Academic Projects

Reinforcement Learning

• Robot Control:
  • Goal: Training a wheeled-bipedal robot to recover from pushes using PPO, reward shaping, curriculum, inductive bias.
  • Supervised by: INRIA Willow team (S. Caron)
• Traffic Optimization using Autonomous Vehicles:
  • Goal: Exploring how DQNs (and PPO) can learn to control autonomous vehicles to avoid traffic jams
  • Inspired by: CIRCLES project.
  • Resources: Report ; RL Environment

Bayesian ML & Probabilistic Methods

• Neural Posterior Estimation (NPE) & Importance Sampling (IS):
  • Goal: Improve estimation of narrow posterior dimensions
  • Context: MVA ‘bayesian ML’ course
  • Resources: Code ; Report
• On the relation between Flow Matching (FM) and Optimal Transport (OT):
  • Goal: does FM recover OT map ?
  • Context: MVA ‘generative modelling for images’ course

Deep Learning, Physics & Vision

• Physics Informed Neural Networks (PINNs):
  • Goal: Solve Helmholtz PDEs with PINNs
  • Supervised by: scientists from Airbus + professor from ENPC
  • Resources: Poster ; Report ; Code
• Neural Radiance Fields (NERFs) for Scene Video Synthesis:
  • Supervised by: Prof. Vincent Lepetit
  • Resources: Slides ; Code
• Self-supervised learning for point clouds:
  • Goal: Paper study
  • Context: MVA ‘geometric DL’ course

Optimization & Operations Research

• Offshore Wind Electrical Network Optimization:
  • Goal: Optimizing an offshore wind electrical network for RTE, FR
  • Competition: KIRO 2023 (Project)
  • Using: Python, Julia, C++, Gurobi (MIP), Hexaly, S.Annealing
  • Resources: Code
• Manufacturing Chain Optimization:
  • Goal: Optimizing a car manufacturing chain for Renault, FR
  • Competition: KIRO 2024 (Hackathon)
  • Using: Python, C++, Julia, Gurobi (MIP), Hexaly, S.Annealing
  • Resources: Code

NLP

• RNN-based Neural Machine Translation Model:
  • Goal: Trained an LSTM-based machine translation toy model and integrated it in a web interface
  • Resources: Code

Internship Projects:

• MLO Lab, CHE 🇨🇭
  • See details in experience, here.
• TII, UAE 🇦🇪
  • Knowledge Distillation and model pruning strategies.
  • Large-scale optimization algorithms and scaling laws for parametrization of LLMs.
  • Example contribution to an open-source Nvidia framework: PR
  • Falcon3 family is finally released (SOTA)!
  • More releases coming in 2025…

P.S

Some code links might not be accessible.
This means generally that I (we) am (are) working on cleaning them.
I may also have changed the repo name (sorry). But I’ll try to update every once in a while.