MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers get the gist as quickly as possible.

[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

[NeurIPS 2023] This is the official code for the paper "TPSR: Transformer-based Planning for Symbolic Regression"

[ICLR 2024 Spotlight] This is the official code for the paper "SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training"

[ICLR'25] Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training

Code & data for ICLR 2024 spotlight paper: 🍯MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

A unified neural-symbolic framework for solving plane and solid geometric problems via Parse2Reason & Official repository for the CVPR 2026 paper Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning.

A collection of recent open-source math datasets for training and evaluating Math LLMs

Repository hosting the resources for the conference "ItaLean 2025", held in Bologna, Italy, December 9–12, 2025.

[ICLR 2024 Spotlight] SNIP on Symbolic Regression: Deep Symbolic Regression with Multimodal Pretraining

SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry

🎓Automatically Update AI4math Papers Daily using Github Actions

[ICLR2025] Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo (https://arxiv.org/abs/2410.01920)

Code to reproduce the experiments of the ICML25-paper: "Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?"

A curated list of awesome formal reasoning AI.

Official code for "Can Transformers Do Enumerative Geometry?"

LeanSlop: LLM-slop black box automation for the Lean4 theorem prover

[NeurIPS 2025 ML4PS] Official implementation of the LIES Network for Symbolic Regression

[ICLR 2026] Divide and Abstract: Autoformalization via Decomposition and Abstraction Learning