{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:57:54Z","timestamp":1768276674369,"version":"3.49.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127464","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1677-1683","source":"Crossref","is-referenced-by-count":2,"title":["IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Zhang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nader","family":"Zantout","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pujith","family":"Kachana","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Robotics Institute,Pittsburgh,PA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref5","first-page":"88218831","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning.","author":"Ramesh","year":"2021"},{"key":"ref6","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume":"27","author":"Karpathy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Human behavior and the principle of least effort: An introduction to human ecology","author":"Zipf","year":"2016","journal-title":"Ravenio Books"},{"key":"ref10","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","author":"Ramakrishnan","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref17","volume-title":"Spatialrgpt: Grounded spatial reasoning in vision language model","author":"Cheng","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.077"},{"key":"ref21","article-title":"Conceptgraphs: Open-vocabulary 3d scene graphs for perception and planning","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00272"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104183"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.028"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2021.XVII.020"},{"key":"ref29","volume-title":"Teach: Task-driven embodied agents that chat","author":"Padmakumar","year":"2021"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2022.XVIII.065","volume-title":"Correcting robot plans with natural language feedback","author":"Sharma","year":"2022"},{"key":"ref31","volume-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","author":"Shah","year":"2022"},{"key":"ref32","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"On evaluation of embodied navigation agents","author":"Anderson","year":"2018","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00775"},{"key":"ref37","article-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","author":"Baruch","year":"2021","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.79"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref40","article-title":"Paul Grice","author":"Grandy","year":"2023","journal-title":"The Stanford Encyclopedia of Philosophy, Fall 2023 ed."}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127464.pdf?arnumber=11127464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:04:05Z","timestamp":1756879445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127464","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}