Fast and memory-efficient exact attention

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

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

【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Fast Segment Anything

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

Convolutions for Sequence Modeling

[NeurIPS 2023] UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Fast Inference in Denoising Diffusion Models via MMD Finetuning

Text-writing denoising diffusion (and much more)

Code for our NeurIPS 2022 paper

An image library for Julia

StackLife is a community-based wayfinding tool for navigating the vast resources of the combined Harvard Library System. It enables researchers, teachers, scholars, and students to find what they n…

Deep Learning for humans