7 papers
GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models
Rong Li, Shijie Li, Jiangyong Huang +7
Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models recover this structure from RGB…
Zero-Shot 3D Visual Grounding from Vision-Language Models
Rong Li, Shijie Li, Lingdong Kong +2
3D Visual Grounding (3DVG) seeks to locate target objects in 3D scenes using natural language descriptions, enabling downstream applications such as augmented reality and robotics.…
Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration
Zeying Gong, Rong Li, Tianshuai Hu +6
Deployable service and delivery robots struggle to navigate multi-floor buildings to reach object goals, as existing systems fail due to single-floor assumptions and requirements f…
Global-Aware Monocular Semantic Scene Completion with State Space Models
Shijie Li, Zhongyao Cheng, Rong Li +4
Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image, enabling diverse real-world applications. However, existing methods a…
SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding
Rong Li, Shijie Li, Lingdong Kong +2
3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG appro…
TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation
Rong Li, ShiJie Li, Xieyuanli Chen +3
LiDAR semantic segmentation plays a crucial role in enabling autonomous driving and robots to understand their surroundings accurately and robustly. A multitude of methods exist wi…
An Examination of the Compositionality of Large Generative Vision-Language Models
Teli Ma, Rong Li, Junwei Liang
With the success of Large Language Models (LLMs), many Generative Vision-Language Models (GVLMs) have been constructed via multimodal instruction tuning. However, the performance o…