TIFR joins the #AIforMath Initiative, supported by Google DeepMind & Google.org, alongside Imperial, IHES, IAS & Simons Institute.
At TIFR, Hariharan Narayanan & Piyush Srivastava coordinate efforts to explore how AI can extend mathematical reasoning & discovery.
More: blog.google/technology/g...
At TIFR, Hariharan Narayanan & Piyush Srivastava coordinate efforts to explore how AI can extend mathematical reasoning & discovery.
More: blog.google/technology/g...
Accelerating discovery with the AI for Math Initiative
The AI for Math Initiative brings together five of the world's most prestigious research institutions.
blog.google
October 29, 2025 at 3:23 PM
Everybody can reply
1 saves
Congratulations to the EPFL team selected for the AI for Math Fund by Renaissance Philanthropy with support from XTX Markets! 🎉
Their project, Document-Level Autoformalization, uses AI to bridge human and machine understanding of mathematics.
🔗 Learn more: ai.epfl.ch/advancing-ma...
#AIforMath
Their project, Document-Level Autoformalization, uses AI to bridge human and machine understanding of mathematics.
🔗 Learn more: ai.epfl.ch/advancing-ma...
#AIforMath
Advancing Mathematics with AI - EPFL AI Center
A research team from EPFL has been awarded funding through the AI for Math Fund, an $18 million program jointly developed to accelerate mathematical discovery through artificial intelligence. Titled D...
ai.epfl.ch
October 16, 2025 at 12:01 PM
Everybody can reply
1 likes
Readings shared June 19, 2025. jaalonso.github.io/vestigium/po... #AI #AIforMath #CoqProver #ITP #IsabelleHOL #LLMs #LeanProver #Math #Rocq
Readings shared June 19, 2025
The readings shared in Bluesky on 19 June 2025 are
Galois energy games (in Isabelle/HOL). ~ Caroline Lemke. #ITP #IsabelleHOL
Chomsky-Schützenberger representation theorem (in Isabelle/HOL). ~ Moritz
jaalonso.github.io
June 20, 2025 at 11:13 AM
Everybody can reply
Reviving DSP for advanced theorem proving in the era of reasoning models. ~ Chenrui Cao, Liangcheng Song, Zenan Li, Xinyi Le, Xian Zhang, Hui Xue, Fan Yang. arxiv.org/abs/2506.114... #AI #Math #AIforMath #LLMs #ITP #LeanProver
Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
Recent advancements, such as DeepSeek-Prover-V2-671B and Kimina-Prover-Preview-72B, demonstrate a prevailing trend in leveraging reinforcement learning (RL)-based large-scale training for automated th...
arxiv.org
June 19, 2025 at 5:12 PM
Everybody can reply
1 likes
Reseña de «Can A.I. quicken the pace of math discovery?». jaalonso.github.io/vestigium/po... #AI #Math #AIforMath #ITP #LeanProver
Reseña de «Can A.I. quicken the pace of math discovery?»
El artículo «Can A.I. quicken the pace of math discovery?» presenta la
iniciativa "Exponentiating Mathematics" de DARPA. Su objetivo es
desarrollar una IA como coautor para acelerar la investigación e
jaalonso.github.io
June 19, 2025 at 3:35 PM
Everybody can reply
Readings shared June 15, 2025. jaalonso.github.io/vestigium/po... #AI #AIforMath #CoqProver #FunctionalProgramming #Haskell #ITP #LeanProver #Lisp #Math #Programming #Rocq
Readings shared June 15, 2025
The readings shared in Bluesky on 15 June 2025 are
BiCoq: Bigraphs formalisation with Coq. ~ Cécile Marcon et als. #ITP #CoqProver #Rocq #Math
Introduction to competitive programming in Haskell. ~ Br
jaalonso.github.io
June 16, 2025 at 7:01 AM
Everybody can reply
Reseña de «Hardest problems in mathematics, physics & the future of AI». jaalonso.github.io/vestigium/po... #ITP #LeanProver #AI #Math #AIforMath
Reseña de «Hardest problems in mathematics, physics & the future of AI
En la entrevista "Hardest problems in mathematics, physics & the future of AI", Terence Tao comparte sus reflexiones sobre diversos problemas
fundamentales sin resolver en análisis y teoría de números
jaalonso.github.io
June 15, 2025 at 11:35 AM
Everybody can reply
1 likes
Hardest problems in mathematics, physics & the future of AI. ~ Terence Tao, Lex Fridman. youtu.be/HUkBz-cdB-k #ITP #LeanProver #AI #Math #AIforMath
Terence Tao: Hardest Problems in Mathematics, Physics & the Future of AI | Lex Fridman Podcast #472
YouTube video by Lex Fridman
youtu.be
June 15, 2025 at 6:03 AM
Everybody can reply
3 reposts
9 likes
Readings shared June 13, 2025. jaalonso.github.io/vestigium/po... #AI #AIforMath #Autoformalization #CoqProver #HOL_Light #ITP #IsabelleHOL #LLMs #LeanProver #Logic #MLLMs #Math #Rocq
Readings shared June 13, 2025
The readings shared in Bluesky on 13 June 2025 are
Formalizing zeta and L-functions in Lean. ~ David Loeffler, Michael Stoll. #ITP #LeanProver #Math
Formal verification of relational algebra transfor
jaalonso.github.io
June 14, 2025 at 9:19 AM
Everybody can reply
The abc conjecture almost always — autoformalized. ~ Jesse Michael Han et als. github.com/morph-labs/l... #Autoformalization #AIforMath #ITP #LeanProver
GitHub - morph-labs/lean-abc-true-almost-always
Contribute to morph-labs/lean-abc-true-almost-always development by creating an account on GitHub.
github.com
June 13, 2025 at 5:31 PM
Everybody can reply
1 likes
Trinity: an autoformalization system for verified superintelligence. www.morph.so/blog/trinity #Autoformalization #AIforMath #ITP #LeanProver
June 13, 2025 at 5:28 PM
Everybody can reply
1 reposts
Reseña de «Mathesis: Towards formal theorem proving from natural languages». jaalonso.github.io/vestigium/po... #AI #LLMs #Math #ITP #LeanProver #AIforMath
Reseña de «Mathesis: Towards formal theorem proving from natural langu
En el artículo «Mathesis: Towards formal theorem proving from natural
languages», se aborda la limitación clave de los demostradores de
teoremas: su dependencia de enunciados ya formalizados. El traba
jaalonso.github.io
June 13, 2025 at 4:44 PM
Everybody can reply
Mathesis: Towards formal theorem proving from natural languages. ~ Yu Xuejun et als. arxiv.org/abs/2506.07047 #AI #LLMs #Math #ITP #LeanProver #AIforMath
Mathesis: Towards Formal Theorem Proving from Natural Languages
Recent advances in large language models show strong promise for formal reasoning. However, most LLM-based theorem provers have long been constrained by the need for expert-written formal statements a...
arxiv.org
June 13, 2025 at 4:30 PM
Everybody can reply
2 likes
Reseña de «MATP-BENCH: Can MLLM be a good automated theorem prover for multimodal problems?». jaalonso.github.io/vestigium/po... #AI #MLLMs #Math #ITP #IsabelleHOL #LeanProver #CoqProver #AIforMath
Reseña de «MATP-BENCH: Can MLLM be a good automated theorem prover for
En el artículo «MATP-BENCH: Can MLLM be a good automated theorem prover for multimodal problems?», los autores investigan la aplicabilidad de
los modelos de lenguaje grandes multimodales (MLLMs) al pr
jaalonso.github.io
June 13, 2025 at 3:20 PM
Everybody can reply
MATP-BENCH: Can MLLM be a good automated theorem prover for multimodal problems? ~ Zhitao He et als. arxiv.org/abs/2506.06034 #AI #MLLMs #Math #ITP #IsabelleHOL #LeanProver #CoqProver #AIforMath
MATP-BENCH: Can MLLM Be a Good Automated Theorem Prover for Multimodal Problems?
Numerous theorems, such as those in geometry, are often presented in multimodal forms (e.g., diagrams). Humans benefit from visual reasoning in such settings, using diagrams to gain intuition and guid...
arxiv.org
June 13, 2025 at 12:29 PM
Everybody can reply
1 likes
StepProof: Step-by-step verification of natural language mathematical proofs. ~ Xiaolin Hu, Qinghua Zhou, Bogdan Grechuk, Ivan Y. Tyukin. arxiv.org/abs/2506.10558 #LLMs #ITP #IsabelleHOL #Math #AIforMath
StepProof: Step-by-step verification of natural language mathematical proofs
Interactive theorem provers (ITPs) are powerful tools for the formal verification of mathematical proofs down to the axiom level. However, their lack of a natural language interface remains a signific...
arxiv.org
June 13, 2025 at 10:15 AM
Everybody can reply
1 reposts
4 likes
Readings shared June 11, 2025. jaalonso.github.io/vestigium/po... #AIforMath #CompSci #IA #ITP #LeanProver #Logic #Math #RustLang #SMT #Z3
Readings shared June 11, 2025
The readings shared in Bluesky on 11 June 2025 are
LeanTutor: A formally-verified AI tutor for mathematical proofs. ~ Manooshree Patel et als. #ITP #LeanProver #Math #AIforMath #Teaching
Common Lean
jaalonso.github.io
June 12, 2025 at 6:18 AM
Everybody can reply
Reseña de 'LeanTutor: A formally-verified AI tutor for mathematical proofs'. jaalonso.github.io/vestigium/po... #ITP #LeanProver #Math #AIforMath #Teaching
Reseña de 'LeanTutor: A formally-verified AI tutor for mathematical pr
El artículo "LeanTutor: A formally-verified AI tutor for mathematical
proofs" aborda un problema común en la educación matemática: los
estudiantes tienen dificultades para aprender demostraciones.
Act
jaalonso.github.io
June 11, 2025 at 5:35 PM
Everybody can reply
1 likes
LeanTutor: A formally-verified AI tutor for mathematical proofs. ~ Manooshree Patel et als. arxiv.org/abs/2506.08321 #ITP #LeanProver #Math #AIforMath #Teaching
LeanTutor: A Formally-Verified AI Tutor for Mathematical Proofs
We present LeanTutor, a Large Language Model (LLM)-based tutoring system for math proofs. LeanTutor interacts with the student in natural language, formally verifies student-written math proofs in Lea...
arxiv.org
June 11, 2025 at 5:01 PM
Everybody can reply
2 likes
El futuro del razonamiento matemático: Integrando IA y Lean. jaalonso.github.io/vestigium/po... #IA #ITP #LeanProver #Math #AIforMath
El futuro del razonamiento matemático: Integrando IA y Lean
En su conferencia "Will computers prove theorems?", Kevin Buzzard
plantea que los ordenadores ya demuestran teoremas, pero la pregunta
crucial es cómo pueden transformar la investigación matemática. A
jaalonso.github.io
June 11, 2025 at 3:53 PM
Everybody can reply
Readings shared June 10, 2025. jaalonso.github.io/vestigium/po... #AI #AIforMath #ATP #AlphaProof #Emacs #ITP #IsabelleHOL #LLMs #LeanProver #Math #Prover9
Readings shared June 10, 2025
The readings shared in Bluesky on 10 June 2025 are
Inductive definitions. ~ Lawrence Paulson. #ITP #IsabelleHOL #Math
The equational theories project: advancing collaborative mathematical research at
jaalonso.github.io
June 11, 2025 at 9:10 AM
Everybody can reply
El proyecto ETP (Un caso de estudio en investigación matemática colaborativa y formalizada). jaalonso.github.io/vestigium/po... #AIforMath #ITP #LeanProver #Math
El proyecto ETP (Un caso de estudio en investigación matemática colabo
Hoy, en su conferencia "The equational theories project", Terence Tao
defendió que la investigación matemática debe evolucionar hacia un
modelo colaborativo a gran escala, semejante al empleado en otr
jaalonso.github.io
June 10, 2025 at 6:29 PM
Everybody can reply
1 likes
The equational theories project: advancing collaborative mathematical research at scale. ~ Terence Tao et als. terrytao.wordpress.com/wp-content/u... #ITP #LeanProver #Math #AIforMath
June 10, 2025 at 5:36 PM
Everybody can reply
2 likes
El futuro de las matemáticas: Descubrimiento colaborativo entre humanos y máquinas. jaalonso.github.io/vestigium/po... #AIforMath #AI #Math
El futuro de las matemáticas - Descubrimiento colaborativo entre human
Ayer, en su conferencia "AI for Math: The future of collaborative
discovery", Mateja Jamnik presentó una visión de la inteligencia
artificial no como una simple herramienta para resolver problemas, si
jaalonso.github.io
June 10, 2025 at 5:13 PM
Everybody can reply
2 likes