LLM-SR

github.com/deep-symbolic-mathematics/llm-sr
Idle269updated 1 year ago
Python
MIT

Scientific equation discovery and symbolic regression using LLMs, combining code generation with evolutionary search (ICLR 2025 Oral)

Sourced from

  • GitHubgithub.com/deep-symbolic-mathematics/llm-sr
  • Awesome AI for Sciencegithub.com/deep-symbolic-mathematics/llm-sr

Related resources

Curated, accuracy-first collection of benchmarks for evaluating LLMs on scientific reasoning and discovery across mathematics, physics, chemistry, materials science, biology, and agentic science (subinium, 29+ stars, MIT License, 2026)

Active293 weeks ago
TypeScript
MIT

Parallel symbolic regression network evaluating millions of expressions on GPU with automated subtree reuse, Nature Computational Science cover article (MIT, 2026)

Active233 months ago
Python
MIT

High-performance symbolic regression for discovering interpretable scientific equations from data, multi-population evolutionary search with Python/Julia backend, widely used in physics and astronomy (Cambridge, NeurIPS 2023)

Active3.6K1 month ago
Python
Apache-2.0

Curated scientific LLM papers (260+ models)

Idle6611 year ago
MIT

Comprehensive survey of foundation models for weather and climate data understanding

Idle2941 year ago

Fast, differentiable, JIT-free finite element library for PyTorch enabling GPU-native PDE solving with native autograd, tensorized assembly, and sparse linear algebra; part of the TensorGalerkin framework (218+ stars, Apache 2.0)

Active2182 weeks ago
Python
Apache-2.0