We propose a zero-shot object-goal navigation framework by constructing an online 3D scene graph to prompt LLMs. Our method can be directly applied to different kinds of scenes and categories without ...

Abstract: Environment representations endowed with sophisticated semantics are pivotal for facilitating seamless interaction between robots and humans, enabling them to effectively carry out various ...

Chemical reactions happen when atoms rearrange themselves, turning molecules into something new—like making medicines or new materials. But current AI methods still aren't good at guessing how ...

Abstract: In this paper, we explore an open research problem concerning the reconstruction of 3D scenes from images. Recent methods have adopt 3D Gaussian Splatting (3DGS) to produce 3D scenes due to ...