idrori / mathQLinks
Data and code for the paper "A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level" by Drori et al., 2022.
☆184Updated 3 years ago
Alternatives and similar repositories for mathQ
Users that are interested in mathQ are comparing it to the libraries listed below
Sorting:
- ☆550Updated last year
- Tutorial on neural theorem proving☆177Updated last year
- Formal to Formal Mathematics Benchmark☆409Updated 2 years ago
- ☆195Updated 2 years ago
- ☆379Updated 4 years ago
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆322Updated last year
- ☆259Updated 6 months ago
- Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network☆81Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆212Updated last year
- An interactive exploration of Transformer programming.☆271Updated 2 years ago
- A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick☆293Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆197Updated 2 years ago
- ChatGPT plugin for theorem proving in Lean☆123Updated last year
- Tools for working with the Abstraction & Reasoning Corpus☆212Updated 4 months ago
- Automatic gradient descent☆215Updated 2 years ago
- ☆167Updated 2 years ago
- Forecasting Future World Events with Neural Networks (NeurIPS 2022)☆183Updated 2 years ago
- Materials for ConceptARC paper☆110Updated last year
- Benchmark for undergraduate-level formal mathematics☆113Updated last year
- A hard gym for programming☆163Updated last year
- Retrieval-Augmented Theorem Provers for Lean☆314Updated 11 months ago
- Code for Parsel 🐍 - generate complex programs with language models☆436Updated 2 years ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆163Updated 5 months ago
- LeanAgent is a novel lifelong learning framework for formal theorem proving that continuously generalizes to and improves on ever-expandi…☆46Updated 6 months ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆174Updated 2 years ago
- ☆164Updated last year
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.☆171Updated 3 months ago
- LLMs + Lean, on your laptop or in the cloud☆199Updated 2 months ago
- Meta-Learning for Compositionality (MLC) for modeling human behavior☆145Updated last month
- Tool for data extraction and interacting with Lean programmatically.☆744Updated this week