{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:30:20Z","timestamp":1766068220481,"version":"3.44.0"},"reference-count":54,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2214177"],"award-info":[{"award-number":["2214177"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA9550-22-1-0249"],"award-info":[{"award-number":["FA9550-22-1-0249"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["W911NF-23-1-0034"],"award-info":[{"award-number":["W911NF-23-1-0034"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128681","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"8307-8314","source":"Crossref","is-referenced-by-count":7,"title":["KALM: Keypoint Abstraction Using Large Models for Object-Relative Imitation Learning"],"prefix":"10.1109","author":[{"given":"Xiaolin","family":"Fang","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Bo-Ruei","family":"Huang","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Jiayuan","family":"Mao","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Jasmine","family":"Shone","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Tom\u00e1s","family":"Lozano-P\u00e9rez","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]},{"given":"Leslie Pack","family":"Kaelbling","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Viola: Imitation learning for vision-based manipulation with object proposal priors","volume-title":"Conference on Robotic Learning","author":"Zhu","year":"2023"},{"key":"ref2","article-title":"Composable part-based manipulation","volume-title":"Conference on Robotic Learning","author":"Liu","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3062315"},{"key":"ref4","article-title":"ReKep: SpatioTemporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","volume-title":"Conference on Robotic Learning","author":"Huang","year":"2024"},{"key":"ref5","article-title":"3d diffuser actor: Policy diffusion with 3d scene representations","volume-title":"Conference on Robotic Learning","author":"Ke","year":"2024"},{"key":"ref6","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"Conference on Robotic Learning","author":"Gervet","year":"2023"},{"key":"ref7","article-title":"Perceiver-actor: A multitask transformer for robotic manipulation","volume-title":"Conference on Robotic Learning","author":"Shridhar","year":"2022"},{"key":"ref8","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"},{"key":"ref11","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"International Conference on Machine Learning","author":"Janner","year":"2022"},{"journal-title":"Hello GPT-4o","year":"2024","key":"ref12"},{"key":"ref13","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref14","article-title":"Featup: A model-agnostic framework for features at any resolution","volume-title":"International Conference on Learning Representations","author":"Fu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152473"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802746"},{"key":"ref17","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Conference on Robotic Learning","author":"Yu","year":"2019"},{"key":"ref18","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1991.131782"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/02783640122067480"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7353384"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811872"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390187"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461196"},{"key":"ref25","article-title":"Entity Abstraction in Visual ModelBased Reinforcement Learning","volume-title":"Conference on Robotic Learning","author":"Veerapaneni","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636023"},{"key":"ref27","article-title":"SORNet: Spatial ObjectCentric Representations for Sequential Manipulation","volume-title":"Conference on Robotic Learning","author":"Yuan","year":"2021"},{"key":"ref28","article-title":"PDSketch: Integrated Domain Programming, Learning, and Planning","author":"Mao","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICAR.2011.6088558"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2016.7803382"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref32","article-title":"Composable Part-Based Manipulation","volume-title":"Conference on Robotic Learning","author":"Liu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-95459-8_9"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196971"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.060"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2022.xviii.044"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"ref38","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Conference on Robotic Learning","author":"Shen","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386006"},{"key":"ref40","article-title":"Grounding language plans in demonstrations through counterfactual perturbations","volume-title":"International Conference on Learning Representations","author":"Wang","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-091420-084139"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01548"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1986.4767747"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2014.7041426"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2826057"},{"key":"ref46","article-title":"One-shot imitation learning via interaction warping","volume-title":"Conference on Robotic Learning","author":"Biza","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560894"},{"journal-title":"Do as i can and not as i say: Grounding language in robotic affordances","year":"2022","author":"Ahn","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref50","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"Conference on Robotic Learning","author":"Huang","year":"2023"},{"journal-title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning","year":"2023","author":"Hu","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.062"},{"key":"ref53","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"International Conference on Learning Representations","author":"Ma","year":"2024"},{"key":"ref54","article-title":"Learning Object-Oriented Dynamics for Planning from Text","volume-title":"International Conference on Learning Representations","author":"Liu","year":"2021"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","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\/11128681.pdf?arnumber=11128681","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:14:23Z","timestamp":1756880063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128681\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128681","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}