Reference implementation for DPO (Direct Preference Optimization)

Use of Attention Gates in a Convolutional Neural Network / Medical Image Classification and Segmentation

The simplest, fastest repository for training/finetuning medium-sized xLSTMs.

Resources about xLSTM by Sepp Hochreiter

Pytorch implementation of the xLSTM model by Beck et al. (2024)

This code implements sparse coding in PyTorch with GPU support.

Experimental implementation for a sparse-dictionary based version of the VQ-VAE2 paper

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

Unifying Multimodal Variational Autoencoders (VAEs) in Pytorch

This is ECGdeli - A selection of delicious algorithms for ECG delineation

Pytorch implementations of generative models: VQVAE2, AIR, DRAW, InfoGAN, DCGAN, SSVAE

Set up a modern web app by running one command.

A minimal 3D Gaussian splatting implementation with depth and density regularization

CUDA accelerated rasterization of gaussian splatting

COLMAP - Structure-from-Motion and Multi-View Stereo

Embodied Chain of Thought: A robotic policy that reason to solve the task.

Official Pytorch implementation of " Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation? "

Replacing Mamba with xLSTM! It works better. We show that xLSTM-Unet can be an effective semantic segmentation backbone.

Sparse Autoencoder for Mechanistic Interpretability

ECG time-series augmentations library

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

SIMD Library for Evaluating Elementary Functions, vectorized libm and DFT

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

Intel® RealSense™ SDK

Repository accompanying the paper "Uncertainty estimation for deep learning-based automated analysis of 12-lead electrocardiograms", accepted in European Heart Journal Digital Health.