4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
Tsinghua University, SIGS(清华大学 SIGS);Meituan(美团);The Chinese University of Hong Kong(香港中文大学);National University of Singapore(新加坡国立大学);LMMs-Lab(LMMs实验室);University of California, Los Angeles(加州大学洛杉矶分校)
Dynamic spatial reasoning from monocular video is essential for bridging visual intelligence and the physical world, yet remains challenging for vision-language models (VLMs). Prior approaches either verbalize spatial-temporal reasoning entirely as text, which is inherently verbose and imprecise for complex dynamics, or rely on external geometric modules that increase inference complexity without fostering intrinsic model capability. In this paper, we present 4DThinker, the first framework that enables VLMs to "think with 4D" through dynamic latent mental imagery, i.e., internally simulating how scenes evolve within the continuous hidden space. Specifically, we first introduce a scalable, annotation-free data generation pipeline that synthesizes 4D reasoning data from raw videos. We then propose Dynamic-Imagery Fine-Tuning (DIFT), which jointly supervises textual tokens and 4D latents to ground the model in dynamic visual semantics. Building on this, 4D Reinforcement Learning (4DRL) further tackles complex reasoning tasks via outcome-based rewards, restricting policy gradients to text tokens to ensure stable optimization. Extensive experiments across multiple dynamic spatial reasoning benchmarks demonstrate that 4DThinker consistently outperforms strong baselines and offers a new perspective toward 4D reasoning in VLMs. Our code is available at https://github.com/zhangquanchen/4DThinker.
How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning
Mila - Québec AI Institute(蒙特利尔AI研究所);Université de Montréal(蒙特利尔大学);McGill University(麦吉尔大学);ServiceNow AI Research(ServiceNow人工智能研究);Canada CIFAR AI Chair(加拿大CIFAR人工智能主席)
DM-KG: A Novel Method for Boosting Spatial Cognition of Vision-Language Models in Street View Imagery
Institute of Surveying and Mapping, Information Engineering University(信息工程大学测绘学院);Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences(中国科学院地理科学与资源研究所)
EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting
School of Interdisciplinary Science, Beijing Institute of Technology(交叉科学学院,北京理工大学);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学);National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology(空间智能信息处理国家重点实验室,北京理工大学);School of Optics and Photonics, Beijing Institute of Technology(光学与 photonics 学院,北京理工大学);State Key Laboratory of Explosion Science and Safety Protection, Beijing(爆炸科学与安全防护国家重点实验室,北京)
Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
The University of Hong Kong(香港大学);Shanghai AI Laboratory(上海人工智能实验室);Shanghai Jiao Tong University(上海交通大学);Fudan University(复旦大学);Beihang University(北航大学)
GeoReason: Aligning Thinking And Answering In Remote Sensing Vision-Language Models Via Logical Consistency Reinforcement Learning
Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院航空信息研究所);Key Laboratory of Target Cognition and Application Technology, Chinese Academy of Sciences(中国科学院目标认知与应用技术重点实验室);University of Chinese Academy of Sciences(中国科学院大学)
Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping
Shandong University of Science and Technology(山东科技大学);Technical University of Munich(慕尼黑工业大学);Wuhan University(武汉大学);Tsinghua University(清华大学);Helmholtz-Zentrum Dresden-Rossendorf(亥姆霍兹德累斯顿罗森多夫研究中心);University of Iceland(冰岛大学)
3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training
Shanghai Jiao Tong University(上海交通大学);Harbin Institute of Technology(哈尔滨工业大学);Nanyang Technological University(南洋理工大学);Fudan University(复旦大学);Nanjing University(南京大学);Daimon Robotics(达梦机器人);Great Bay University(大亚大学)
GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
National University of Defense Technology, China(国防科技大学);Beijing University of Posts and Telecommunications, China(北京邮电大学);University of the Chinese Academy of Sciences, China(中国科学院大学);Shanghai Jiao Tong University, China(上海交通大学);Wuhan University, China(武汉大学);Chinese Academy of Science, China(中国科学院);Tsinghua University, China(清华大学);Renmin University of China, China(中国人民大学)
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Ant Group(蚂蚁集团);CUHK MMLab(香港中文大学MMLab);Nanjing University(南京大学)
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features
Beijing Institute of Technology(北京理工大学);German Aerospace Center (DLR)(德国航空航天中心);Technical University of Munich (TUM)(慕尼黑工业大学);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立高等物理、数学与信息学院);University of Iceland(冰岛大学)
Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
S-Lab, Nanyang Technological University(南洋理工大学S-Lab);SenseTime Research(商汤科技研究院);University of Michigan(密歇根大学);Max-Planck Institute for Informatics(马克斯·普朗克信息学研究所)
Evaluating Semantic and Spatial Guidance for Foundation Model Segmentation of Small-Scale PV in Remote Sensing Imagery
Ben-Gurion University of the Negev(内盖夫本-古里安大学);The Hebrew University of Jerusalem(耶路撒冷希伯来大学);Ben Gurion Institute for the Study of Israel & Zionism(本-古里安以色列与犹太复国主义研究所);Ben-Gurion Israel Research Institute(本-古里安以色列研究所)
EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing(信息工程测绘遥感国家重点实验室);Wuhan University(武汉大学);Wuhan University Shenzhen Research Institute(武汉大学深圳研究院);School of Computer Science(计算机学院);School of Automation Science and Engineering(自动化科学与工程学院);South China University of Technology(华南理工大学)
How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery
Hong Kong University of Science and Technology(香港科技大学);Jiangnan University(江南大学);The Chinese University of Hong Kong(香港中文大学);Nanjing University of Information Science and Technology(南京信息工程大学);Peking University(北京大学)