中文
相关论文

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

200 篇论文

Though recent advances in vision-language models (VLMs) have achieved remarkable progress across a wide range of multimodal tasks, understanding 3D spatial relationships from limited views remains a significant challenge. Previous reasoning…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Zhangquan Chen , Manyuan Zhang , Xinlei Yu , Xufang Luo , Mingze Sun , Zihao Pan , Xiang An , Yan Feng , Peng Pei , Xunliang Cai , Ruqi Huang

Vision-language models solve geometry problems with rising accuracy, yet their intermediate states remain latent and unverifiable: a relation expressed in textual reasoning or drawing code carries no guarantee that a constraint-satisfying…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Juncheng Hu , Jiawei Du , Xin Zhang , Joey Tianyi Zhou

Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Yudi Shi , Shangzhe Di , Qirui Chen , Qinian Wang , Jiayin Cai , Xiaolong Jiang , Yao Hu , Weidi Xie

Text-based Visual Question Answering~(TextVQA) aims to produce correct answers for given questions about the images with multiple scene texts. In most cases, the texts naturally attach to the surface of the objects. Therefore, spatial…

计算机视觉与模式识别 · 计算机科学 2023-06-16 Hao Li , Jinfa Huang , Peng Jin , Guoli Song , Qi Wu , Jie Chen

Mathematical geometric reasoning is essential for scientific discovery and educational development, requiring precise logic and rigorous formal verification. While recent advances in Multimodal Large Language Models (MLLMs) have improved…

人工智能 · 计算机科学 2025-08-06 Jingxuan Wei , Caijun Jia , Qi Chen , Honghao He , Linzhuang Sun , Conghui He , Lijun Wu , Bihui Yu , Cheng Tan

Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Jiaxu Wan , Xu Wang , Mengwei Xie , Hang Zhang , Mu Xu , Yang Han , Hong Zhang , Ding Yuan , Yifan Yang

Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of this failure arises before language reasoning begins: the…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Renjie Gu , Kaichen Zhou , Yan Luo , Mengyu Wang

Large language model-based agents operating in long-horizon interactions require memory systems that support temporal consistency, multi-hop reasoning, and evidence-grounded reuse across sessions. Existing approaches largely rely on…

计算与语言 · 计算机科学 2026-01-27 Juexiang Ye , Xue Li , Xinyu Yang , Chengkai Huang , Lanshun Nie , Lina Yao , Dechen Zhan

Geometric Problem Solving (GPS) poses a unique challenge for Multimodal Large Language Models (MLLMs), requiring not only the joint interpretation of text and diagrams but also iterative visuospatial reasoning. While existing approaches…

人工智能 · 计算机科学 2026-03-26 Shichao Weng , Zhiqiang Wang , Yuhua Zhou , Rui Lu , Ting Liu , Zhiyang Teng , Xiaozhang Liu , Hanmeng Liu

Multimodal large language models have demonstrated remarkable capabilities in 2D vision, motivating their extension to 3D scene understanding. Recent studies represent 3D scenes as 3D spatial videos composed of image sequences with depth…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Han Li , Zehao Huang , Jiahui Fu , Naiyan Wang , Si Liu

Recognition and reasoning are two pillars of visual understanding. However, these tasks have an imbalance in focus; whereas recent advances in neural networks have shown strong empirical performance in visual recognition, there has been…

计算机视觉与模式识别 · 计算机科学 2023-11-14 Calvin Luo , Boqing Gong , Ting Chen , Chen Sun

Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Linhui Xiao , Xiaoshan Yang , Xiangyuan Lan , Yaowei Wang , Changsheng Xu

Multimodal Large Language Models (MLLMs) have increasingly localized and interleaved visual evidence for deliberative reasoning. Grounding-based approaches typically focus on regions of interest (RoIs) by injecting cropped image patches or…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Guannan Lv , Ren Nie , Hongjian Dou , Tingting Gao

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations,…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Yuan Feng , Yue Yang , Xiaohan He , Jiatong Zhao , Jianlong Chen , Zijun Chen , Daocheng Fu , Qi Liu , Renqiu Xia , Bo Zhang , Junchi Yan

Applying AI foundation models directly to geospatial datasets remains challenging due to their limited ability to represent and reason with geographical entities, specifically vector-based geometries and natural language descriptions of…

计算与语言 · 计算机科学 2025-05-26 Yuhan Ji , Song Gao , Ying Nie , Ivan Majić , Krzysztof Janowicz

Large vision-language models have achieved remarkable progress in visual reasoning, yet most existing systems rely on single-step or text-only reasoning, limiting their ability to iteratively refine understanding across multiple visual…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Wenfang Sun , Hao Chen , Yingjun Du , Yefeng Zheng , Cees G. M. Snoek

Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning…

计算机视觉与模式识别 · 计算机科学 2025-11-24 Jiajie Guo , Qingpeng Zhu , Jin Zeng , Xiaolong Wu , Changyong He , Weida Wang

Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance…

人工智能 · 计算机科学 2025-10-28 Nannan Shi , Chuanyu Qin , Shipeng Song , Man Luo

Large language models have shown impressive results for multi-hop mathematical reasoning when the input question is only textual. Many mathematical reasoning problems, however, contain both text and image. With the ever-increasing adoption…

计算机视觉与模式识别 · 计算机科学 2023-12-20 Mehran Kazemi , Hamidreza Alvari , Ankit Anand , Jialin Wu , Xi Chen , Radu Soricut

This work tackles the problem of geo-localization with a new paradigm using a large vision-language model (LVLM) augmented with human inference knowledge. A primary challenge here is the scarcity of data for training the LVLM - existing…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Ling Li , Yu Ye , Yao Zhou , Bingchuan Jiang , Wei Zeng