-
Amazon Robotics AI
- Atlanta, GA
- pettni.github.io
Stars
Official inference repo for FLUX.1 models
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
This is the source code of our CVPR 2025 Oral paper: 3D Student Splatting and Scooping
A reimplementation of Stable Diffusion 3.5 in pure PyTorch
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
General purpose Nix configuration for macOS / NixOS (with starter templates!)
Complete 2024 to 2015 entries written in Rust for the annual Advent of Code challenge, solving 500 stars in less than 1 second.
Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/
Refine high-quality datasets and visual AI models
KISS-Matcher: Fast, Robust, and Scalable Registration + ROS2 SLAM examples
A C++ compile-time math library using generalized constant expressions
Advent of code solutions with Haskell
Mobile manipulation research tools for roboticists
An efficient C++17 GPU numerical computing library with Python-like syntax
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields. https://arxiv.org/abs/2210.13641 + Sigma-Fusion: Probabilistic Volumetric Fusion for Dense Monocular SLAM https://arxiv.org/ab…
🚀 Kick-start your C++! A template for modern C++ projects using CMake, CI, code coverage, clang-format, reproducible dependency management and much more.
A modern, fast, lightweight thread pool library based on C++20
The simplest, fastest repository for training/finetuning medium-sized GPTs.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.
A playbook for systematically maximizing the performance of deep learning models.
A library for differentiable nonlinear optimization
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
Extremely simple yet powerful header-only C++ plotting library built on the popular matplotlib