GLoW Reimplementation
in progressClean reimplementation of the Global Latent Workspace architecture in PyTorch, with modular domain encoders and a shared latent broadcast space.
AI/ML Research PyTorch
Victor Monnot
Building the bridge
between minds and machines.
AI researcher & engineer working on global workspace architectures, multi-agent systems, and the foundations of post-language communication.
Projects
View all →Multi-Agent Simulation
in progressAgent-based simulation environment exploring emergent collective behaviors from simple local interaction rules.
Multi-Agent Simulation Python
EOS Website
conceptPublic-facing website for the EOS brand-vision — documenting humanity's transition towards augmented intelligence and space exploration.
Web Design Vision
Latest writing
View all →Why Global Workspace Theory Matters for AI
Global Workspace Theory is one of the most promising — and underexplored — frameworks for building AI systems that actually integrate information like brains do.
AI/ML Research Neuroscience
From Sci-Fi to Specs: Reverse-Engineering the Future
How I use science fiction as a design tool — starting from a vivid picture of the future and working backwards to identify the technical bricks that need to exist.
Vision Method
Notes on Shimmer and GLoW
Technical notes from reading through the Shimmer codebase and the GLoW architecture — what works, what's unclear, and what I want to extend.
AI/ML Research Notes