{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:56:39Z","timestamp":1770231399487,"version":"3.49.0"},"reference-count":28,"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\/iros60139.2025.11246145","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"2201-2208","source":"Crossref","is-referenced-by-count":2,"title":["SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models"],"prefix":"10.1109","author":[{"given":"Nader","family":"Zantout","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Haochen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Pujith","family":"Kachana","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Jinkai","family":"Qiu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Guofei","family":"Chen","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Ji","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]},{"given":"Wenshan","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"ref2","article-title":"Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai","author":"Ramakrishnan","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01508"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00272"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802793"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00257"},{"key":"ref8","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Solving zero-shot 3d visual grounding as constraint satisfaction problems","author":"Yuan","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610443"},{"key":"ref11","article-title":"Vlm-grounder: A vlm agent for zero-shot 3d visual grounding","author":"Xu","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00351"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref15","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref16","first-page":"24 824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Advances in neural information processing systems","volume":"35","author":"Wei"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA55743.2025.11127464","article-title":"Iref-vla: A benchmark for interactive referential grounding with imperfect language in 3d scenes","author":"Zhang","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72673-6_16"},{"key":"ref20","first-page":"20 522","article-title":"Language conditioned spatial relation reasoning for 3d object grounding","volume-title":"Advances in neural information processing systems","volume":"35","author":"Chen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01949"},{"key":"ref22","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3554559"},{"key":"ref25","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"ref26","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"ref27","article-title":"Qwen2 technical report","year":"2024"},{"key":"ref28","article-title":"Mistral large 2: The new generation of flag- ship model","year":"2024"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Hangzhou, China","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246145.pdf?arnumber=11246145","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:10:00Z","timestamp":1765519800000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246145\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246145","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}