A generative world for general-purpose robotics & embodied AI learning.

A project to map out the relations between different equational theories of Magmas.

Prompt, run, edit, and deploy full-stack web applications using any LLM you want!

You like pytorch? You like micrograd? You love tinygrad! ❤️

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

An open-source platform for Visual AI.

A Simulation Environment to train Robots in Large Realistic Interactive Scenes

Template for Python Projects

An Integrated Cyber-Physical Ecosystem for Autonomous Driving Research and Education

This repository contains maps from over 20 real race tracks (mainly F1 and DTM) downscaled for the usage in the F1TENTH Gym and F1TENTH Simulator.

Using Low-rank adaptation to quickly fine-tune diffusion models.

Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)

This is an unofficial implementation of the Point Transformer paper.

CUDA accelerated rasterization of gaussian splatting

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

[IPCAI'2024 (IJCARS special issue)] Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

[NeurIPS'22] An official PyTorch implementation of PTv2.

code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).

PyTorch Implementation of Diffusion Schrodinger Bridge Matching

Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

A curated list of resources for using LLMs to develop more competitive grant applications.

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

Official implementation of Fully Spiking Denoising Diffusion Implicit Models

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering