Various projects I worked on
Overview of multiple projects, some of them have their dedicated page you can access to see demos.
ROADEF Challenge proposed by Orange Research (in progress)
Several-month optimization challenge proposed by ROADEF (French Operations Research Society) and Orange Research.
The T-Adaptive Segment Routing (T-ASR) problem consists of routing a set of traffic demands on an IP/MPLS network under planned intervention scenarios (with unavailable links). Routing relies on Segment Routing, which makes it possible to deviate traffic from shortest paths by adding waypoints.
Subject accessible here: Challenge_Orange_ROADEF_2026_Subject.pdf.
CharlesGPT — home-made documented chatbot (in progress)
End-to-end project to explore how a small generative model works in practice: Flutter client, FastAPI backend, local GPT-2 inference, token-level metrics (top‑k, perplexity) and adjustable sampling parameters.
CharlesGPT demo.
COPER latents — clinical EHR trajectories (MIMIC-III)
Research at RIKEN AIP, Statistical Genetics Team on MIMIC-III time series: Perceiver- and transformer-style models, including Continuous Patient State Perceiver (COPER) (Chauhan et al., 2024), for patient trajectory embeddings; Markov decision process head-level experiments for interpretability.
Repository: COPER-latents. Slides: view. Poster: view.
To be presented at the AIP Research Exchange Event, 1 June 2026, Nihombashi.
Identifying codes in graphs: study and coding experiments
2-month research project on identifying codes in graphs, based on the paper Charon et al., Minimum Sizes of Identifying Codes in Graphs Differing by One Vertex.
Poster: view.
Coding experiments and implementations: Identifying_codes_graphs.
CPSolver — Constraint Satisfaction Problem solver
A constraint programming solver developed as part of a Parisian Master of Operations Research Constraint Programming class (course page).
╔══════════════════════════════════════════════════════════════════════════════╗ ║ ║ ║ ██████╗██████╗ ███████╗ ██████╗ ██╗ ██╗ ╔██ ███████╗██████╗ ║ ║ ██╔════╝██╔══██╗ ██╔════╝██╔═══██╗██║ ██║ ║██ ██╔════╝██╔══██╗ ║ ║ ██║ ██████╔╝ ██ ███████╗██║ ██║██║ █║ ║█ █████╗ ██████╔╝ ║ ║ ██║ ██╔═══╝ ╚════██║██║ ██║██║ ║█ █║ ██╔══╝ ██╔══██╗ ║ ║ ╚██████╗██║ ███████║╚██████╔╝╚██████╚█████╝ ███████╗██║ ██║ ║ ║ ╚═════╝╚═╝ ╚══════╝ ╚═════╝ ╚════╝ ╚═══╝ ╚══════╝╚═╝ ╚═╝ ║ ║ ║ ║ Constraint Satisfaction Problem Solver ║ ╚══════════════════════════════════════════════════════════════════════════════╝
A Constraint Satisfaction Problem (CSP) is defined by variables, which form a finite set where each variable has a domain of possible values, and constraints, which form a finite set restricting the combinations of values that variables can take.
Main solver components include the DIMACS CSP parser, constraint propagation with AC-3 and forward checking, variable/value ordering heuristics (such as MRV and LCV), and a backtracking search engine to enumerate solutions.
Repository: charles-vzf/CPSolver.
(Un)capacitated Facility Location Problem (UFLP)
The (Un)capacitated Facility Location Problem (UFLP) is a classic optimization problem in operations research and logistics. The problem involves determining the optimal locations for facilities (such as warehouses, distribution centers, or service centers) to serve a set of customers while minimizing total costs.
We developed a multithreaded simulated annealing heuristic based on several initialization and perturbation strategies.
Experiments for propagation of chaos in mean field underdamped regime for wide neural networks
5-month internship at RIKEN AIP (Deep Learning Theory Team).
Studying Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble. Discussing hypothesis, and providing experimental validation, see code, and report: view.
ModularyNN — modular neural network framework (Python)
Lightweight, composable neural network building blocks for experiments and teaching: customizable layers and training loops.
from scratch (no advanced libraries).
Repository: modularyNN.
Technical support for Ardian startup studio
3-day Ardian Startup Studio hackathon.
Technical support for prototyping ideas for internal use at Ardian France; demonstrated feasibility and identified long-term limitations.
Yearly event in Paris (see Artefact press release).
KIRO Inter School Operational Research Challenge
3 participations with strong results on optimization problems from RTE, Renault, and Pelico. See KIRO challenge.
Repository from first participation (extended): Projet_RO_RTE.
AI and machine learning for theme park attraction attendance prediction
One-day challenge by Eleven Strategy at Ecole des Ponts; ranked 2nd. With Mathis Wauquiez and Célestin Hans as teammates.
See our slides: view.
Simulation and learning for gas storage refueling optimization
6-month project at Ecole des Ponts in partnership with Air Liquide R&D. Superior cost function results compared to previous naive methods.
Differential and Riemannian geometry — general relativity and black hole trajectory simulation
6-month research project (1st year, Ecole des Ponts).
Reproducing results from generic simulations. Supervised by Éric Cancès.
You can see our report here: view.
Study of Torsion of a Parallelepiped in 3D Modeling with Cast3M
This project models and visualizes the 3D torsion behavior of a parallelepiped using Cast3M, a structural analysis and fluid mechanics simulation code, to analyze its thermomechanical response under deformation (see Cast3M).
Report: view PDF (in French).
Modeling granular media using cellular automata
One and a half year project as part of mathematical and physics preparatory classes (MP), known as TIPE.
Mathematical theory of cellular automata and open-source tooling to reproduce erosion and craterization with custom rules (using Golly), combining hashing techniques with macro-cell techniques so large runs remain tractable.
See the short description and the slides (both in French).
Eratosthenes: history & science overview (3rd c. BC)
Cross-disciplinary high-school group project between history and science, centred on Eratosthenes of Cyrene: the sieve of Eratosthenes for prime numbers and his method for estimating Earth’s circumference with surprisingly good accuracy once measurement uncertainty is taken into account—impressive given that many civilizations did not yet treat Earth as round long afterwards.
Report (French): view PDF.