2026
LLaVA³: Representing 3D Scenes Like a Cubist Painter to Boost 3D Scene Understanding of VLMs
AAAI 2026technical
Developing a multi-modal language model capable of understanding 3D scenes remains challenging due to the limited availability of 3D training data, in contrast to the abundance of 2D datasets used for vision-language models (VLMs). As an alternative, we introduce LLaVA³ (pronounced LLaVA Cube), a no