{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:25Z","timestamp":1792786945498,"version":"4.5.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Brain Science and Brain-like Intelligence Technology\u2014National Science and Technology Major Project","award":["2025ZD0219400"],"award-info":[{"award-number":["2025ZD0219400"]}]},{"name":"National Natural Science Foundation of China","award":["62376009"],"award-info":[{"award-number":["62376009"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Beijing Nova program","id":[{"id":"https:\/\/ror.org\/033pgsq69","id-type":"ROR","asserted-by":"crossref"}]},{"name":"NVIDIA Academic Grant Program using Spark and Thor"},{"name":"State Key Lab of General AI at Peking University"},{"name":"PKU-BingJi Joint Laboratory for Artificial Intelligence"},{"name":"Wuhan Major Scientific and Technological Special Program","award":["2025060902020304"],"award-info":[{"award-number":["2025060902020304"]}]},{"name":"Hubei Embodied Intelligence Foundation Model Research and Development Program"},{"name":"National Comprehensive Experimental Base for Governance of Intelligent Society, Wuhan East Lake High-Tech Development Zone"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/tpami.2026.3722040","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:10:35Z","timestamp":1786475435000},"page":"15079-15096","source":"Crossref","is-referenced-by-count":0,"title":["Afford-X: Generalizable and Slim Affordance Reasoning for Task-Oriented Manipulation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0704-6314","authenticated-orcid":false,"given":"Xiaomeng","family":"Zhu","sequence":"first","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5794-7997","authenticated-orcid":false,"given":"Yuyang","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4925-6983","authenticated-orcid":false,"given":"Leiyao","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8114-6207","authenticated-orcid":false,"given":"Pengfei","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6727-5778","authenticated-orcid":false,"given":"Huan-ang","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7024-1545","authenticated-orcid":false,"given":"Yixin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Peking University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7903-581X","authenticated-orcid":false,"given":"Hao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"56","article-title":"The theory of affordances. the ecological approach to visual perception","volume-title":"The People, Place and, Space Reader","author":"Gibson","year":"1979"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2020.01.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262514620.001.0001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref5","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2022.1009488"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2664"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X11001452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199571154.001.0001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298903"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3446370"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1279"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1865"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919872545"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3252578"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191793"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1912341117"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/en16186677"},{"key":"ref23","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.69796"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28314-7_5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_3"},{"key":"ref27","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2020"},{"key":"ref28","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1410-8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.062"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDH57206.2022.00051"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.544"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"ref40","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref42","first-page":"80","article-title":"Behavior-1 k: A benchmark for embodied AI with 1,000 everyday activities and realistic simulation","volume-title":"Proc. Conf. Robot Learn.","author":"Li","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759429"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007465528199"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1206-1565"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399517"},{"issue":"1","key":"ref47","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TRO.2007.914848","volume":"24","author":"Montesano","year":"2008","journal-title":"IEEE Trans. Robot."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1177\/1059712310370625"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2023.3291558"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"issue":"39","key":"ref51","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref53","first-page":"7605","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Sawatzky","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_27"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341553"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610247"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"ref59","first-page":"72009","article-title":"3D-affordancellm: Harnessing large language models for open-vocabulary affordance detection in 3D worlds","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu","year":"2025"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00164"},{"key":"ref61","article-title":"Partafford: Part-level affordance discovery from 3D objects","volume-title":"Proc. IEEE Eur. Conf. Comput. Vis. VOLI Workshop","author":"Xu","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/124"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3199190"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-3984-0_11"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2003.1241860"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989187"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2409912"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139624"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01873"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1177\/17298806221095974"},{"key":"ref74","first-page":"3453","article-title":"Dexterous functional grasping","volume-title":"Proc. Conf. Robot Learn.","author":"Agarwal","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272571"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01133"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755239"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref82","first-page":"2980","article-title":"Focaltecti loss for dense object deon","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Lin","year":"2017"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160765"},{"key":"ref87","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11723300\/11651465.pdf?arnumber=11651465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:09:14Z","timestamp":1791486554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11651465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":90,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3722040","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":[[2026,11]]}}}