François Charton
@f_charton
Followers
4K
Following
220
Media
58
Statuses
254
AI for mathematics and theoretical physics Tomorrow's problems on yesterday's machines Axiom - École nationale des ponts et chaussées
France
Joined December 2019
I am joining Axiom Math, a seed-stage startup on AI for maths. I will lead discovery: AI for advancing math research. 6 years after Deep Learning for Symbolic Maths, our first paper with @GuillaumeLample, I am proud of the field's progress, and excited about what comes next.
15
17
268
Congratulations Jeremy! And long live AI4Maths !.
“The institute will focus on the mathematical components of these tasks and use the technologies to support mathematical reasoning and computation in all its applications,” said Jeremy Avigad, director of ICARM.
0
1
16
Lesson 2 on AI for arithmetic, and maths for interpretability.
0
1
8
Two lessons I gave in March, for the Journées de Calcul Formel (Francophone Computer Algebra Days), in Luminy. Lesson one on AI and mathematical discovery (integration, differential system stability, combinatorics).
1
3
15
RT @gary_shiu: Excited to share with you an exciting project with Jacky Yip @UWMadPhysics and @arnal_charles and @f_charton @Meta where we….
0
5
0
Open sourcing Int2Int, a Python code base for AI for maths, with a special focus on arithmetic and number theory A user manual, and instructions on how to extend it, can be found here
0
3
22
RT @Rythian47: I am extremely happy to announce that our paper.Can Transformers Do Enumerative Geometry? ( has been….
arxiv.org
How can Transformers model and learn enumerative geometry? What is a robust procedure for using Transformers in abductive knowledge discovery within a mathematician-machine collaboration? In this...
0
5
0
Expériences conduisant aux intuitions. Les résultats des expériences avec des transformers nous ont indiqué où regarder.
0
0
6
A pure physics paper based on intuitions from AI experiments, expect more of these!.
I’m pretty excited about our new paper, which is a follow up to our last paper using AI to help solve a problem in theoretical particle physics. (With Lance, @f_charton, Matthias, Tianji, and @merz_garrett
2
6
41
The code for our paper: Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers, with @albe_alfa and @Amaury_Hayat is available at We will be in NeurIPS: come see us at the poster session next Thursday at 5PM.
github.com
PyTorch original implementation of "Global Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers" (NeurIPS 2024). - facebookresearch/Lyapunov
3
32
320
Thank you for having me @KyleCranmer and @gary_shiu .Research featured in the talk: discovering Lyapunov functions (9:55), PatternBoost: generative models in combinatorics (31:20), Scattering amplitudes (44:10), Arithmetic, repetition, and a few unpublished results (46:40).
We had a great turnout for our inaugural AI for Science seminar with François Charton last week. If you missed it, check out the recording: @KyleCranmer
0
4
19
RT @KyleCranmer: I'm thrilled to announce that François Charton (@f_charton @AIatMeta) will be kicking off our new AI for Science seminar s….
0
22
0
How do transformers learn arithmetic tasks, such as GCD and modular sums and products?.My talk in Collège de France on November 4th (in French, but the English subtitles are quite good). Thank you @wtgowers for inviting me to your seminar!.
6
21
108
Transformers for discrete optimisation problems .1- Train a model on candidate solutions.2- Use the model to generate more candidates.3- Improve the solutions with local search.4- Use the best candidates to fine tune the model.5- Iterate.
New preprint up! "PatternBoost: Constructions in Mathematics with a Little Help from AI," with F. Charton, A.Z. Wagner, and G. Williamson:
11
58
430
Our Lyapunov paper in the New Scientist. Thanks @stokel !.
An AI system has helped tackle a longstanding tough mathematical problem involving tools called Lyapunov functions. My latest for @newscientist
0
4
36
Human mathematicians (masters students) achieve less than 10% accuracy on this task (vs more than 80% for our model). 8/8
1
1
31
We tested our models on sets of random dynamical systems, the stability of which is unknown, and could find new Lyapunov functions in 10 to 13% of the cases. (7/8)
1
0
18
Performance is greatly improved by adding a tiny number (0.03%) of easy and solvable "forward" examples (systems for which we have solutions) to the backward training set. Such "primed models" outperform state of the art methods by a large margin. 6/8
1
0
19