ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

Translate the video from one language to another and add dubbing. 将视频从一种语言翻译为另一种语言，同时支持语音识别转录、语音合成、字幕翻译。

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality

复刻伯克利机器人关节开源

A Fully Self-Hosted Solution for Full-Duplex Voice Interaction

Visualizer for neural network, deep learning and machine learning models

⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

Umo Editor is an open-source document editor, based on Vue3 and Tiptap.

Open source AI platform for rapid development of advanced AI and AGI pipelines.

[NDSS 2025] "CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models"

Enhanced Generative Structure Prior for Text Image Super-Resolution [TPAMI]

Learning Generative Structure Prior for Blind Text Image Super-resolution [CVPR 2023]

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Hierarchical Reasoning Model Official Release

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

ONNX Model Exporter for PaddlePaddle

Pivotal Token Search

dzzoffice

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

verl: Volcano Engine Reinforcement Learning for LLMs

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.

The official repo for “WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?“

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks

A general framework for bridging LLMs and recommendation systems via reinforcement learning. https://arxiv.org/pdf/2503.24289