{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:22:42Z","timestamp":1775665362154,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}]},{"name":"Scientific Research Innovation Capability Support Project for Young Faculty","award":["ZYGXQNJSKYCXNLZCXM-I28"],"award-info":[{"award-number":["ZYGXQNJSKYCXNLZCXM-I28"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Nansha Key Research and Development Program","award":["2022ZD014"],"award-info":[{"award-number":["2022ZD014"]}]},{"name":"Pengcheng Laboratory Major Research Project","award":["PCL2025A02"],"award-info":[{"award-number":["PCL2025A02"]}]},{"name":"Pengcheng Laboratory Major Research Project","award":["PCL2024A04"],"award-info":[{"award-number":["PCL2024A04"]}]},{"DOI":"10.13039\/501100001809","name":"General Embodied AI Center of Sun Yat-sen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tnnls.2025.3594117","type":"journal-article","created":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:23:30Z","timestamp":1757096610000},"page":"20092-20104","source":"Crossref","is-referenced-by-count":1,"title":["Surfer: A World Model-Based Framework for Vision-Language Robot Manipulation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9965-8088","authenticated-orcid":false,"given":"Pengzhen","family":"Ren","sequence":"first","affiliation":[{"name":"PengCheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8678-6895","authenticated-orcid":false,"given":"Kaidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hetao","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1553-3748","authenticated-orcid":false,"given":"Zixuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6644-4075","authenticated-orcid":false,"given":"Yuhang","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengda","family":"Zhu","sequence":"additional","affiliation":[{"name":"ByteDance Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8340-9762","authenticated-orcid":false,"given":"Shikui","family":"Ma","sequence":"additional","affiliation":[{"name":"Hunan Artificial Intelligence and Robotics Institute Company Ltd., Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02100"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref3","article-title":"Unleashing large-scale video generative pre-training for visual robot manipulation","author":"Wu","year":"2023","journal-title":"arXiv:2312.13139"},{"key":"ref4","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","volume-title":"Proc. Int. Conf. Robot. Learn.","author":"Kalashnikov"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461249"},{"key":"ref6","article-title":"MT-opt: Continuous multi-task robotic reinforcement learning at scale","author":"Kalashnikov","year":"2021","journal-title":"arXiv:2104.08212"},{"key":"ref7","first-page":"991","article-title":"BC-Z: Zero-shot task generalization with robotic imitation learning","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Jang"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref9","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"},{"key":"ref10","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Annu. Conf. Robot Learn.","author":"Brohan"},{"key":"ref11","first-page":"1","article-title":"Open X-embodiment: Robotic learning datasets and RT-X models","volume-title":"Proc. Towards Generalist Robots, Learn. Paradigms Scalable Skill Acquisition@ CoRL","author":"Collaboration"},{"key":"ref12","article-title":"Vision-language foundation models as effective robot imitators","author":"Li","year":"2023","journal-title":"arXiv:2311.01378"},{"key":"ref13","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2019","journal-title":"arXiv:1912.01603"},{"key":"ref14","first-page":"25","article-title":"Improving PILCO with Bayesian neural network dynamics models","volume-title":"Proc. Data-Efficient Mach. Learn. Workshop","volume":"4","author":"Gal"},{"key":"ref15","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"Ebert","year":"2018","journal-title":"arXiv:1812.00568"},{"key":"ref16","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sekar"},{"key":"ref17","article-title":"Mastering Atari with discrete world models","author":"Hafner","year":"2020","journal-title":"arXiv:2010.02193"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00131"},{"key":"ref19","first-page":"1332","article-title":"Masked world models for visual control","volume-title":"Proc. Conf. Robot Learn.","author":"Seo"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1176\/appi.books.9781585622665.33114"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref23","first-page":"251","article-title":"Habitat 2.0: Training home assistants to rearrange their habitat","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Szot"},{"key":"ref24","first-page":"1","article-title":"ManiSkill2: A unified benchmark for generalizable manipulation skills","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"ref26","article-title":"IGibson 2.0: Object-centric simulation for robot learning of everyday household tasks","author":"Li","year":"2021","journal-title":"arXiv:2108.03272"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01075"},{"key":"ref28","first-page":"665","article-title":"VLMbench: A compositional benchmark for vision-and-language manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref29","first-page":"12014","article-title":"HandMeThat: Human\u2013robot communication in physical and social environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.090"},{"key":"ref31","first-page":"1","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ha"},{"key":"ref32","article-title":"DriveDreamer: Towards real-world-driven world models for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv:2309.09777"},{"key":"ref33","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref34","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref35","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref36","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref37","volume-title":"Vicuna: An Open-source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref38","volume-title":"Stanford Alpaca: An Instruction-Following Llama Model","author":"Taori et al","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref40","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"arXiv:2201.11903"},{"key":"ref41","article-title":"Self-consistency improves chain of thought reasoning in language models","author":"Wang","year":"2022","journal-title":"arXiv:2203.11171"},{"key":"ref42","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023","journal-title":"arXiv:2305.10601"},{"key":"ref43","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv:2303.04671"},{"key":"ref44","volume-title":"Video-ChatGPT","author":"Maaz","year":"2023"},{"key":"ref45","first-page":"477","article-title":"BEHAVIOR: Benchmark for everyday household activities in virtual, interactive, and ecological environments","volume-title":"Proc. 5th Conf. Robot Learn.","author":"Srivastava"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref47","first-page":"1","article-title":"ALFWorld: Aligning text and embodied environments for interactive learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shridhar"},{"key":"ref48","first-page":"1","article-title":"VIMA: General robot manipulation with multimodal prompts","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref49","article-title":"HomeRobot: Open-vocabulary mobile manipulation","author":"Yenamandra","year":"2023","journal-title":"arXiv:2306.11565"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20097"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3193254"},{"key":"ref52","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arxiv:2103.00020"},{"key":"ref53","first-page":"12786","article-title":"TokenLearner: Adaptive space-time tokenization for videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ryoo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref55","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019","journal-title":"arXiv:1910.10683"},{"key":"ref56","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Zeng"},{"key":"ref57","article-title":"Robosuite: A modular simulation framework and benchmark for robot learning","author":"Zhu","year":"2020","journal-title":"arXiv:2009.12293"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812302"},{"key":"ref59","first-page":"1","article-title":"ManiSkill: Generalizable manipulation skill benchmark with large-scale demonstrations","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 2)","author":"Mu"},{"key":"ref60","article-title":"LIBERO: Benchmarking knowledge transfer for lifelong robot learning","author":"Liu","year":"2023","journal-title":"arXiv:2306.03310"},{"key":"ref61","article-title":"RoboCasa: Large-scale simulation of everyday tasks for generalist robots","author":"Nasiriany","year":"2024","journal-title":"arXiv:2406.02523"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref64","volume-title":"Introducing ChatGPT","year":"2023"},{"key":"ref65","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref66","article-title":"Self-instruct: Aligning language models with self-generated instructions","author":"Wang","year":"2022","journal-title":"arXiv:2212.10560"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.105"},{"key":"ref68","article-title":"Cross-task generalization via natural language crowdsourcing instructions","author":"Mishra","year":"2021","journal-title":"arXiv:2104.08773"},{"key":"ref69","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2021","journal-title":"arXiv:2109.01652"},{"key":"ref70","article-title":"Rapidly-exploring random trees: A new tool for path planning","author":"LaValle","year":"1998"},{"key":"ref71","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"arXiv:2205.06175"},{"key":"ref72","article-title":"OpenVLA: An open-source vision-language-action model","author":"Jin Kim","year":"2024","journal-title":"arXiv:2406.09246"},{"key":"ref73","article-title":"Zero-shot robotic manipulation with pretrained image-editing diffusion models","author":"Black","year":"2023","journal-title":"arXiv:2310.10639"},{"issue":"140","key":"ref74","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref76","article-title":"All robots in one: A new standard and unified dataset for versatile, general-purpose embodied agents","author":"Wang","year":"2024","journal-title":"arXiv:2408.10899"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11272992\/11152367.pdf?arnumber=11152367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:43:30Z","timestamp":1764787410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11152367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":76,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3594117","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}