi-Ouis, Paul Bernard +1
We introduce a tool designed to improve the capabilities of Large Language Models (LLMs) in assisting with code development using the ReservoirPy library, as well as in answering c…
Deploying Open-Source Large Language Models: A performance Analysis
Yannis Bendi-Ouis, Dan Dutartre, Xavier Hinaut
Since the release of ChatGPT in November 2022, large language models (LLMs) have seen considerable success, including in the open-source community, with many open-weight models ava…