{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:41:31Z","timestamp":1771922491861,"version":"3.50.1"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":["62173319"],"award-info":[{"award-number":["62173319"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,3]]},"DOI":"10.1109\/robio66223.2025.11376322","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:43:52Z","timestamp":1771879432000},"page":"403-408","source":"Crossref","is-referenced-by-count":0,"title":["Transferring General Models to Vertical Domains for Fine-Grained Discrete Control Under Data Scarcity"],"prefix":"10.1109","author":[{"given":"Guangyu","family":"Qu","sequence":"first","affiliation":[{"name":"Dalian University of Technology,Dalian,China,116024"}]},{"given":"Yongsheng","family":"Ou","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Science and Technology, School of Control Science and Engineering, Dalian University of Technology,Dalian,China,116024"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(71)90010-5"},{"key":"ref2","volume-title":"Pddl-the planning domain definition language","author":"Aeronautiques","year":"1998"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0070-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(85)90084-0"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref7","volume-title":"Solving the rubik\u2019s cube without human knowledge","author":"McAleer","year":"2018"},{"key":"ref8","first-page":"4582","article-title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li","year":"2021"},{"key":"ref9","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref10","first-page":"10088","article-title":"Qlora: Efficient finetuning of quantized 11 ms","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Dettmers","year":"2023"},{"key":"ref11","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Liu","year":"2022"},{"key":"ref12","article-title":"Multi-lora composition for image generation","author":"Zhong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref13","volume-title":"Parameterefficient fine-tuning for large models: A comprehensive survey","author":"Han","year":"2024"},{"key":"ref14","volume-title":"Self-supervision is all you need for solving rubik\u2019s cube","author":"Takano","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2314"},{"key":"ref16","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342230"},{"key":"ref18","first-page":"37607","article-title":"Masked trajectory models for prediction, representation, and control","volume-title":"International Conference on Machine Learning","author":"Wu","year":"2023"},{"key":"ref19","first-page":"3909","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions","volume-title":"Conference on Robot Learning","author":"Chebotar","year":"2023"},{"key":"ref20","article-title":"Q-value regularized transformer for offline reinforcement learning","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"Behavior generation with latent actions","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Should we ever prefer decision transformer for offline reinforcement learning?","author":"Omori","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"ref24","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Conference on Robot Learning","author":"Zitkovich","year":"2023"},{"key":"ref25","article-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","first-page":"09","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proceedings of the 36th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"97","author":"Houlsby","year":"2019"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18653\/v1\/2022.acl-short.1","article-title":"BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","author":"Ben Zaken","year":"2022"}],"event":{"name":"2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Chengdu, China","start":{"date-parts":[[2025,12,3]]},"end":{"date-parts":[[2025,12,7]]}},"container-title":["2025 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373909\/11375854\/11376322.pdf?arnumber=11376322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T07:36:38Z","timestamp":1771918598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11376322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/robio66223.2025.11376322","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}