Haotian-Zhang

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT better.

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LLaVA

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

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

GroundingDINO

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

tpu

Reference models and tools for Cloud TPUs.

Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

GPT-4-LLM

Instruction Tuning with GPT-4

open_flamingo

An open-source framework for training large multimodal models.

t5x

EVA

EVA Series: Visual Representation Fantasies from BAAI

mPLUG-Owl

mPLUG-Owl & mPLUG-Owl2: Modularized Multimodal Large Language Model

GLIGEN

Open-Set Grounded Text-to-Image Generation

Word-As-Image

MM-REACT

Official repo for MM-REACT

mmc4

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Co-DETR

[ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

pix2seq

Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)

U-ViT

A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".

GFocal

Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection, NeurIPS2020

copy-paste-aug

Copy-paste augmentation for segmentation and detection tasks

MIMDet

[ICCV 2023] You Only Look at One Partial Sequence

VLDet

[ICLR 2023] PyTorch implementation of VLDet （https://arxiv.org/abs/2211.14843）

gRefCOCO

A benchmark dataset for GRES and GREC [CVPR2023 Highlight]

praxis

react

REACT (CVPR 2023, Highlight 2.5%)

videoCC-data

VideoCC is a dataset containing (video-URL, caption) pairs for training video-text machine learning models. It is created using an automatic pipeline starting from the Conceptual Captions Image-Captioning Dataset.

VaLM

VaLM: Visually-augmented Language Modeling. ICLR 2023.