2026
Real-time discrete world-model control in Geometry Dash using FSQ tokenization, action-conditioned transformer dynamics, and an actor-critic trained in latent rollouts.
Florent Tariolle
I build deep neural networks that think, predict and act.
World models · Self-supervised learning · Reinforcement learning
Research that crosses representation and action.
I am an engineering student in Computer Science and Artificial Intelligence at INSA Rouen Normandy and an incoming Master's student in Machine Learning for Artificial Intelligence at the University of Rouen Normandy.
At InterDigital, I work on deep learning for next-generation video compression. At Enedis, I work on generative modeling and large-scale pipelines for high-frequency electricity-grid time series.
Seeking a six-month research internship starting in April 2027
Selected Work.
Research is where I turn difficult questions into working systems.
Explore publications, independent research, patents, and engineering projects.
06.2026
Developed at Hack the World(s), a Yann LeCun-sponsored 24-hour challenge centered on JEPAs and world models: a compact self-supervised EEG pipeline combining SIGReg frozen-transfer baselines with Riemannian analysis of structure in SPD covariance representations.
05.2026
A lightweight wrapper for query-efficient black-box attacks that uses early class-confidence signals to reduce class drift and commit to promising adversarial targets.
2026
An official PyTorch Ecosystem project for visualizing neural-network architectures. I maintain the project and designed and implemented its MCP integration for generating editable diagrams from model definitions.
2025
A high-traffic real-time customization tool whose Python backend, Cloudflare Workers relay, and browser integration serve more than 25,000 daily active users.
No public patent work yet.
Public patent work will appear here once it is available.