#Ai4science
Showing 26 of 26 repositories tagged #ai4science, ranked by stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
🔬 Harness Vibe Research with Self-evolving AI Scientists
Graphormer is a general-purpose deep learning backbone for molecular modeling.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.
MatterSim: A deep learning atomistic model across elements, temperatures and pressures.
The resources of LucaOne, including: the model code, training scripts, embedding inference code, and trained checkpoints.
A language agent gym with challenging scientific tasks
Code and datasets for paper "K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization" in WSDM-2024
A fast, differentiable, JIT-free, debugging-friendly finite element library for PyTorch.
🦞 ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
A Text-guided Protein Design Framework, Nat Mach Intell 2025 (https://www.nature.com/articles/s42256-025-01011-z)
TorchLean is the first unified Lean 4 framework for neural-network specification, execution, and verification.
CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
[ICML 2025] 🧬 ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation
A unified evaluation toolkit and leaderboard for rigorously assessing the scientific intelligence of large language and vision–language models across the full research workflow.
[NeurIPS 2023] This is the official code for the paper "TPSR: Transformer-based Planning for Symbolic Regression"
LucaVirus: Modeling the Evolutionary and Functional Landscape of Viruses with a Unified Genome-Protein Language Model
A curated list of awesome AI and Bioinformatics.
ChatCell: Facilitating Single-Cell Analysis with Natural Language
[PNAS 2025] Code of "Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design".
Research Math Agents, Official code release for our paper RMA
MatAgent: A generative framework for interpretable and targeted inorganic materials design using diffusion-based generation, property prediction, and LLM-driven reasoning.
A generative model for phenotypic-based drug discovery