PaddleOCR 3.0 (2024/2025)
github.com/paddlepaddle/paddleocrAdvanced OCR with PP-StructureV3 document parsing, 13% accuracy improvement, supports 80+ languages
Sourced from
- Awesome AI for Science — github.com/paddlepaddle/paddleocr
- GitHub — github.com/paddlepaddle/paddleocr
Related resources
SOTA multimodal document parsing with 1.2B parameters outperforming GPT-4o, converts PDFs to LLM-ready Markdown/JSON
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)
General-purpose deep learning backbone for molecular modeling
Curated list of atomistic ML projects for materials science
Curated scientific LLM papers (260+ models)
First fully customizable open-source multiagent framework automating complete research lifecycle from idea conception to LaTeX papers with dynamic workflows