{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:15:39Z","timestamp":1783188939192,"version":"3.54.6"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003819","name":"Hubei Province Natural Science Foundation","doi-asserted-by":"publisher","award":["2025AFA055"],"award-info":[{"award-number":["2025AFA055"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132833","type":"journal-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:24:45Z","timestamp":1778757885000},"page":"132833","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HiQST: A unified hierarchical quantized skill framework for multitask and few-shot robotic manipulation"],"prefix":"10.1016","volume":"327","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1157-1346","authenticated-orcid":false,"given":"Guangpeng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9036-0290","authenticated-orcid":false,"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5917-2294","authenticated-orcid":false,"given":"Wupeng","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6884-7935","authenticated-orcid":false,"given":"Jiwei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9257-7154","authenticated-orcid":false,"given":"Zude","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132833_sbref0001","series-title":"Autort: Embodied foundation models for large scale orchestration of robotic agents","author":"Ahn","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0002","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1109\/TASE.2025.3637854","article-title":"Practical mixed palletizing manipulator system: Incorporating practical reinforcement learning and configuration-space motion planning","volume":"23","author":"Ahn","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"9","key":"10.1016\/j.eswa.2026.132833_bib0003","doi-asserted-by":"crossref","first-page":"9024","DOI":"10.1109\/LRA.2025.3583608","article-title":"Few-shot transfer of tool-use skills using human demonstrations with proximity and tactile sensing","volume":"10","author":"Aoyama","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.132833_sbref0004","series-title":"Gen2act: Human video generation in novel scenarios enables generalizable robot manipulation","author":"Bharadhwaj","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_sbref0005","series-title":"Rt-1: Robotics transformer for real-world control at scale","author":"Brohan","year":"2022"},{"key":"10.1016\/j.eswa.2026.132833_sbref0006","series-title":"Learning to act anywhere with task-centric latent actions","author":"Bu","year":"2025"},{"issue":"10\u201311","key":"10.1016\/j.eswa.2026.132833_bib0007","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1177\/02783649241273668","article-title":"Diffusion policy: Visuomotor policy learning via action diffusion","volume":"44","author":"Chi","year":"2025","journal-title":"The International Journal of Robotics Research"},{"key":"10.1016\/j.eswa.2026.132833_sbref0008","series-title":"Griffin: Mixing gated linear recurrences with local attention for efficient language models","author":"De","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0009","series-title":"2024\u202fIEEE international conference on robotics and automation (ICRA)","first-page":"2798","article-title":"Dinobot: Robot manipulation via retrieval and alignment with vision foundation models","author":"Di Palo","year":"2024"},{"issue":"10","key":"10.1016\/j.eswa.2026.132833_bib0010","doi-asserted-by":"crossref","first-page":"8579","DOI":"10.1109\/LRA.2024.3445630","article-title":"A comparison of imitation learning algorithms for bimanual manipulation","volume":"9","author":"Drolet","year":"2024","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.132833_bib0011","series-title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets","author":"Ebert","year":"2021"},{"key":"10.1016\/j.eswa.2026.132833_bib0012","doi-asserted-by":"crossref","first-page":"35544","DOI":"10.52202\/075280-1544","article-title":"Improving clip training with language rewrites","volume":"36","author":"Fan","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0013","series-title":"First conference on language modeling","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106251","article-title":"Bagail: Multi-modal imitation learning from imbalanced demonstrations","volume":"174","author":"Gu","year":"2024","journal-title":"Neural Networks"},{"issue":"2","key":"10.1016\/j.eswa.2026.132833_bib0015","doi-asserted-by":"crossref","first-page":"1672","DOI":"10.1109\/LRA.2024.3524904","article-title":"Variation-robust few-shot 3d affordance segmentation for robotic manipulation","volume":"10","author":"Hu","year":"2025","journal-title":"IEEE Robotics and Automation Letters"},{"key":"10.1016\/j.eswa.2026.132833_bib0016","first-page":"1","article-title":"Hypernet: Self-supervised hyperspectral spatial\u2013spectral feature understanding network for hyperspectral change detection","volume":"60","author":"Hu","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.eswa.2026.132833_bib0017","series-title":"2024\u202fIEEE international conference on robotics and automation (ICRA)","first-page":"300","article-title":"Collision avoidance and navigation for a quadrotor swarm using end-to-end deep reinforcement learning","author":"Huang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_sbref0018","series-title":"Vid2robot: End-to-end video-conditioned policy learning with cross-attention transformers","author":"Jain","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0019","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2024","article-title":"Causal motion tokenizer for streaming motion generation","author":"Jiang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_sbref0020","series-title":"H-gap: Humanoid control with a generalist planner","author":"Jiang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_sbref0021","series-title":"Efficient planning in a compact latent action space","author":"Jiang","year":"2022"},{"issue":"31","key":"10.1016\/j.eswa.2026.132833_bib0022","first-page":"1","article-title":"Sample-efficient adversarial imitation learning","volume":"25","author":"Jung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.eswa.2026.132833_sbref0023","series-title":"Language-driven representation learning for robotics","author":"Karamcheti","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128734","article-title":"Functional connectivity guided deep neural network for decoding high-level visual imagery","volume":"294","author":"Kwon","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132833_sbref0025","series-title":"Behavior generation with latent actions","author":"Lee","year":"2024"},{"issue":"39","key":"10.1016\/j.eswa.2026.132833_bib0026","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"10.1016\/j.eswa.2026.132833_bib0027","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/MRA.2025.3642671","article-title":"The developments and challenges toward dexterous and embodied robotic manipulation: A survey","volume":"33","author":"Li","year":"2025","journal-title":"IEEE Robotics & Automation Magazine"},{"key":"10.1016\/j.eswa.2026.132833_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122881","article-title":"Rethinking scene representation: A saliency-driven hierarchical multi-scale resampling for RGB-d scene point cloud in robotic applications","volume":"243","author":"Li","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132833_sbref0029","series-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0030","doi-asserted-by":"crossref","first-page":"44776","DOI":"10.52202\/075280-1939","article-title":"Libero: Benchmarking knowledge transfer for lifelong robot learning","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0031","article-title":"A hierarchical active inference framework for stable robotic control","author":"Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"10.1016\/j.eswa.2026.132833_bib0032","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1109\/TCSVT.2024.3495533","article-title":"Variational feature imitation conditioned on visual descriptions for few-shot fine-grained recognition","volume":"35","author":"Lu","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.eswa.2026.132833_bib0033","series-title":"Conference on robot learning","first-page":"1113","article-title":"Learning latent plans from play","author":"Lynch","year":"2020"},{"key":"10.1016\/j.eswa.2026.132833_bib0034","series-title":"2022 international conference on robotics and automation (ICRA)","first-page":"2434","article-title":"Towards more generalizable one-shot visual imitation learning","author":"Mandi","year":"2022"},{"key":"10.1016\/j.eswa.2026.132833_sbref0035","series-title":"Finite scalar quantization: Vq-vae made simple","author":"Mentzer","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_bib0036","doi-asserted-by":"crossref","first-page":"4062","DOI":"10.52202\/079017-0133","article-title":"Quest: Self-supervised skill abstractions for learning continuous control","volume":"37","author":"Mete","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0037","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Film: Visual reasoning with a general conditioning layer","volume":"vol. 32","author":"Perez","year":"2018"},{"key":"10.1016\/j.eswa.2026.132833_bib0038","series-title":"Conference on robot learning","first-page":"188","article-title":"Accelerating reinforcement learning with learned skill priors","author":"Pertsch","year":"2021"},{"key":"10.1016\/j.eswa.2026.132833_bib0039","series-title":"2017\u202fIEEE-RAS 17th international conference on humanoid robotics (humanoids)","first-page":"191","article-title":"Learning deep movement primitives using convolutional neural networks","author":"Pervez","year":"2017"},{"key":"10.1016\/j.eswa.2026.132833_sbref0040","series-title":"Learning complex dexterous manipulation with deep reinforcement learning and demonstrations","author":"Rajeswaran","year":"2017"},{"key":"10.1016\/j.eswa.2026.132833_sbref0041","series-title":"Goal-conditioned imitation learning using score-based diffusion policies","author":"Reuss","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_bib0042","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","author":"Shen","year":"2021"},{"key":"10.1016\/j.eswa.2026.132833_sbref0043","series-title":"Latent diffusion model without variational autoencoder","author":"Shi","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_sbref0044","series-title":"Parrot: Data-driven behavioral priors for reinforcement learning","author":"Singh","year":"2020"},{"key":"10.1016\/j.eswa.2026.132833_bib0045","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/j.jmsy.2026.01.018","article-title":"A human\u2013robot collaborative framework for draping of advanced composite materials","volume":"85","author":"Terreran","year":"2026","journal-title":"Journal of Manufacturing Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0046","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0047","article-title":"Damf: A semantic-guided dynamic attention framework for visual-haptic-textual multimodal fusion","author":"Wang","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132833_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22883","article-title":"Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_sbref0049","series-title":"Sparse diffusion policy: A sparse, reusable, and flexible policy for robot learning","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_sbref0050","series-title":"Vq-vla: Improving vision-language-action models via scaling vector-quantized action tokenizers","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_bib0051","series-title":"Forty-second international conference on machine learning","article-title":"DiffusionVLA: Scaling robot foundation models via unified diffusion and autoregression","author":"Wen","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_bib0052","series-title":"2024\u202fIEEE\/RSJ international conference on intelligent robots and systems (IROS)","first-page":"12156","article-title":"Gello: A general, low-cost, and intuitive teleoperation framework for robot manipulators","author":"Wu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0053","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19801","article-title":"Mvhumannet: A large-scale dataset of multi-view daily dressing human captures","author":"Xiong","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_sbref0054","series-title":"Speci: Skill prompts based hierarchical continual imitation learning for robot manipulation","author":"Xu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_sbref0055","series-title":"Gated linear attention transformers with hardware-efficient training","author":"Yang","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_bib0056","series-title":"Conference on robot learning","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2020"},{"issue":"12","key":"10.1016\/j.eswa.2026.132833_bib0057","doi-asserted-by":"crossref","first-page":"7173","DOI":"10.1109\/TCYB.2024.3395626","article-title":"A survey of imitation learning: Algorithms, recent developments, and challenges","volume":"54","author":"Zare","year":"2024","journal-title":"IEEE Transactions on Cybernetics"},{"key":"10.1016\/j.eswa.2026.132833_bib0058","doi-asserted-by":"crossref","DOI":"10.1016\/j.rcim.2025.103021","article-title":"Dexterous hand towards intelligent manufacturing: A review of technologies, trends, and potential applications","volume":"95","author":"Zhang","year":"2025","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"key":"10.1016\/j.eswa.2026.132833_bib0059","doi-asserted-by":"crossref","first-page":"116870","DOI":"10.52202\/079017-3710","article-title":"Gated slot attention for efficient linear-time sequence modeling","volume":"37","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132833_sbref0060","series-title":"Learning fine-grained bimanual manipulation with low-cost hardware","author":"Zhao","year":"2023"},{"key":"10.1016\/j.eswa.2026.132833_bib0061","unstructured":"Zheng, R., Cheng, C.-A., Daum\u00e9 III, H., Huang, F., & Kolobov, A. (2024). Prise: Llm-style sequence compression for learning temporal action abstractions in control. arXiv: 2402.10450."},{"key":"10.1016\/j.eswa.2026.132833_sbref0062","series-title":"Mvmoe: Multi-task vehicle routing solver with mixture-of-experts","author":"Zhou","year":"2024"},{"key":"10.1016\/j.eswa.2026.132833_bib0063","series-title":"Proceedings of the 34th ACM international conference on information and knowledge management","first-page":"4529","article-title":"Latentexplainer: Explaining latent representations in deep generative models with multimodal large language models","author":"Zhu","year":"2025"},{"key":"10.1016\/j.eswa.2026.132833_bib0064","series-title":"Conference on robot learning","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Zitkovich","year":"2023"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601746X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742601746X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:20:29Z","timestamp":1783185629000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742601746X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":64,"alternative-id":["S095741742601746X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132833","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HiQST: A unified hierarchical quantized skill framework for multitask and few-shot robotic manipulation","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132833","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132833"}}