PaddleOCR 3.0 (2024/2025)

github.com/paddlepaddle/paddleocr
Active81.3Kupdated 1 week ago
Python
Apache-2.0

Advanced OCR with PP-StructureV3 document parsing, 13% accuracy improvement, supports 80+ languages

Sourced from

  • Awesome AI for Sciencegithub.com/paddlepaddle/paddleocr
  • GitHubgithub.com/paddlepaddle/paddleocr

Related resources

SOTA multimodal document parsing with 1.2B parameters outperforming GPT-4o, converts PDFs to LLM-ready Markdown/JSON

Active65.9K1 week ago
Python
NOASSERTION

Self-evolving AI scientist with 6 specialized sub-agents (plan/research/code/debug/analyze/write) and persistent memory, #1 on DeepResearch Bench II and AstaBench, supporting multi-provider LLMs and multi-channel deployment (Apache 2.0, 2026)

Active3.3K1 week ago
Python
Apache-2.0

General-purpose deep learning backbone for molecular modeling

Stale2.5K2 years ago
Python
MIT

Curated list of atomistic ML projects for materials science

Active6911 week ago
CC-BY-SA-4.0

Curated scientific LLM papers (260+ models)

Idle66011 months ago
MIT

First fully customizable open-source multiagent framework automating complete research lifecycle from idea conception to LaTeX papers with dynamic workflows

Active5604 weeks ago
Python
MIT