视觉大模型 / VLM

GenerativeMPC: VLM-RAG-guided Whole-Body MPC with Virtual Impedance for Bimanual Mobile Manipulation

GenerativeMPC：基于VLM-RAG的全身体姿MPC与虚拟阻抗的双臂移动 manipulation

Marcelino Julio Fernando, Miguel Altamirano Cabrera, Jeffrin Sam, Yara Mahmoud, Konstantin Gubernatorov, Dzmitry Tsetserukou

机构 * Intelligent Space Robotics Laboratory（智能空间机器人实验室） ； Skolkovo Institute of Science and Technology（斯克尔科沃科学与技术研究所） 纠错

专题命中 GUI与屏幕智能体 ：VLM(title,title_cn)；vision-language model(abstract)；grounding(abstract)

AI总结 本文提出GenerativeMPC框架，通过VLM-RAG将语义理解与物理控制参数结合，实现双臂移动 manipulation的高效安全控制，实验表明在近人区域速度降低60%并实现安全社交导航。

Comments 6 pages, 7 figures

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving

从表征互补性到双系统：协同VLM和纯视觉骨干网络用于端到端驾驶

Sining Ang, Yuguang Yang, Chenxu Dang, Canyu Chen, Cheng Chi, Haiyan Liu, Xuanyao Mao, Jason Bao, Xuliang, Bingchuan Sun, Yan Wang

机构 * Department of Automation, University of Science and Technology of China（中国科学技术大学自动化系） ； School of Electronic Information Engineering, Beihang University（北京航空航天大学电子信息工程学院） ； School of Artificial Intelligence and Automation, Huazhong University of Science and Technology（华中科技大学人工智能与自动化学院） ； National Superior College for Engineers, Beihang University（北京航空航天大学国家级工程师学院） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） ； Lenovo Group Limited（联想集团有限公司） ； Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院） 纠错

专题命中 GUI与屏幕智能体 ：VLM(title,title_cn)；vision-language model(abstract)；分类 cs.CV

AI总结 本文通过协同VLM和纯视觉骨干网络，提出HybridDriveVLA和DualDriveVLA，提升端到端驾驶的PDMS性能。

CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning

CoNav-UAV：基于Stackelberg学习的协同双高度无人机导航

Junru Song, Wenhao Zhang, Yang Yang, Xuekai Qiu, Feifei Wang, Weien Zhou, Tingsong Jiang, Ying Wen, Yang Li, Wen Yao

专题命中 GUI与屏幕智能体 ：VLM(abstract,abstract_cn)；grounding(abstract)；分类 cs.AI

AI总结 针对双高度无人机协同导航的合作问题，本文提出CoNav-UAV，通过迭代Stackelberg学习优化高空领导者与低空跟随者，在AerialVLN基准上显著提升导航成功率且适配数据需求更少。

DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams

DataClaw0: 从原始流中智能定制多模态数据

Cong Wan, Zeyu Guo, Zijian Cai, Jiangyang Li, SongLin Dong, Lin Peng, Xiangyang Luo, Zhiheng Ma, Yihong Gong

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Shenzhen University of Advanced Technology（深圳理工大学） ； Tsinghua University（清华大学） 纠错

专题命中 GUI与屏幕智能体 ：vision-language model(abstract)；VLM(abstract_cn)；分类 cs.AI、cs.LG

AI总结 提出DataClaw0模型，通过两阶段流水线将生成语义合成锚定于确定性事实锚点，结合SFT与GRPO实现复杂数据精炼意图的对齐，首个数据精炼基准验证其高效性。

Comments add base model: Qwen3.5-27B

SSTG-Nav: Metric-Grounded Spatial-Semantic Topological Graphs for Reusable Object Navigation

SSTG-Nav：用于可重复物体导航的度量空间语义拓扑图

Daojie Peng, Bingtao Wang, Jun Ma

专题命中 GUI与屏幕智能体 ：grounding(abstract,abstract_cn)；分类 cs.AI

AI总结 该研究提出SSTG-Nav，将一次性勘测转化为可执行物体目标，在HM3D-v2数据集实验中显著提升语义导航的成功率与SPL，验证了预探索在可靠重复语义导航中的实用性。

Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

Jetson-PI：通过前瞻对齐异步推理实现机载实时机器人控制

Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li

机构 * Peking University（北京大学） ； AIRS（无合适中文名，保留英文） ； PrimeBot Research Institute（PrimeBot 研究院） 纠错

专题命中 GUI与屏幕智能体 ：VLM(abstract,abstract_cn)；分类 cs.AI

AI总结 研究针对低功耗机载设备部署VLA模型的挑战，提出Jetson-PI方法。通过训练轻量级未来校正模块解决感知-执行未对齐，引入基于置信度的调度优化减少反应时间，辅以系统级加速，实验显示其显著提升控制频率和成功率。

Comments 16 pages, 10 figures

FreqNav: Stage-Wise Frequency Routing for Object-Oriented Aerial Vision-Language Navigation

FreqNav：面向面向对象空中视觉语言导航的分阶段频率路由

Yin Tang, Jiawei Ma, Jiahao Li, Hao Zhang, Zhemin Sun, Jianqiao Sun, Deyu Zhang

专题命中 GUI与屏幕智能体 ：grounding(abstract,abstract_cn)

AI总结 针对现有空中VLN方法的感知干扰问题，提出FreqNav框架，通过动态分配视觉令牌实现分阶段频率路由，提升性能并加快推理速度，验证了其实际应用潜力。

Decoding Children's Gait Behavior

儿童步态行为解码

Yifan Shen, Boyi Li, Meihuan Huang, Yuanzhe Liu, Xu Cao, Jinyang Jin, Zhengyuan Li, Anglin Liu, Junho Kim, Jingyuan Zhu, Lan Fangzhou, Jianguo Cao, Jintai Chen, Ismini Lourentzou, James Matthew Rehg

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； PediaMed AI ； Shenzhen Children’s Hospital（深圳市儿童医院） ； Hong Kong Polytechnic University（香港理工大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） 纠错

专题命中 GUI与屏幕智能体 ：multimodal large language model(abstract)；分类 cs.CV

AI总结 针对儿童步态分析的临床需求，本文构建含110名受试者的1100余条高帧率视频数据集，指出现有先进模型难以解析其临床细节，提出统一端到端框架并建立自动化儿童步态评估基线。

Journal ref ECCV 2026

Robostral Navigate

稳健导航

Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra, Adrian Valente, Adrien Petralia, Adrien Sade, Alan Jeffares, Albert Jiang, Aleksandr Timashov, Alexandre Cahill, Alexandre Gavaudan, Alexandre Laval, Alexandre Sablayrolles, Amelie Heliou, Amos You, Andre Jonasson, Andrew Bai, Andrew Ehrenberg, Andrew Zhao, Angele Lenglemetz, Anmol Agarwal, Antonia Calvi, Arata Suzuki, Arjun Majumdar, Arthur Fournier, Artjom Joosen, Avinash Sooriyarachchi, Aylin Guliz Akkus, Aysenur Karaduman, Baptiste Bout, Baptiste Roziere, Baudouin De Monicault, Benjamin Holzschuh, Benjamin Lefaudeux, Benjamin Tibi, Bernhard Stadlbauer, Blazej Osinski, Camille Le Scao, Chaoran Yu, Charlotte Cronjager, Chen-Yo Sun, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clemence Lanfranchi, Corentin Barreau, Corentin Sautier, Cristiana-Diana Diaconu, Cyprien Courtot, Daniel Marczak, Darius Dabert, Diego de Las Casas, Dominik Nuss, Dylan Rubini, Dzmitry Soupel, Elizaveta Demyanenko, Elliot Chane-Sane, Emilien Fugier, Emmanuel Gottlob, Erik Aas, Etienne Goffinet, Etienne Millon, Eujeong Choi, Fabian Paischer, Fabian Schlager, Faruk Ahmed, Federico Baldassarre, Filip Szatkowski, Florian Wiesner, Gabrielle Berrada, Gaetan Ecrepont, Gaetan Lepage, Gaspard Blanchet, Gaspard Donada-Vidal, Gauthier Delerce, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Gianluca Galletti, Guillaume Breton, Guillaume Kunsch, Guillaume Lample, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hasan Furkan Vural, Hedi Hadiji, Hope McGovern, Hugo Cisneros, Hugo Thimonier, Indraneel Mukherjee, Ivan Cuevas Salazar, Jacques Sun, Jan Ludziejewski, Jason Rute, Jean Quentin, Jean-Hadrien Chabran, Jean-Malo Delignon, Jie Zhang, Joachim Studnia, Joep Barmentlo, Johannes Brandstetter, John Harvill, Jonas Amar, Jonas Schweizer, Josephine Delas, Josselin Somerville, Julien Denize, Julien Tauran, Kartik Khandelwal, Khyathi Raghavi Chandu, Kilian Tep, Kush Jain, Larissa Laich, Laura Calem, Laurence Aitchison, Laurent Callot, Laurent Fainsin, Leo Cotteleer, Leonard Blier, Lingxiao Zhao, Louis Martin, Louis Serrano, Lucile Saulnier, Ludovic Ho Fuh, Luis Montero, Maarten Buyl, Manon Chossegros, Marcin Mozejko, Margaret Jennings, Markus Hennerbichler, Martin Alexandre, Mathieu Poiree, Mathieu Schmitt, Mathilde Guillaumin, Matthieu Andre, Matthieu Dinot, Matthieu Futeral, Maurits Bleeker, Mauro Comi, Max Mynter, Maxim Berman, Maxime Darrin, Maxime Louis, Maximilian Augustin, Maximilian Muller, Melina Jingting Laimon, Mert Unsal, Mia Chiquier, Michael Pilcer, Michal Pietruszka, Michal Zajac, Mikhail Biriuchinskii, Minh-Quang Pham, Minwoo Kang, Morgane Riviere, Namit Katariya, Nathan Grinsztajn, Nathan Simpson, Neeraj Aggarwal, Neha Gupta, Ola Mysiak, Oliver Leicht, Olivier Bousquet, Olivier Duchenne, Parag Jain, Patricia Wang, Patrick Blies, Patrick von Platen, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavan Kumar Reddy, Pavel Kuksa, Philippe Pinel, Philomene Chagniot, Pierre Stock, Pierre-Andre Savalle, Piotr Milos, Prateek Gupta, Pravesh Agrawal, Quentin Desreumaux, Quentin Torroba, Quercus Hernandez, Ram Ramrakhya, Randall Isenhour, Ranjit Parva, Raul Perez Pelaez, Reinhard Sonnleitner, Remi Delacourt, Richard Kurle, Rishi Shah, Rob Romijnders, Rohin Arora, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Belkadi, Samuel Humeau, Sanchit Gandhi, Sandeep Subramanian, Sarthak Mittal, Saskia Adaime, Sean Cha, Sebastian Kaltenbach, Shashwat Dalal, Shashwat Verma, Sherif Waly, Shrimai Prabhumoye, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Simon Sorg, Soham Ghosh, Sophie Marbach, Srijan Mishra, Stanislas Lange, Steve Hong, Sumukh Aithal, Szymon Antoniak, Tarun Kumar Vangani, Teven Le Scao, Theo Cachet, Thibaut Lavril, Thomas Chabal, Thomas Coste, Thomas Defard, Thomas Foubert, Thomas Robert, Thomas Wang, Tianyu Zhang, Tim Lawson, Timothee Lacroix, Tobias Kronlachner, Tom Bewley, Tom Edwards, Tomas Hodan, Tuhin Das, Tyler Wang, Ulrick BLE, Umar Jamil, Umberto Tomasini, Valentin Mace, Van Phung, Vedant Nanda, Victor Jouault, Victor Letzelter, Victor Paltz, Victor Poucheret, Vincent Maladiere, Vincent Pfister, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yann Dreze, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Yves Martin des Taillades, Zaccharie Ramzi, Zhenlin Xu, Zsofia Csakany

专题命中 GUI与屏幕智能体 ：vision-language model(abstract)；分类 cs.AI

AI总结 研究旨在解决大规模导航系统部署问题，提出Robostral Navigate模型，仅用单目RGB图像流预测路点，具鲁棒性。通过模拟场景减少对真实数据依赖，用前缀缓存训练等方法，在基准测试中达新最优，提升导航系统性能。

EgoIntent: A Pre-Outcome Micro-Step Benchmark for Understanding What, Why, and Next

EgoIntent: 一种用于理解‘是什么、为什么和下一步’的以自我为中心的步级基准

Ye Pan, Chi Kit Wong, Yuanhuiyi Lyu, Hanqian Li, Chenfei Liao, Jiahao Huo, Lutao Jiang, Zixin Zhang, Jiacheng Chen, Yuqian Fu, Xu Zheng

专题命中 GUI与屏幕智能体 ：multimodal large language model(abstract)；分类 cs.CV

AI总结 EgoIntent基准旨在通过步级意图理解解决以自我为中心视频中对‘是什么、为什么和下一步’的细粒度理解难题，包含15种日常生活场景，评估模型在三个维度上的表现。

Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models

面向视觉-语言-动作模型的鲁棒指令泛化的基础语义重绑定

Zhaokai Yin, Zhipeng Zhang

专题命中 GUI与屏幕智能体 ：grounding(abstract)

AI总结 针对视觉-语言-动作模型因指令释义导致性能骤降的架构问题，提出GSR方法，在LIBERO-Para基准提升成功率44.6%，推出ParaVLA模型，规避低效数据扩展，实现鲁棒指令泛化。

Comments 23 pages, 8 figures

EndoWAM: A Grounded World-Action Model for Generalizable Endoscopic Navigation

EndoWAM：用于通用内窥镜导航的基于接地的世界-动作模型

Jinsong Lin, Zikang Pan, Wanhao Liu, Chi Kit Ng, Liangjing Shao, Zihang Yu, Ziyu Wang, Yin Wang, Jiaxi Wang, Jeremy Yuen-Chun Teoh, Zhiyong Xiong, Huxin Gao, Hongliang Ren

专题命中 GUI与屏幕智能体 ：grounding(abstract)

AI总结 EndoWAM是首个用于通用机器人内窥镜导航的世界-动作模型，通过未来接地机制结合轻量型扩散Transformer与离散动作专家，在EndoMotion数据集上优于基线，具强零样本泛化能力。

SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control

SelfWAM：一种用于快速机器人控制的自 grounded 统一世界动作模型

Bikang Pan, Fan Liu, Haotao Lu, Jingya Wang, Ye Shi

专题命中 GUI与屏幕智能体 ：grounding(abstract)

AI总结 SelfWAM是一种基于MoT架构的统一自 grounded WAM，通过联合预测动作等改进机器人控制，在RoboTwin 2.0等实验中提升了策略性能与推理速度。