AI 大模型

视觉大模型 / VLM

视觉语言模型、视觉推理、视觉问答、图文理解和视觉 grounding。

2025-10-15 至 2025-10-15 共收录 5 篇信号源：cs.CV, cs.AI, cs.LG

1. 视觉推理 5 篇

2510.12400 2025-10-15 cs.CV 83%

Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agenda

André Torneiro, Diogo Monteiro, Paulo Novais, Pedro Rangel Henriques, Nuno F. Rodrigues

机构 * ALGORITMI Research Centre/LASI（ALGORITMI研究机构/LASI）； University of Minho（明霍大学）； Logimade（Logimade公司）； INESC TEC（INESC TEC研究机构）； Ai, School of Technology（2Ai技术学院）； IPCA

专题命中视觉推理：vision-language model(title,abstract)；VLM(abstract)；分类 cs.CV

Comments 44 pages

2510.12190 2025-10-15 cs.CV 79%

Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos

Shingo Yokoi, Kento Sasaki, Yu Yamaguchi

机构 * Turing Inc.（图灵公司）

专题命中视觉推理：vision-language model(title,abstract)；分类 cs.CV

Comments 2nd Place Winner, ICCV 2025 2COOOL Competition

2509.25026 2025-10-15 cs.CV 70%

GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning

Mustansar Fiaz, Hiyam Debary, Paolo Fraccaro, Danda Paudel, Luc Van Gool, Fahad Khan, Salman Khan

机构 * IBM Research（IBM研究院）； INSAIT ； ETH Zürich（苏黎世联邦理工学院）； MBZUAI（穆斯林人工智能研究所）； Linköping University（林雪平大学）； ANU Australia（澳大利亚国立大学）

专题命中视觉推理：vision language model(abstract)；grounding(abstract)；分类 cs.CV

Comments Tables 6 and Figures 8. https://mustansarfiaz.github.io/GeoVLM-R1/

2510.11996 2025-10-15 cs.CV 57%

Prompt-Guided Spatial Understanding with RGB-D Transformers for Fine-Grained Object Relation Reasoning

Tanner Muturi, Blessing Agyei Kyem, Joshua Kofi Asamoah, Neema Jakisa Owor, Richard Dyzinela, Andrews Danyo, Yaw Adu-Gyamfi, Armstrong Aboah

机构 * University of Missouri–Columbia（密苏里大学哥伦比亚分校）； North Dakota State University（北达科他州立大学）； Texas A&M（德克萨斯农工大学）

专题命中视觉推理：grounding(abstract)；分类 cs.CV

Comments The paper was accepted at ICCV Conference 2025

2507.07984 2025-10-15 cs.CV 57%

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

Jingli Lin, Chenming Zhu, Runsen Xu, Xiaohan Mao, Xihui Liu, Tai Wang, Jiangmiao Pang

机构 * Shanghai AI Laboratory（上海人工智能实验室）； Shanghai Jiao Tong University（上海交通大学）； The University of Hong Kong（香港大学）； The Chinese University of Hong Kong（香港中文大学）

专题命中视觉推理：multimodal large language model(abstract)；分类 cs.CV

Comments 30 pages, a benchmark designed to evaluate Online Spatio-Temporal understanding from the perspective of an agent actively exploring a scene. Project Page: https://rbler1234.github.io/OSTBench.github.io/