Joined December 2019
- Tweets 306
- Following 34
- Followers 4,097
- Likes 272
64 Photos and videos
May 27
Using our own prover to discover new mathematics!
May 27
1/ Since February, 8 papers across algebraic geometry, representation theory, number theory, combinatorics have been quietly appearing on arXiv.
Proofs by AxiomProver.
5 papers are now accepted at solid peer-reviewed math journals. To our knowledge, a first for the literature.
2
24
2,182
François Charton retweeted
May 19
It's my pleasure giving the opening talk of the Strings and Geometry Conference: indico.uu.se/event/1912/ where I presented joint work with Jacky Yip and Alessandro Mininno @UWMadPhysics and collaborators @arnal_charles @Meta @f_charton @axiommathai
2
4
16
1,828
Mar 26
Axplorer: an open source library for constructing interesting mathematical objects (and attacking really hard problems).
Have fun!
Mar 26
We open-sourced Axplorer.
Axplorer builds on PatternBoost; it discovers outlier math constructions to attack open problems.
On Turán 4-Cycles, No 5 Points on Sphere, and Isosceles-Free Sets, Axplorer matched SOTA w/ a fraction of compute cost and time.
It's now in your hands.
1
7
55
7,373
Mar 12
Announcing our series A, and a great video!
Mar 12
Axiom launched six months ago with one conviction: mathematics is the right foundation for building systems that reason.
Today we announce Axiom's Series A.
We raised $200M at a $1.6B valuation, led by @MenloVentures, to extend our lead in formal mathematics into Verified AI.
1
1
31
5,096
Feb 5
Verified mathematical discovery. An impressive first !
Feb 5
1/ AxiomProver has solved Fel’s open conjecture on syzygies of numerical semigroups, autonomously generating a formal proof in Lean with zero human guidance.
This is the first time an AI system has settled an unsolved research problem in theory-building math and self verifies.
7
102
11,156
Jan 26
In Aarhus for the AI and math workshop, our regular meeting of the AI for math discovery community (after Seoul last July and Oberwolfach last September). Can’t attend? The talks will be recorded and broadcast on the Youtube channel of Aarhus University.
Jan 26
1/ We’re proud to announce the Aarhus Math&AI Workshop, sponsored and co-organized by Axiom.
Speakers include Fields Medalists Terence Tao and Maryna Viazovska✨
From Axiom: Francois Charton @f_charton, Alberto Alfarano @albe_alfa, Seewoo Lee @antimath3
See you in Denmark! ❄️
1
5
29
4,642
Jan 10
Our results on the latest Putnam challenge, together with the proofs and a discussion.
Jan 9
1/ AxiomProver got 12/12 of Putnam 2025. Today we release the Lean proofs AxiomProver generated autonomously.
We also provide our take of the problems, proof visualizations, and compare how humans vs AI approach differently. Tons of fun math and Lean!
Our findings in thread.
1
5
41
3,797
François Charton retweeted
11 Dec 2025
For more info, here's a video of Francois @f_charton speaking at the renowned Kavli Institute for Theoretical Physics (Collatz starts 40'49''):
online.kitp.ucsb.edu/online/…
The talk also covers other discovery work: Lyapunov functions, PatternBoost, generating Calabi-Yau manifolds.
10 Dec 2025
1/ The Collatz conjecture has humbled mathematicians for near 90 years. Paul Erdös said "mathematics is not yet ready for such problems." 🧵
So we handed it to transformers. What they learned stunned us!
New research from Axiom's math discovery team, blog live this morning.
1
7
38
8,034
10 Dec 2025
Curious about AI discovering new maths? Come join us!
10 Dec 2025
9/ Axiom's discovery team @f_charton @albe_alfa @KenOno691 is currently looking for a highly selected group of PhD interns.
We are searching for candidates with advanced mathematics and strong machine learning backgrounds.
Apply: axiommath.ai/join-us
📧 careers@axiommath.ai
1
13
2,448
10 Dec 2025
A blog post about our recent Collatz paper
axiommath.ai/territory/learn…
10 Dec 2025
1/ The Collatz conjecture has humbled mathematicians for near 90 years. Paul Erdös said "mathematics is not yet ready for such problems." 🧵
So we handed it to transformers. What they learned stunned us!
New research from Axiom's math discovery team, blog live this morning.
1
2
10
1,764
7 Dec 2025
And here we go !!
7 Dec 2025
Putnam, the world's hardest undergrad math contest, ended 4pm PT yesterday.
By 3:58pm, AxiomProver @axiommathai autonomously solved 8/12 of Putnam2025 in Lean, a 100% verifiable language.
Last year, our score would've been #4 of ~4000 and a Putnam Fellow (top 10 in recent yrs)
3
3
14
2,478
François Charton retweeted
4 Dec 2025
I've spent my career thinking about hard math problems.
I am excited to share that I've joined Axiom @axiommathai as Founding Mathematician working with my former student @CarinaLHong.
AI for mathematical discovery in WSJ today.
4 Dec 2025
AxiomProver keeps getting stronger.
And @axiommathai keeps growing.
I'm excited to share that Prof. Ken Ono @KenOno691 has joined Axiom as Founding Mathematician and FTE #15.
He left his tenured position as STEM Advisor to Provost at UVA to build an AI mathematician with us.
Here's Ken's story. (1)
106
467
5,097
545,737
4 Dec 2025
Very excited to have @KenOno691 in Axiom! Looking forward to many collaborations.
4 Dec 2025
AxiomProver keeps getting stronger.
And @axiommathai keeps growing.
I'm excited to share that Prof. Ken Ono @KenOno691 has joined Axiom as Founding Mathematician and FTE #15.
He left his tenured position as STEM Advisor to Provost at UVA to build an AI mathematician with us.
Here's Ken's story. (1)
2
28
7,478
François Charton retweeted
2 Dec 2025
Axiom sets out to build an AI mathematician.
We are the underdog.
4 months old, 2 years late to the game, under 10 FTEs (recently grew to 17), and had 1:5 in funding and in valuation to our competitor.
Today, AxiomProver solved Erdos Problems #124 and #481 in Lean, a 100% verifiable language.
Onwards!
45
70
813
125,886
25 Nov 2025
Introducing Alberto Alfarano, the first author in our Lyapunov paper, and a coauthor in the transformer for post-quantum cryptography series. Welcome to Axiom, @albe_alfa !
25 Nov 2025
Introducing Axiom's discovery team: @albe_alfa
Alberto's path runs from the IMO → trading → training AI to crack a 130-year-old conjecture.
He found new Lyapunov functions while no general algorithm existed before.
AI for math discovery redefines the boundary of human minds.
2
15
1,429
24 Nov 2025
Transformers can learn the Collatz sequence, and do so in a very principled way. Models learn to predict, with 99% accuracy, classes of inputs defined by their base-2 representation, which correspond to particular instances of the computation algorithm 1/4 arxiv.org/abs/2511.10811
4
18
74
30,078
24 Nov 2025
When it fails, the model does not hallucinate, but predicts "almost correct" answers. In fact, 90% of model errors can be explained by a small number of deterministic rules (underestimating the number of passes in the loops of the computation algorithm). 3/4
1
2
8
828
24 Nov 2025
This leads to a new understanding of arithmetic transformers. They struggle with the control structures of the algorithms they learn, rather than the arithmetic operations, and do not hallucinate (when trained with supervision) but make "close" errors. 4/4
2
9
731