Reference PyTorch implementation and models for DINOv3

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

闻达：一个LLM调用平台。为小模型外挂知识库查找和设计自动执行动作，实现不亚于于大模型的生成能力

An open-source tool-augmented conversational language model from Fudan University

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

PyTorch code and models for the DINOv2 self-supervised learning method.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

Simple, online, and realtime tracking of multiple objects in a video sequence.

Pytorch implementation of Center Loss

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

PyTorch Implementation for Neural Graph Collaborative Filtering

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

GPT-3: Language Models are Few-Shot Learners

SOTA ReID Methods and Toolbox

Our solution to Domain Adaptive Pedestrian Re-identification in VisDA2020