{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:11:38Z","timestamp":1779311498549,"version":"3.51.4"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801993","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T14:17:39Z","timestamp":1735136259000},"page":"7580-7587","source":"Crossref","is-referenced-by-count":21,"title":["ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models"],"prefix":"10.1109","author":[{"given":"Siyuan","family":"Huang","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iaroslav","family":"Ponomarenko","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengkai","family":"Jiang","sequence":"additional","affiliation":[{"name":"UCAS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Hu","sequence":"additional","affiliation":[{"name":"TUM"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Sphinx-x: Scaling data and parameters for a family of multi-modal large language models","author":"Gao","year":"2024"},{"key":"ref3","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01710"},{"key":"ref5","article-title":"Towards diverse behaviors: A benchmark for imitation learning with human demonstrations","author":"Jia","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610744"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610090"},{"key":"ref12","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref13","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023"},{"key":"ref14","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023"},{"key":"ref15","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref16","first-page":"785","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","volume-title":"Conference on Robot Learning","author":"Shridhar"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10139-z"},{"key":"ref19","article-title":"Bridging zero-shot object navigation and foundation models through pixel-guided navigation skill","author":"Cai","year":"2023"},{"key":"ref20","article-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023"},{"key":"ref21","article-title":"Eureka: Human-level reward design via coding large language models","author":"Ma","year":"2023"},{"key":"ref22","article-title":"Code as policies: Language model programs for embodied control","author":"Liang","year":"2022"},{"key":"ref23","first-page":"287","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","volume-title":"Conference on Robot Learning","author":"Brohan"},{"key":"ref24","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref25","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref29","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"Krishna","year":"2016"},{"key":"ref30","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref31","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"},{"key":"ref32","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref33","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023"},{"key":"ref34","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01988"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.018"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801993.pdf?arnumber=10801993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T04:40:27Z","timestamp":1769488827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801993","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}