PaddleOCR
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.
- 93k
- Python
- Apache-2.0
- 2 mo ago
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.
Toward High-Accuracy Open-Source Biomolecular Structure Prediction.
A curated list of awesome AI tools, libraries, papers, datasets, and frameworks that accelerate scientific discovery โ from physics and chemistry to biology, materials, and beyond.
GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).
๐๐๐A 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.
๐ A ranked list of awesome atomistic machine learning projects โ๏ธ๐งฌ๐.
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.
JEPA-Anything: Learning Predictive Models across Different Worlds
The resources of LucaOne, including: the model code, training scripts, embedding inference code, and trained checkpoints.
[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models
๐ฆ ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery
A fast, differentiable, JIT-free, debugging-friendly finite element library for PyTorch.
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
A general AI agent framework that can be adapted to various tasks and environments.
[ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
A Text-guided Protein Design Framework, Nat Mach Intell 2025 (https://www.nature.com/articles/s42256-025-01011-z)
Open-source AI4S workspace connecting people, agents, and compute through project-based collaboration, proactive workflows, and distributed tasks.
A command line and Python toolkit featured artificial intelligence ร ab initio for complex chemistry systems research.
A unified evaluation toolkit and leaderboard for rigorously assessing the scientific intelligence of large language and visionโlanguage models across the full research workflow.
LucaVirus: Modeling the Evolutionary and Functional Landscape of Viruses with a Unified Genome-Protein Language Model
Easy wins for reproducible machine learning in research, as a Jupyter Book tutorial.
The official code for "TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation"
[๐ง๐๐ญ๐ฎ๐ซ๐ ๐ฆ๐๐๐ก๐ข๐ง๐ ๐ข๐ง๐ญ๐๐ฅ๐ฅ๐ข๐ ๐๐ง๐๐] ImmunoStruct enables multimodal deep learning for immunogenicity prediction