Making large AI models cheaper, faster and more accessible

Official Code for DragGAN (SIGGRAPH 2023)

PyTorch implementations of Generative Adversarial Networks.

A paper list of object detection using deep learning.

A PyTorch Implementation of Single Shot MultiBox Detector

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

Official implementations for paper: Anydoor: zero-shot object-level image customization

Model summary in PyTorch similar to `model.summary()` in Keras

RepVGG: Making VGG-style ConvNets Great Again

A PyTorch Library for Meta-learning Research

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

PANet for Instance Segmentation and Object Detection

Speed up Stable Diffusion with this one simple trick!

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

A fast and differentiable model predictive control (MPC) solver for PyTorch.

[ICCV-2021] TransReID: Transformer-based Object Re-Identification

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

Fast Diffusion Models with Transformers

Pytorch implementation of Hinton's Dynamic Routing Between Capsules

PyTorch Implementation for Deep Metric Learning Pipelines

EAGLE: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024

[NeurIPS-2020] Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID.

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

AI-Generated Presets for Faithful 4K Color Style Transfer in Real Time [CVPR 2023]