{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:18:06Z","timestamp":1777889886434,"version":"3.51.4"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00596","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"6315-6326","source":"Crossref","is-referenced-by-count":0,"title":["MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation"],"prefix":"10.1109","author":[{"given":"Pingrui","family":"Zhang","sequence":"first","affiliation":[{"name":"Fudan University"}]},{"given":"Xianqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Yuhan","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}]},{"given":"Kehui","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Zhigang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Yan","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"TeleAI,China Telecom Corp Ltd"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247088"},{"key":"ref2","author":"Ahn","year":"2024","journal-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref4","author":"Batra","year":"2020","journal-title":"Rearrangement: A challenge for embodied ai"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref7","author":"Chang","year":"2015","journal-title":"Shapenet: An information-rich 3d model repository"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00508"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref10","author":"Das","year":"2020","journal-title":"Probing emergent semantics in predictive agents via question answering"},{"key":"ref11","author":"Duan","year":"2024","journal-title":"Manipulateanything: Automating real-world robots using visionlanguage models"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01537"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01244"},{"key":"ref14","first-page":"138","article-title":"Deep wholebody control: learning a unified policy for manipulation and locomotion","volume-title":"Conference on Robot Learning","author":"Fu","year":"2023"},{"key":"ref15","author":"Fu","year":"2024","journal-title":"Mobile aloha: Learning bimanual mobile manipulation with low-cost whole-body teleoperation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32318"},{"key":"ref17","first-page":"3766","article-title":"Scaling up and distilling down: Language-guided robot skill acquisition","volume-title":"Conference on Robot Learning","author":"Ha","year":"2023"},{"key":"ref18","author":"Huang","year":"2023","journal-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01352"},{"key":"ref20","author":"Jiang","year":"2025","journal-title":"Behavior robot suite: Streamlining realworld whole-body manipulation for everyday household activities"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref24","first-page":"603","article-title":"Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators","volume-title":"Conference on Robot Learning","author":"Li","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2007.911536"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913886"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3011148"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3543033"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.091"},{"key":"ref30","author":"Liu","year":"2024","journal-title":"Stat: Towards generalizable temporal action localization"},{"key":"ref31","article-title":"Task planning for visual room rearrangement under partial observability","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mirakhor","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981779"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref34","article-title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","author":"Ruizhongtai Qi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref37","author":"Qiu","year":"2024","journal-title":"Open-vocabulary mobile manipulation in unseen dynamic environments with 3d semantic maps"},{"key":"ref38","author":"Ramakrishnan","year":"2021","journal-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai"},{"key":"ref39","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-8405-5_14"},{"key":"ref41","author":"Song","year":"2025","journal-title":"Hume: Introducing system-2 thinking in visual-language-action model"},{"key":"ref42","first-page":"477","article-title":"Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments","volume-title":"Conference on robot learning","author":"Srivastava","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843605000545"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28323"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_26"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1342250.1342272"},{"key":"ref48","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00360"},{"key":"ref50","author":"Wang","year":"2024","journal-title":"Mosaic: A modular system for assistive and interactive cooking"},{"key":"ref51","author":"Wang","year":"2023","journal-title":"Gensim: Generating robotic simulation tasks via large language models"},{"key":"ref52","author":"Wang","year":"2024","journal-title":"Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341337"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160982"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0697"},{"key":"ref56","author":"Wang","year":"2023","journal-title":"Robogen: Towards unleashing infinite data for automated robot learning via generative simulation"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00586"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref59","first-page":"1367","article-title":"Error-aware imitation learning from teleoperation data for mobile manipulation","volume-title":"Conference on Robot Learning","author":"Wong","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160934"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2965078"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3295"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00459"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-025-41109-6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref69","author":"Yenamandra","year":"2023","journal-title":"Homerobot: Open-vocabulary mobile manipulation"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3336109"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00974"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref74","author":"Zhang","year":"2025","journal-title":"Cross from left to right brain: Adaptive text dreamer for vision-and-language navigation"},{"key":"ref75","article-title":"Question-guided knowledge graph rescoring and injection for knowledge graph question answering","volume-title":"Conference on Empirical Methods in Natural Language Processing","author":"Zhang","year":"2024"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_19"},{"key":"ref77","author":"Kehui","year":"2025","journal-title":"Fastumi: A scalable and hardware-independent universal manipulation interface with dataset"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127975"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11127975"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11247165"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446261.pdf?arnumber=11446261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:32Z","timestamp":1777612892000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00596","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}