A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

Fast Multimodal LLM on Mobile Devices

Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)

CLIP inference in plain C/C++ with no extra dependencies

multimodal routing, geocoding, and map tiles

llama.cpp (GGUF LLMs) and llava.cpp (GGUF VLMs) for ROS 2

LLaVA server (llama.cpp).

The simulation system for robotic general intelligence™

[ECCV 2022] Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation

ROS2 package that integrates L3CAM sensors using L3CAM SDK

Highway Driving (project 7 of 9 from Udacity Self-Driving Car Engineer Nanodegree)

ROS2 package for the visualization of the fusion of the L3Cam device sensors

L3Cam Viewer

Repository to document and advertise our McGill Capstone Group 22 Project