Arthur Renard

Applied Mathematician & AI Researcher

Exploring the frontiers of AI in mathematical reasoning and LLMs.

Currently researching at EPFL under Prof. C. Hongler. Graduate from ETH Zürich with a Master's in Applied Mathematics.

Research Projects

Exploring AI, mathematical reasoning, and symbolic regression at EPFL

Symbolic Math Solver

Symbolic Math Solver

Master's Thesis - ETH Zürich | Supervised by Clément Hongler - EPFL

PyTorchTransformersSymbolic RegressionFunctional Equations

This research explores the intersection of functional equations, symbolic regression, and deep learning through innovative methods. I developed Symbolic Math Solver (SMS), a novel framework extending ...

Learn More
Paper submission in preparation
Boolformer

Boolformer

Under review - ICML 2025 | Stéphane d'Ascoli*, Arthur Renard*, Emmanuel Abbé, Clément Hongler, Vassilis Papadopoulos, Josh Susskind, Samy Bengio - APPLE, EPFL

PyTorchTransformersAcademic ResearchSymbolic Regression

We introduce Boolformer, a Transformer-based model trained to perform end-to-end symbolic regression of Boolean functions. The model can predict compact formulas for complex functions not seen during ...

Learn More
GitHub
Under review at ICML 2025

Experience Highlight

Current research position

Researcher

EPFL, Chair of Statistical Field Theory, Prof. C. Hongler

2023 - Now

Exploring the application of artificial intelligence in mathematical reasoning while investigating inference techniques and the security of large language models.

Key Publications & Projects

Boolformer: End-to-end symbolic regression for Boolean functions

Phase Transition Finder: Published at GECCO 2024, doubling discovery rate in Lenia

Symbolic Math Solver: International Mathematical Olympiad problems solver powered by AI

LLM Security: Exploring optimization methods in embedding space for enhanced inference

Core Skills

Technical expertise and professional competencies

Programming

  • Python/PyTorch
  • C++
  • Rust
  • Next.js/React Native

Machine Learning

  • Deep Learning
  • Transformers
  • Symbolic Regression
  • LLMs and their applications

Languages

  • French (Native)
  • English (C1, Cambridge)
  • German (Intermediate)
  • Dutch (Basic)

Get In Touch

Feel free to reach out for collaborations or just a friendly chat

LinkedIn ProfileGitHub Profile
Lausanne, Switzerland