gpoesia / minimoLinks
Learning Formal Mathematics from Intrinsic Motivation
☆35Updated this week
Alternatives and similar repositories for minimo
Users that are interested in minimo are comparing it to the libraries listed below
Sorting:
- An environment for learning formal mathematical reasoning from scratch☆71Updated 10 months ago
- Proof artifact co-training for Lean☆45Updated 2 years ago
- The official implementation of "Self-play LLM Theorem Provers with Iterative Conjecturing and Proving"☆98Updated 3 months ago
- ☆190Updated 2 years ago
- Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving☆39Updated 2 years ago
- ☆60Updated last week
- The official repository for the paper Multilingual Mathematical Autoformalization☆36Updated last year
- ☆67Updated last year
- Code for the paper LeanReasoner: Boosting Complex Logical Reasoning with Lean: https://arxiv.org/pdf/2403.13312.pdf☆22Updated last year
- llmstep: [L]LM proofstep suggestions in Lean 4.☆137Updated last year
- ProofNet dataset ported into Lean 4☆22Updated last month
- An evaluation benchmark for undergraduate competition math in Lean4, Isabelle, Coq, and natural language.☆140Updated last week
- An updated version of miniF2F with lots of fixes and informal statements / solutions.☆87Updated 6 months ago
- NaturalProver: Grounded Mathematical Proof Generation with Language Models☆38Updated 2 years ago
- Harmonic Datasets☆40Updated last year
- Python wrapper for lean-gym☆12Updated 2 years ago
- [COLM 2024] A Survey on Deep Learning for Theorem Proving☆195Updated last month
- https://albertqjiang.github.io/Portal-to-ISAbelle/☆56Updated last year
- Benchmark for undergraduate-level formal mathematics☆108Updated 9 months ago
- LeanEuclid is a benchmark for autoformalization in the domain of Euclidean geometry, targeting the proof assistant Lean.☆101Updated 2 months ago
- NeqLIPS: a powerful Olympiad-level inequality prover☆37Updated 2 months ago
- Tutorial on neural theorem proving☆175Updated last year
- COPRA: An in-COntext PRoof Agent which uses LLMs like GPTs to prove theorems in formal languages.☆62Updated 2 months ago
- Neural theorem proving evaluation via the Lean REPL☆23Updated 9 months ago
- ☆31Updated 6 months ago
- Retrieval-Augmented Theorem Provers for Lean☆279Updated 5 months ago
- The Lean Theorem Proving Environment☆14Updated 2 years ago
- Code for the paper LEGO-Prover: Neural Theorem Proving with Growing Libraries☆65Updated last year
- Adaptive Subgoal Search☆19Updated 2 years ago
- Kimina Lean server☆90Updated last week