中文
相关论文

相关论文: Why Far Looks Up: Probing Spatial Representation i…

200 篇论文

Recent advancements in Vision Language Models (VLMs) have expanded their capabilities to interactive agent tasks, yet existing benchmarks remain limited to single-agent or text-only environments. In contrast, real-world scenarios often…

人工智能 · 计算机科学 2026-04-14 Zelai Xu , Zhexuan Xu , Xiangmin Yi , Huining Yuan , Mo Guang , Kaiwen Long , Xinlei Chen , Yi Wu , Chao Yu , Yu Wang

Genuine spatial reasoning relies on the capacity to construct and manipulate coherent internal spatial representations, often conceptualized as mental models, rather than merely processing surface linguistic associations. While large…

人工智能 · 计算机科学 2026-03-04 Peiyao Jiang , Zequn Qin , Xi Li

Recently, the remarkable success of ChatGPT has sparked a renewed wave of interest in artificial intelligence (AI), and the advancements in visual language models (VLMs) have pushed this enthusiasm to new heights. Differring from previous…

人工智能 · 计算机科学 2025-01-03 Lijie Tao , Haokui Zhang , Haizhao Jing , Yu Liu , Dawei Yan , Guoting Wei , Xizhe Xue

Humans can imagine and manipulate visual images mentally, a capability known as spatial visualization. While many multi-modal benchmarks assess reasoning on visible visual information, the ability to infer unseen relationships through…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Siting Wang , Minnan Pei , Luoyang Sun , Cheng Deng , Yuchen Li , Kun Shao , Zheng Tian , Haifeng Zhang , Jun Wang

Vision-language foundation models (VLMs) have shown impressive performance in guiding image generation through text, with emerging applications in medical imaging. In this work, we are the first to investigate the question: 'Can fine-tuned…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Amar Kumar , Anita Kriz , Barak Pertzov , Tal Arbel

Pre-trained foundation models have recently made significant progress in table-related tasks such as table understanding and reasoning. However, recognizing the structure and content of unstructured tables using Vision Large Language Models…

计算机视觉与模式识别 · 计算机科学 2025-06-02 Yitong Zhou , Mingyue Cheng , Qingyang Mao , Feiyang Xu , Xin Li

Vision-Language Models (VLMs) have shown great success as foundational models for downstream vision and natural language applications in a variety of domains. However, these models are limited to reasoning over objects and actions currently…

机器人学 · 计算机科学 2025-06-13 Zachary Chavis , Hyun Soo Park , Stephen J. Guy

Vision-Language Models (VLMs) excel at high-level scene understanding but falter on fine-grained perception tasks requiring precise localization. This failure stems from a fundamental mismatch, as generating exact numerical coordinates is a…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Peng Liu , Haozhan Shen , Chunxin Fang , Zhicheng Sun , Jiajia Liao , Tiancheng Zhao

Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Lama Moukheiber , Caleb M. Yeung , Haotian Xue , Alec Helbling , Zelin Zhao , Yongxin Chen

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perception, even when the required information is still present…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Haz Sameen Shahgir , Xiaofu Chen , Yu Fu , Erfan Shayegani , Nael Abu-Ghazaleh , Yova Kementchedjhieva , Yue Dong

Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a novel approach to address this gap by translating physical-world…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Xiyang Wu , Zongxia Li , Jihui Jin , Guangyao Shi , Gouthaman KV , Vishnu Raj , Nilotpal Sinha , Jingxi Chen , Fan Du , Dinesh Manocha

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing…

人工智能 · 计算机科学 2025-11-25 Antonia Wüst , Wolfgang Stammer , Hikaru Shindo , Lukas Helff , Devendra Singh Dhami , Kristian Kersting

Multimodal Large Language Models (MLLMs) show reasoning promise, yet their visual perception is a critical bottleneck. Strikingly, MLLMs can produce correct answers even while misinterpreting crucial visual elements, masking these…

计算机视觉与模式识别 · 计算机科学 2025-12-11 Aditya Kanade , Tanuja Ganu

A reliable driving assistant should provide consistent responses based on temporally grounded reasoning derived from observed information. In this work, we investigate whether Vision-Language Models (VLMs), when applied as driving…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Chun-Peng Chang , Chen-Yu Wang , Holger Caesar , Alain Pagani

Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing what is visible, it remains unclear whether they can infer…

计算机视觉与模式识别 · 计算机科学 2026-05-25 Jianshu Zhang , Chengxuan Qian , Haosen Sun , Haoran Lu , Dingcheng Wang , Letian Xue , Han Liu

Spatial expressions in situated communication can be ambiguous, as their meanings vary depending on the frames of reference (FoR) adopted by speakers and listeners. While spatial language understanding and reasoning by vision-language…

计算与语言 · 计算机科学 2025-04-18 Zheyuan Zhang , Fengyuan Hu , Jayjun Lee , Freda Shi , Parisa Kordjamshidi , Joyce Chai , Ziqiao Ma

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts…

计算与语言 · 计算机科学 2026-01-09 Ziteng Wang , Yujie He , Guanliang Li , Siqi Yang , Jiaqi Xiong , Songxiang Liu

Spatial intelligence in vision-language models (VLMs) attracts research interest with the practical demand to reason in the 3D world.Despite promising results, most existing methods follow the conventional 2D pipeline in VLMs and use…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Jerry Jiang , Haowen Sun , Denis Gudovskiy , Yohei Nakata , Tomoyuki Okuno , Kurt Keutzer , Wenzhao Zheng

Spatial reasoning is a fundamental capability of multimodal large language models (MLLMs), yet their performance in open aerial environments remains underexplored. In this work, we present Open3D-VQA, a novel benchmark for evaluating MLLMs'…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Weichen Zhang , Zile Zhou , Xin Zeng , Xuchen Liu , Jianjie Fang , Chen Gao , Yong Li , Jinqiang Cui , Xinlei Chen , Xiao-Ping Zhang

Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Sungjune Park , Yeongyun Kim , Se Yeon Kim , Yong Man Ro