ATP Tennis Rankings, Results, and Stats

[CVPR 2025] "Towards Universal Soccer Video Understanding".

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepEP: an efficient expert-parallel communication library

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Everything about the SmolLM2 and SmolVLM family of models

Pretraining code for a large-scale depth-recurrent language model

A minimal, easy-to-read PyTorch reimplementation of the Qwen2 series—without the complexity of larger frameworks.

Editor with LLM generation tree exploration

On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

Eagle Family: Exploring Model Designs, Data Recipes and Training Strategies for Frontier-Class Multimodal LLMs

小红书 (xiaohongshu, rednote) ai运营助手，包括小红书风格内容（包含图片）的生成和自动发布两部分，其中自动发布利用selenium实现RPA模拟点击，将生成内容和封面图和内容图自动发布

An implementation of the TrueSkill rating system for Python

A Comprehensive Benchmark for Document Parsing and Evaluation

Align Anything: Training All-modality Model with Feedback

The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"

This project aims to collect and collate various datasets for multimodal large model training, including but not limited to pre-training data, instruction fine-tuning data, and In-Context learning …

Deep learning software for colorizing black and white images with a few clicks.

Style-Text data synthesis tool

[Survey] Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey

Synthetic data generation pipelines for text-rich images.

💥 Blazing fast terminal file manager written in Rust, based on async I/O.

Code for the Molmo Vision-Language Model

Python tool for converting files and office documents to Markdown.

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

ETL, Analytics, Versioning for Unstructured Data

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.