Xinyu Huang

Open-source and strong foundation image recognition models.

Code for paper: Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

Code for paper: IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training [ACM MM2022]

verl: Volcano Engine Reinforcement Learning for LLMs

High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning

No description.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

No description.

Open-source unified multimodal model

No description.

Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

Accelerating the development of large multimodal models (LMMs) with lmms-eval

Object Detection Metrics

No description.

No description.

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

Marrying Grounding DINO with Segment Anything & Tag2Text & Stable Diffusion & BLIP & Whisper - Automatically Recognize, Detect, Segment and Generate Anything with Image, Text, and Speech Inputs

The official implementation of "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Official implementation of paper "Query2Label: A Simple Transformer Way to Multi-Label Classification".

Code for ALBEF: a new vision-language pre-training method

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

No description.

Code implementation for paper "On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals".

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Contrastive Language-Image Pretraining

This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

一键平安复旦小脚本，自动化快速上报疫情