-
South China University of Technology
- GuangZhou
Starred repositories
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
[EMNLP 2025] Code for paper "Table-R1: Inference-Time Scaling for Table Reasoning"
verl: Volcano Engine Reinforcement Learning for LLMs
Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)
📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.
开源易用的中文离线OCR,识别率媲美大厂,并且提供了易用的web页面及web的接口,方便人类日常工作使用或者其他程序来调用~
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
Official git for "TabuLa: Harnessing Language Models for Tabular Data Synthesis"
Official git for "CTAB-GAN: Effective Table Data Synthesizing"
This repo is the official implementation of the ACMMM 2025 paper "G2LFormer: Global-to-Local Query Enhancement for Robust Table Structure Recognition"
Dataset and Code for our ACL 2024 paper: "Multimodal Table Understanding". We propose the first large-scale Multimodal IFT and Pre-Train Dataset for table understanding and develop a generalist tab…
[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Twitter Crawler Core and some based apps
Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free
Free ChatGPT&DeepSeek API Key,免费ChatGPT&DeepSeek API��免费接入DeepSeek API和GPT4 API,支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。
CMMLU: Measuring massive multitask language understanding in Chinese
Measuring Massive Multitask Language Understanding | ICLR 2021

