vision-transformer

OpenMMLab Detection Toolbox and Benchmark

pix2tex: Using a ViT to convert images of equations into LaTeX code.

This repository contains demos I made with the Transformers library by HuggingFace.

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

OpenMMLab Pre-training Toolbox and Benchmark

Scenic: A Jax Library for Computer Vision Research and Beyond

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

An all-in-one toolkit for computer vision

Get clean data from tricky documents, powered by vision-language models ⚡

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

This repository provides programs to build Retrieval Augmented Generation (RAG) code for Generative AI with LlamaIndex, Deep Lake, and Pinecone leveraging the power of OpenAI and Hugging Face models for generation and evaluation.

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).