7 papers
3D-Aware VLMs with Implicit and Explicit Geometries
Wenhao Li, Xueying Jiang, Quanhao Qian +4
Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial unde…
GeoProp: Grounding Robot State in Vision for Generalist Manipulation
Guoyang Zhao, Quanhao Qian, Gongjie Zhang +5
Proprioception is fundamental to robotic manipulation, yet standard fusion methods often treat it as an isolated vector lacking explicit alignment with visual tokens. Without a dir…
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
Wenhao Li, Xueying Jiang, Quanhao Qian +4
Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing vie…
Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs
Xueying Jiang, Wenhao Li, Quanhao Qian +4
3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera intrinsic ambiguity: the same…
STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
Wenhao Li, Xueying Jiang, Gongjie Zhang +3
4D point cloud videos capture rich spatial and temporal dynamics of scenes which possess unique values in various 4D understanding tasks. However, most existing methods work in the…
On the Generalization Capacities of MLLMs for Spatial Intelligence
Gongjie Zhang, Wenhao Li, Quanhao Qian +4
Multimodal Large Language Models (MLLMs) that directly process RGB inputs for tasks like 3D localization and navigation have shown remarkable potential. However, we argue that thes…