{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:08Z","timestamp":1777865528433,"version":"3.51.4"},"reference-count":56,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332016"],"award-info":[{"award-number":["62332016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00944","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10130-10140","source":"Crossref","is-referenced-by-count":0,"title":["GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping Under Flexible Language Instructions"],"prefix":"10.1109","author":[{"given":"Xiaomeng","family":"Chu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoliang","family":"You","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingchen","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmin","family":"Ji","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/mti2030057"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02496"},{"key":"ref3","article-title":"Grounded 3d-llm with referent tokens","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref4","article-title":"3d-llava: Towards generalist 3 d 1 mms with omni superpoint transformer","author":"Deng","year":"2025","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560844"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref10","article-title":"Scene-llm: Extending language model for 3d visual understanding and reasoning","author":"Fu","year":"2024","journal-title":"CoRR"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0900"},{"key":"ref13","article-title":"Reasoning grasping via multimodal large language model","volume-title":"Conference on Robot Learning","author":"Jin","year":"2024"},{"key":"ref14","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Conference on robot learning","author":"Kalashnikov","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509508"},{"key":"ref17","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802654"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801661"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref22","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"GLOVER: generalizable open-vocabulary affordance reasoning for task-oriented grasping","author":"Ma","year":"2024","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2992195"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00299"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3280597"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610008"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_21"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref32","article-title":"Thinkgrasp: A vision-language system for strategic part grasping in clutter","author":"Qian","year":"2024","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"ref34","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463204"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2969946"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342331"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3320012"},{"key":"ref39","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref40","article-title":"Towards openworld grasping with large vision-language models","author":"Tziafas","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161569"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01566"},{"key":"ref43","first-page":"70","article-title":"Goal-auxiliary actor-critic for 6d robotic grasping with point clouds","volume-title":"Conference on Robot learning","author":"Wang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1487"},{"key":"ref47","first-page":"357","article-title":"An economic framework for 6-dof grasp detection","volume-title":"European Conference on Computer vision","author":"Wu","year":"2024"},{"key":"ref48","article-title":"Deligrasp: Inferring object properties with 11 ms for adaptive grasp policies","volume-title":"8th Annual Conference on Robot Learning","author":"Xie","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801718"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02558"},{"key":"ref51","article-title":"A parameter-efficient tuning framework for language-guided object grounding and robot grasping","author":"Yu","year":"2024","journal-title":"CoRR"},{"key":"ref52","article-title":"Robotic grasping from classical to modern: A survey","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_11"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561920"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00841"},{"key":"ref56","article-title":"Llava-3d: A simple yet effective pathway to empowering 1 mms with 3d-awareness","author":"Zhu","year":"2024","journal-title":"CoRR"}],"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\/11445047.pdf?arnumber=11445047","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:35Z","timestamp":1777531595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445047\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00944","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}