junha1125

img2dataset

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

LWM

pycocoevalcap

Python 3 support for the MS COCO caption evaluation tools

LMOps

General technology for enabling AI capabilities w/ LLMs and MLLMs

minillm

MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs

LLaVA

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

FiGCLIP

Official repository for FiGCLIP

LLaVA-Med

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Awesome-Knowledge-Distillation-of-LLMs

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

ViECap

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning, ICCV 2023

recognize-anything

Codebase for the Recognize Anything Model (RAM)

smallcap

SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation

CLIP_prefix_caption

Simple image captioning model

recognize-anything

Open-source and strong foundation image recognition models.

MIC

[CVPR23] Official Implementation of MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation

corenet

CoreNet: A library for training deep neural networks

clip-distillation

Zero-label image classification via OpenCLIP knowledge distillation

Awesome-Multimodal-Large-Language-Models

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

ReCLIP_WACV

DreamLIP

[ECCV 2024] Official PyTorch implementation of DreamLIP: Language-Image Pre-training with Long Captions

source-free-domain-adaptation

Awesome-Mamba-Papers

Awesome Papers related to Mamba.

Awesome-Robotics-Foundation-Models

home-robot

Mobile manipulation research tools for roboticists

ml-mobileclip

This repository contains the official implementation of the research paper, "MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training" CVPR 2024

RIPU

[CVPR 2022 Oral] Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation https://arxiv.org/abs/2111.12940

cs229-2018-autumn

All notes and materials for the CS229: Machine Learning course by Stanford University

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

BECoTTA

Code for "BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation [ICML2024]".

PETL-ViT

[ICCV 2023] Binary Adapters, [AAAI 2023] FacT, [Tech report] Convpass