Mehran Maghoumi

Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

Pytorch project accompanying the paper "A Unified Perspective on CTC and SDTW using Differentiable DTW", submitted to IEEE TASLPRO, 2025

An implementation of SoftDTW for PyTorch.

Adds support for NVIDIA Jetson platform

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

.NET Wrapper for Carve's CSG and mesh boolean operations

Second-order differentiable PyTorch GRUs in JIT with TorchScript

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Scalable toolkit for data curation

Deep Non-Adversarial Gesture Generation

Deep Gesture Recognition Utility

librealsense with CUDA

No description provided.

Visualization toolkit based on OpenTK

An efficient implementation of HoG feature extractor in CUDA

Carve is a fast, robust constructive solid geometry library. (fork from https://code.google.com/p/carve/)

Realtime Unsupervised Object Classification and Tracking using Genetic Programming and NVIDIA CUDA

No description provided.

A Lightweight Sketch-Based Shape Retrieval Framework

A Framework for the Volumetric Integration of Depth Images

CUDA Extensions for Genetic Programming in ECJ

RamDrive that is backed by GPU Memory

No description provided.

Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in 3D.

Math.NET Spatial

Provides transparent scalability for using multiple GPUs with JCuda