A curated list of awesome LLM for Autonomous Driving resources (continually updated)

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

Official repo for "iVideoGPT: Interactive VideoGPTs are Scalable World Models", https://arxiv.org/abs/2405.15223

LLM training in simple, raw C/Metal Shading Language

WIP

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Swift Package to implement a transformers-like API in Swift

Tcode Input Method for macOS

Japanese input method for fcitx5, powered by azooKey engine

Benkei(弁慶)は薙刀式かな入力のMac OS実装です。

A macOS kaomoji palette. (＾▽＾)

LLM training in simple, raw C/CUDA

Tools for merging pretrained large language models.

Ongoing research training Mixture of Expert models.

Ongoing Research Project for continaual pre-training LLM(dense mode)

[ICLR 2023] S-NeRF: Neural Radiance Fields for Street Views

This repository is used to collect NeRF papers on autonomous driving

ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Scratch React implementation on Swift for Wasm

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

[CVPR 2024] DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

This project aims to enable language model inference on FPGAs, supporting AI applications in edge devices and environments with limited resources.

NeRFチュートリアル

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

A cross compile environment Docker image, can be used like docker multiarch image without speed penalty.

Yet Another macOS SKK Input Method

MetaDrive: Open-source driving simulator