中文
相关论文

相关论文: GeoWeaver: Grounding Visual Tokens with Geometric …

200 篇论文

Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of…

计算机视觉与模式识别 · 计算机科学 2025-12-24 Shengchao Zhou , Yuxin Chen , Yuying Ge , Wei Huang , Jiehong Lin , Ying Shan , Xiaojuan Qi

Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Wenbo Hu , Jingli Lin , Yilin Long , Yunlong Ran , Lihan Jiang , Yifan Wang , Chenming Zhu , Runsen Xu , Tai Wang , Jiangmiao Pang

When thinking with images, humans rarely rely on a single glance: they revisit visual evidence while reasoning. In contrast, most Multimodal Language Models encode an image once to key-value cache and then reason purely in text, making it…

计算与语言 · 计算机科学 2026-05-08 Jiwan Chung , Junhyeok Kim , Siyeol Kim , Jaeyoung Lee , Min Soo Kim , Youngjae Yu

Despite their proficiency in general tasks, Multi-modal Large Language Models (MLLMs) struggle with automatic Geometry Problem Solving (GPS), which demands understanding diagrams, interpreting symbols, and performing complex reasoning. This…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Renqiu Xia , Mingsheng Li , Hancheng Ye , Wenjie Wu , Hongbin Zhou , Jiakang Yuan , Tianshuo Peng , Xinyu Cai , Xiangchao Yan , Bin Wang , Conghui He , Botian Shi , Tao Chen , Junchi Yan , Bo Zhang

While Vision-Language Models (VLMs) have significantly advanced remote sensing interpretation, enabling them to perform complex, step-by-step reasoning remains highly challenging. Recent efforts to introduce Chain-of-Thought (CoT) reasoning…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Lang Sun , Ronghao Fu , Zhuoran Duan , Haoran Liu , Xueyan Liu , Bo Yang

Despite recent advances in multimodal reasoning, representing auxiliary geometric constructions remains a fundamental challenge for multimodal large language models (MLLMs). Such constructions are absent from the original diagram and must…

计算机视觉与模式识别 · 计算机科学 2026-03-13 Haiying Xu , Zihan Wang , Song Dai , Zhengxuan Zhang , Kairan Dou , Xuming Hu

Language-goal aerial navigation requires UAVs to localize targets in the complex outdoors, such as urban blocks based on textual instructions. The indoor methods are often hard to scale to urban scenes due to ambiguous objects, limited…

机器人学 · 计算机科学 2026-03-10 Haotian Xu , Yue Hu , Chen Gao , Zhengqiu Zhu , Yong Zhao , Yong Li , Quanjun Yin

Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens and lack explicit spatial structure, resulting in substantial computational overhead…

计算机视觉与模式识别 · 计算机科学 2026-05-22 Jiahao Yang , Zihan Wang , Xiangyang Li , Xing Zhu , Yujun Shen , Yinghao Xu , Shuqiang Jiang

Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, leading to accumulated errors in object…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Zhiheng Liu , Xueqing Deng , Shoufa Chen , Angtian Wang , Qiushan Guo , Mingfei Han , Zeyue Xue , Mengzhao Chen , Ping Luo , Linjie Yang

Geometry problem-solving (GPS), a challenging task requiring both visual comprehension and symbolic reasoning, effectively measures the reasoning capabilities of multimodal large language models (MLLMs). Humans exhibit strong reasoning…

计算与语言 · 计算机科学 2025-04-25 Liangyu Xu , Yingxiu Zhao , Jingyun Wang , Yingyao Wang , Bu Pi , Chen Wang , Mingliang Zhang , Jihao Gu , Xiang Li , Xiaoyong Zhu , Jun Song , Bo Zheng

Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding. Recent studies have sought to enhance the reasoning capabilities of remote sensing MLLMs, typically through cold-start…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Di Wang , Shunyu Liu , Wentao Jiang , Fengxiang Wang , Yi Liu , Xiaolei Qin , Zhiming Luo , Chaoyang Zhou , Haonan Guo , Jing Zhang , Bo Du , Dacheng Tao , Liangpei Zhang

Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…

机器人学 · 计算机科学 2025-11-03 Simindokht Jahangard , Mehrzad Mohammadi , Abhinav Dhall , Hamid Rezatofighi

Three-dimensional geospatial analysis is critical for applications in urban planning, climate adaptation, and environmental assessment. However, current methodologies depend on costly, specialized sensors, such as LiDAR and multispectral…

计算机视觉与模式识别 · 计算机科学 2025-12-23 Mai Tsujimoto , Junjue Wang , Weihao Xuan , Naoto Yokoya

Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. However, applying MLLMs to geometry problem solving (GPS)…

计算与语言 · 计算机科学 2025-04-18 Yicheng Pan , Zhenrong Zhang , Pengfei Hu , Jiefeng Ma , Jun Du , Jianshu Zhang , Quan Liu , Jianqing Gao , Feng Ma

AI-driven geometric problem solving is a complex vision-language task that requires accurate diagram interpretation, mathematical reasoning, and robust cross-modal grounding. A foundational yet underexplored capability for this task is the…

机器学习 · 计算机科学 2025-09-26 Bing Liu , Wenqiang Yv , Xuzheng Yang , Shichang Wang , Junzhuo Liu , Peng Wang , Guoqing Wang , Yang Yang , Heng Tao Shen

Visual grounding (VG) aims to establish fine-grained alignment between vision and language. Ideally, it can be a testbed for vision-and-language models to evaluate their understanding of the images and texts and their reasoning abilities…

计算机视觉与模式识别 · 计算机科学 2023-07-24 Zhihong Chen , Ruifei Zhang , Yibing Song , Xiang Wan , Guanbin Li

Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries, which is crucial for embodied AI applications such as autonomous navigation, robotics, and augmented reality. Learning 3D language…

计算机视觉与模式识别 · 计算机科学 2025-07-10 Zhenyang Liu , Sixiao Zheng , Siyu Chen , Cairong Zhao , Longfei Liang , Xiangyang Xue , Yanwei Fu

Large vision language models exhibit notable limitations on Geometry Problem Solving (GPS) because of their unreliable diagram interpretation and pure natural-language reasoning. A recent line of work mitigates this by using symbolic…

机器学习 · 计算机科学 2025-08-13 Tianyun Yang , Yunwen Li , Ziniu Li , Zhihang Lin , Ruoyu Sun , Tian Ding

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities. However, they struggle to perceive fine-grained geometric structures, constraining their ability of geometric understanding…

计算机视觉与模式识别 · 计算机科学 2026-03-30 Jiayin Sun , Caixia Sun , Boyu Yang , Hailin Li , Xiao Chen , Yi Zhang , Errui Ding , Liang Li , Chao Deng , Junlan Feng

Recent advancements in reinforcement learning (RL) have enhanced the reasoning abilities of large language models (LLMs), yet the impact on multimodal LLMs (MLLMs) is limited. Particularly in vision-intensive tasks like geometric reasoning,…

计算与语言 · 计算机科学 2025-09-23 Guizhen Chen , Weiwen Xu , Hao Zhang , Hou Pong Chan , Deli Zhao , Anh Tuan Luu , Yu Rong