{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T22:14:59Z","timestamp":1778624099540,"version":"3.51.4"},"reference-count":222,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong SAR Research Grants Council","award":["PolyU 15224823"],"award-info":[{"award-number":["PolyU 15224823"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515011524"],"award-info":[{"award-number":["2024A1515011524"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302246"],"award-info":[{"award-number":["62302246"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ZJNSFC","award":["LQ23F010008"],"award-info":[{"award-number":["LQ23F010008"]}]},{"name":"Ningbo","award":["2023Z237"],"award-info":[{"award-number":["2023Z237"]}]},{"name":"Ningbo","award":["2023CX050011"],"award-info":[{"award-number":["2023CX050011"]}]},{"name":"Ningbo","award":["2024Z284"],"award-info":[{"award-number":["2024Z284"]}]},{"name":"Ningbo","award":["2024Z289"],"award-info":[{"award-number":["2024Z289"]}]},{"name":"Ningbo","award":["2025Z038"],"award-info":[{"award-number":["2025Z038"]}]},{"name":"Ningbo","award":["2025Z059"],"award-info":[{"award-number":["2025Z059"]}]},{"name":"Ningbo Institute of Digital Twin","award":["S203.2.01.32.002"],"award-info":[{"award-number":["S203.2.01.32.002"]}]},{"name":"High Performance Computing Center at the IDT"},{"name":"Eastern Institute of Technology, Ningbo"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3649177","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T18:37:35Z","timestamp":1767119855000},"page":"4909-4927","source":"Crossref","is-referenced-by-count":2,"title":["A Survey of Behavior Foundation Model: Next-Generation Whole-Body Control System of Humanoid Robots"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9149-6202","authenticated-orcid":false,"given":"Mingqi","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Yu","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1925-0226","authenticated-orcid":false,"given":"Wenqi","family":"Ge","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuyong","family":"Yao","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2619-6825","authenticated-orcid":false,"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1274-6363","authenticated-orcid":false,"given":"Huijiang","family":"Wang","sequence":"additional","affiliation":[{"name":"CREATE Lab, EPFL, Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7708-5247","authenticated-orcid":false,"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Data and Systems Engineering, The University of Hong Kong, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7500-8355","authenticated-orcid":false,"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Zeng","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Chen","sequence":"additional","affiliation":[{"name":"LimX Dynamics, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1820-8358","authenticated-orcid":false,"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236952"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-60615-1_20"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.124140"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9479-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2587744"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-6046-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-021-07682-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811670"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-91745-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843605000594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914521306"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2597314"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1142\/S0219843615500401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids53995.2022.10000129"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2015.2512933"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341391"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2947001"},{"key":"ref21","article-title":"Embodied chain of action reasoning with multi-modal foundation model for humanoid loco-manipulation","author":"Hao","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3475052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref24","article-title":"Parrot: Data-driven behavioral priors for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Singh","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918770733"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2019.00120"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3018325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223407"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3192418"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3314762"},{"key":"ref33","first-page":"4895","article-title":"Multi-task hierarchical adversarial inverse reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Chen","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435790"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.064"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids57100.2023.10375203"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1164660"},{"key":"ref40","article-title":"ExBody2: Advanced expressive humanoid whole-body control","volume-title":"Proc. RSS Workshop Whole-Body Control Bimanual Manipulation, Appl. Humanoids Beyond","author":"Ji","year":"2025"},{"key":"ref41","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Ma","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3064065"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3303714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611113"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(99)01327-3"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref48","first-page":"143","article-title":"DART: Noise injection for robust imitation learning","volume-title":"Proc. Conf. Robot Learn.","author":"Laskey","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00103-5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/s21041278"},{"key":"ref51","article-title":"Fast imitation via behavior foundation models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Pirotta","year":"2024"},{"key":"ref52","first-page":"1647","article-title":"Finer behavioral foundation models via auto-regressive features and advantage weighting","volume-title":"Proc. Reinforcement Learn. Conf.","author":"Cetin","year":"2025"},{"key":"ref53","article-title":"Zero-shot whole-body humanoid control via behavioral foundation models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Tirinzoni","year":"2025"},{"key":"ref54","first-page":"1048","article-title":"Fast adaptation with behavioral foundation models","volume-title":"Proc. Reinforcement Learn. Conf.","author":"Sikchi","year":"2025"},{"key":"ref55","article-title":"Task tokens: A flexible approach to adapting behavior foundation models","author":"Vainshtein","year":"2025"},{"key":"ref56","article-title":"Zero-shot adaptation of behavioral foundation models to unseen dynamics","author":"Bobrin","year":"2025"},{"key":"ref57","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref58","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref61","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref62","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. Conf. Robot Learn.","author":"Kim","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544909"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927961"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-6046-2_51"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.067"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128549"},{"key":"ref68","article-title":"From experts to a generalist: Toward general whole-body control for humanoid robots","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst.","author":"Wang","year":"2025"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref71","first-page":"37607","article-title":"Masked trajectory models for prediction, representation, and control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu","year":"2023"},{"key":"ref72","article-title":"H-GAP: Humanoid control with a generalist planner","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Jiang","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abo0235"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591541"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618205"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01145"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3658137"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3687951"},{"key":"ref80","first-page":"12394","article-title":"ModSkill: Physical character skill modularization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Huang","year":"2025"},{"key":"ref81","first-page":"4493","article-title":"CLONE: Closed-loop whole-body humanoid teleoperation for long-horizon tasks","volume-title":"Proc. 9th Annu. Conf. Robot Learn.","author":"Li","year":"2025"},{"key":"ref82","first-page":"2143","article-title":"TWIST: Teleoperated whole-body imitation system","volume-title":"9th Annu. Conf. Robot Learn.","author":"Ze","year":"2025"},{"key":"ref83","article-title":"Twist2: Scalable, portable, and holistic humanoid data collection system","author":"Ze","year":"2025"},{"key":"ref84","article-title":"Agility meets stability: Versatile humanoid control with heterogeneous data","author":"Pan","year":"2025"},{"key":"ref85","article-title":"Track any motions under any disturbances","author":"Zhang","year":"2025"},{"key":"ref86","article-title":"Behavior foundation model for humanoid robots","author":"Zeng","year":"2025"},{"key":"ref87","article-title":"Sonic: Supersizing motion tracking for natural humanoid whole-body control","author":"Luo","year":"2025"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref89","article-title":"Diversity is all you need: Learning skills without a reward function","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Eysenbach","year":"2019"},{"key":"ref90","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Burda","year":"2019"},{"key":"ref91","first-page":"6736","article-title":"APS: Active pretraining with successor features","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref92","first-page":"11920","article-title":"Reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yarats","year":"2021"},{"key":"ref93","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Seo","year":"2021"},{"key":"ref94","first-page":"67925","article-title":"A unified algorithm framework for unsupervised discovery of skills based on determinantal point process","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen","year":"2023"},{"key":"ref95","first-page":"13","article-title":"Learning one representation to optimize all rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Touati","year":"2021"},{"key":"ref96","article-title":"BFM-Zero: A promptable behavioral foundation model for humanoid control using unsupervised reinforcement learning","author":"Li","year":"2025"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00506"},{"key":"ref98","article-title":"Unified human-scene interaction via prompted chain-of-contacts","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Xiao","year":"2024"},{"key":"ref99","first-page":"13214","article-title":"UniPhys: Unified planner and controller with diffusion for flexible physics-based character control","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wu","year":"2025"},{"key":"ref100","article-title":"CLoSD: Closing the loop between simulation and diffusion for multi-task character control","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Tevet","year":"2025"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.065"},{"key":"ref102","article-title":"Leverb: Humanoid whole-body control with latent vision-language instruction","author":"Xue","year":"2025"},{"key":"ref103","article-title":"BeyondMimic: From motion tracking to versatile humanoid control via guided diffusion","author":"Liao","year":"2025"},{"key":"ref104","article-title":"Sentinel: A fully end-to-end language-action model for humanoid whole body control","author":"Wang","year":"2025"},{"key":"ref105","article-title":"Neural probabilistic motor primitives for humanoid control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Merel","year":"2019"},{"key":"ref106","first-page":"5062","article-title":"Self-supervised exploration via disagreement","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pathak","year":"2019"},{"key":"ref107","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sekar","year":"2020"},{"key":"ref108","article-title":"Variational intrinsic control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gregor","year":"2017"},{"key":"ref109","article-title":"Fast task inference with variational intrinsic successor features","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hansen","year":"2020"},{"key":"ref110","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare","year":"2016"},{"key":"ref111","first-page":"2721","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ostrovski","year":"2017"},{"key":"ref112","article-title":"URLB: Unsupervised reinforcement learning benchmark","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 2)","volume":"1","author":"Laskin","year":"2021"},{"key":"ref113","article-title":"Learning successor states and goal-dependent values: A mathematical viewpoint","author":"Blier","year":"2021"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.4.613"},{"key":"ref115","article-title":"Deep successor reinforcement learning","author":"Kulkarni","year":"2016"},{"key":"ref116","article-title":"Deepmind control suite","author":"Tassa","year":"2018"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref118","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Janner","year":"2022"},{"key":"ref119","article-title":"Stream of search (SoS): Learning to search in language","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Gandhi","year":"2024"},{"key":"ref120","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ouyang","year":"2022"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref122","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3506283"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-75417-8_57"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICRTCST54752.2022.9782047"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10491-7"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2021.10.006"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.09.017"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.07.010"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.3390\/asi5010027"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.3390\/app14041466"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.3390\/app12010135"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1016\/j.trpro.2021.07.052"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.3390\/app12020937"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.51393\/j.jamst.2024007"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2022.121893"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-8356-3_3"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1162\/DAED_a_00332"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-1914-4_154-1"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1016\/j.techfore.2025.124070"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/ICORR.2005.1501143"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0055975"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.937861"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3127874"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.3390\/robotics10010047"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.3390\/technologies9010008"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202008278"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abm6010"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1142\/S2424862222500154"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341260"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3207619"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610677"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2025.3555559"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.066"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-04239-4_11"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2026.3664167"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975643"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2021.3060963"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/280814.280820"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_20"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref168","first-page":"25268","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lin","year":"2023"},{"key":"ref169","article-title":"Motion-X: A large-scale multimodal 3D whole-body human motion dataset","author":"Zhang","year":"2025"},{"key":"ref170","article-title":"PHUMA: Physically-grounded humanoid locomotion dataset","author":"Lee","year":"2025"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids65713.2025.11203143"},{"key":"ref172","first-page":"1516","article-title":"OmniH2O: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","volume-title":"Proc. 8th Annu. Conf. Robot Learn.","author":"He","year":"2024"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1115\/1.4053806"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202308829"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300359"},{"key":"ref176","first-page":"38154","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Shen","year":"2023"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.669"},{"key":"ref178","article-title":"Chateval: Towards better LLM-based evaluators through multi-agent debate","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chan","year":"2024"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3534586"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3562422"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584698"},{"key":"ref182","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref183","first-page":"4057","article-title":"Unified scaling laws for routed language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Clark","year":"2022"},{"key":"ref184","first-page":"265","article-title":"Scaling laws for generative mixed-modal language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Aghajanyan","year":"2023"},{"key":"ref185","article-title":"Scaling laws for downstream task performance of large language models","volume-title":"Proc. ICLR Workshop Math. Empirical Understanding Found. Models","author":"Isik","year":"2024"},{"key":"ref186","first-page":"90318","article-title":"D-CPT law: Domain-specific continual pre-training scaling law for large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Que","year":"2024"},{"key":"ref187","article-title":"LLM post-training: A deep dive into reasoning large language models","author":"Kumar","year":"2025"},{"key":"ref188","article-title":"DISC-LawLLM: Fine-tuning large language models for intelligent legal services","author":"Yue","year":"2023"},{"key":"ref189","article-title":"LongLoRA: Efficient fine-tuning of long-context large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.410"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref192","first-page":"53038","article-title":"Fine-tuning language models with just forward passes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Malladi","year":"2023"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3657354"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3460180"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0482"},{"key":"ref196","article-title":"Skywork-reward: Bag of tricks for reward modeling in LLMs","author":"Liu","year":"2024"},{"key":"ref197","article-title":"RLHF workflow: From reward modeling to online RLHF","volume":"2024","author":"Dong","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref198","article-title":"UltraFeedback: Boosting language models with high-quality feedback","author":"Cui","year":"2023"},{"key":"ref199","first-page":"8657","article-title":"Guiding pretraining in reinforcement learning with large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du","year":"2023"},{"key":"ref200","article-title":"Self-refined large language model as automated reward function designer for deep reinforcement learning in robotics","author":"Song","year":"2023"},{"key":"ref201","article-title":"Magpie: Alignment data synthesis from scratch by prompting aligned LLMs with nothing","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Xu","year":"2025"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609633"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1670"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TRA.2002.806024"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICIInfS.2012.6304778"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114660"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004269"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2022.107336"},{"key":"ref211","article-title":"GPQA: A graduate-level Google-proof Q&A benchmark","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Rein","year":"2024"},{"key":"ref212","article-title":"Measuring mathematical problem solving with the math dataset","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","volume":"1","author":"Hendrycks","year":"2021"},{"key":"ref213","article-title":"MUSR: Testing the limits of chain-of-thought with multistep soft reasoning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sprague","year":"2024"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3507000"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3539433"},{"key":"ref216","article-title":"Ethical and social risks of harm from language models","author":"Weidinger","year":"2021"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13370"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1126\/science.adp1848"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630576"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1561\/2300000052"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2019.2940964"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11319214.pdf?arnumber=11319214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:32Z","timestamp":1773106472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11319214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":222,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3649177","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":[[2026,4]]}}}