5 papers
Think-Capture: Active 3D Geometry Acquisition for Spatial Reasoning in Vision-Language Models
Junjie Wang, Zhihao Yuan, Yunhan Tang +7
Vision-Language Models (VLMs) excel at 2D recognition but often fail to maintain consistent 3D relations across sparse viewpoints, leading to spatial hallucinations under occlusion…
Auditing Medical Vision-Language Models on Chest Radiographs: Estimating Reference Agreement Across Institutions
Pengyang Yu, Yiou Wang, Zhongping Dong +3
Vision-language models return structured chest-radiograph findings through interfaces exposing no confidence score, so a receiving institution cannot read off how far to trust an i…
Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning with Lightweight Annotations
Junjie Wang, Zhihao Yuan, Shuyi Jiang +5
Large language models are increasingly being applied to 3D scene understanding. However, existing 3D-aware LLMs largely operate as black boxes: they produce bounding boxes or textu…
Empowering Large Language Models with 3D Situation Awareness
Zhihao Yuan, Yibo Peng, Jinke Ren +7
Driven by the great success of Large Language Models (LLMs) in the 2D image domain, their applications in 3D scene understanding has emerged as a new trend. A key difference betwee…
PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models
Zilu Guo, Hongbin Lin, Zhihao Yuan +6
3D Multimodal Large Language Models (MLLMs) have recently made substantial advancements. However, their potential remains untapped, primarily due to the limited quantity and subopt…