{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:47:43Z","timestamp":1790995663537,"version":"4.1.0"},"reference-count":104,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62273093"],"award-info":[{"award-number":["62273093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tpami.2026.3688692","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:47:46Z","timestamp":1777405666000},"page":"11166-11182","source":"Crossref","is-referenced-by-count":3,"title":["ImagineNav++: Prompting Vision-Language Models as Embodied Navigator Through Scene Imagination"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1802-0435","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"first","affiliation":[{"name":"Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8455-4496","authenticated-orcid":false,"given":"Xinxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhe","family":"Cai","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"additional","affiliation":[{"name":"Southeast University","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Frontier based exploration for autonomous robot","author":"Topiwala","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610499"},{"key":"ref3","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chaplot","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00511"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_10"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01775"},{"issue":"PMLR","key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Radford","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref14","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"issue":"240","key":"ref15","first-page":"1","article-title":"PALM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref17","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref18","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref19","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref23","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","first-page":"42829","article-title":"ESC: Exploration with soft commonsense constraints for zero-shot object navigation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.24"},{"key":"ref27","first-page":"53737","article-title":"VoroNav: Voronoi-based zero-shot object navigation with large language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802670"},{"key":"ref29","first-page":"19057","article-title":"Navigation with large language models: Semantic guesswork as a heuristic for planning","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342512"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/02783649251369549"},{"key":"ref32","article-title":"Evaluating spatial understanding of large language models","author":"Yamada","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73036-8_25"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01609"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00653"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812027"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01432"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref39","article-title":"MEM2Ego: Empowering vision-language models with global-to-ego memory for long-horizon embodied navigation","volume-title":"Proc. CVPR 2025 Workshop Found. Models Meet Embodied Agents","author":"Zhang","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.013"},{"key":"ref42","article-title":"Multimodal large language model for visual navigation","author":"Tsai","year":"2023"},{"key":"ref43","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref44","first-page":"2021","article-title":"Habitat-matterport 3D dataset (HM3D): 1000 large-scale 3D environments for embodied AI","volume-title":"Proc. 35th NeurIPS Datasets and Benchmarks Track","author":"Ramakrishnan"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01550"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref47","article-title":"ImagineNav: Prompting vision-language models as embodied navigator through scene imagination","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao","year":"2025"},{"key":"ref48","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref50","article-title":"Instruct2ACT: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0278"},{"key":"ref52","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ahn","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref55","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for vlms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nasiriany","year":"2024"},{"key":"ref56","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeng","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02219"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2343"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160969"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.073"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01002"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01003"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981766"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_24"},{"key":"ref67","article-title":"Learning to map for active semantic goal navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Georgakis","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560925"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01553"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610712"},{"key":"ref71","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"2023","author":"Li"},{"key":"ref72","article-title":"End-to-end navigation with vision language models: Transforming spatial reasoning into question-answering","volume-title":"Proc. Int. Conf. Neuro-Symbolic Syst.","author":"Goetting","year":"2025"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3592071"},{"key":"ref74","article-title":"OctoNav: Towards generalist embodied navigation","author":"Gao","year":"2025"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00900"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00876"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2012.06.013"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-3569-x"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_22"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00085"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01590"},{"key":"ref86","article-title":"GPT-4O-Mini","year":"2024"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.064"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610025"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0561"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611319"},{"key":"ref91","article-title":"Offline visual representation learning for embodied navigation","volume-title":"Proc. Workshop Reincarnating Reinforcement Learn. ICLR 2023","author":"Yadav","year":"2023"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0171"},{"key":"ref93","article-title":"Habitat 3.0: A co-habitat for humans, avatars and robots","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Puig","year":"2024"},{"key":"ref94","article-title":"Habitatchallenge 2023","author":"Yadav","year":"2023"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref96","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018"},{"key":"ref97","article-title":"Instance-specific image goal navigation: Training embodied agents to find object instances","author":"Krantz","year":"2022"},{"key":"ref98","article-title":"OVRL-V2: A simple State-of-Art baseline for imagenav and objectnav","author":"Yadav","year":"2023"},{"key":"ref99","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref101","article-title":"GPT-4 Turbo","year":"2023"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref103","article-title":"Qwen3-Vl Technical report","author":"Bai","year":"2025"},{"key":"ref104","article-title":"Qwen3.5: Towards native multimodal agents","author":"Team","year":"2026"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11643729\/11498592.pdf?arnumber=11498592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T19:06:24Z","timestamp":1786129584000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11498592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":104,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3688692","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}