3D-VLA is a framework that connects vision-language-action (VLA) models to the 3D physical world. Unlike traditional 2D models, 3D-VLA integrates 3D perception, reasoning, and action through a ...

This repository represents the official implementation of the paper titled "MangaNinja: Line Art Colorization with Precise Reference Following". Zhiheng Liu* · Ka Leong Cheng* · Xi Chen · Jie Xiao · ...