YOLOE: Real-Time Seeing Anything [ICCV 2025]

BiLSTM-CRF Model for Named Entity Recognition

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

Named Entity Recognition (LSTM + CRF) - Tensorflow

LSTM-CRF in PyTorch

Lstm-crf,Lattice-CRF,bert-ner及近年ner相关论文follow

we want to create a repo to illustrate usage of transformers in chinese

[CVPR2026] Detect Anything via Next Point Prediction

Label Rotated Rect On Images for training

Official code implementation of Slow Perception:Let's Perceive Geometric Figures Step-by-step

[ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

OCR, layout analysis, reading order, table recognition in 90+ languages

PandaOCR - 多功能OCR图文识别+翻译+朗读+弹窗+公式+表格+图床+搜图+二维码

多功能多引擎OCR文字识别、翻译、朗读、语音合成、日漫游戏机翻汉化、验证码识别、图床上传、以图搜图、扫码工具

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

A lightweight LMM-based Document Parsing Model

Trained models with fast variant of the "best" LSTM models + legacy models

Contexts Optical Compression

梦想是做出最棒的生肉翻译软件喵

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Toolkit for linearizing PDFs for LLM datasets/training

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Pioneering Automated GUI Interaction with Native Agents

TensorFlow code and pre-trained models for BERT

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.