Extreme Image Compression using Fine-tuned VQGAN Models (DCC 2024)

TensorFlow implementation of EGIC (EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation, ECCV 2024)

Official implementation of "Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model" (WACV2024).

An open-source implementaion for fine-tuning Qwen2-VL series by Alibaba Cloud.

✨✨ MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Accepted by IJCAI-24 Survey Track

中国大模型

Awesome-LLM: a curated list of Large Language Model

Pytorch implementation of the paper "You Can Mask More For Extremely Low-Bitrate Image Compression".

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

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

✨✨Latest Advances on Multimodal Large Language Models

Vector (and Scalar) Quantization, in Pytorch

[CVPR2023] All in One: Exploring Unified Video-Language Pre-training

ArcFace unofficial Implemented in Tensorflow 2.0+ (ResNet50, MobileNetV2). "ArcFace: Additive Angular Margin Loss for Deep Face Recognition" Published in CVPR 2019. With Colab.

Research code for pixel-based encoders of language (PIXEL)

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

(TPAMI 2024) A Survey on Open Vocabulary Learning

ICCV 2023 Paper Global Features are All You Need for Image Retrieval and Reranking Official Repository

MLCD & UNICOM : Large-Scale Visual Representation Model

All-In-One VLM: Image + Video + Transfer to Other Languages / Domains (TPAMI 2023)

X-VLM: Multi-Grained Vision Language Pre-Training (ICML 2022)

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

A Pytorch Implementation of a continuously rate adjustable learned image compression framework.

Repository of the NeurIPS'22 paper "Selective compression learning of latent representations for variable-rate image compression" pytorch implementation

A collection of tools for neural compression enthusiasts.