z-fabian

diffusiondb

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

InterpretDiffusion

[CVPR 2024] Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation

SpLiCE

Sparse Linear Concept Embeddings

sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability

sparse_coding

Using sparse coding to find distributed representations used by neural networks.

MediConfusion

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

textgrad

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

cryoet-deepfinder

Macromolecules Localization and Identification in 3D Cellular Cryo-Electron Tomograms

llm_benchmarks

A collection of benchmarks and datasets for evaluating LLM.

ProLLaMA

A Protein Large Language Model for Multi-Task Protein Language Processing

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

topaz

Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with DNNs.

InternVL

[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

MultiDiffusion

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

CLIP_benchmark

CLIP-like model evaluation

whatsup_vlms

Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".

YOLOv6

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

detr

End-to-End Object Detection with Transformers

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

tomotwin-cryoet

cryo-ET particle picking by representation and metric learning

RecvisProject

In this project, we propose to study Vision Transformers trained using the Barlow Twins self-supervised method, and compare the results with DINO. We demonstrate the effectiveness of the Barlow Twins method by showing that networks pretrained on the small PASCAL VOC 2012 dataset are able to generalize well. Authors: Apavou Clément & Zucker Arthur

Awesome-Foundation-Models

A curated list of foundation models for vision and language tasks

devit

CoRL 2024

finetune-anything

Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scenarios

DCI

Densely Captioned Images (DCI) dataset repository.

fiftyone

Refine high-quality datasets and visual AI models

img2dataset

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

USCthesis

a LaTeX style for theses and dissertations at USC

RadFM

The official code for "Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data".