{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T03:19:22Z","timestamp":1773976762938,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819620630","type":"print"},{"value":"9789819620647","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2064-7_25","type":"book-chapter","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:25:23Z","timestamp":1735327523000},"page":"340-353","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["RoLD: Robot Latent Diffusion for\u00a0Multi-task Policy Modeling"],"prefix":"10.1007","author":[{"given":"Wenhui","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Chaumette, F., Hutchinson, S.: Visual servo control. I. basic approaches. IEEE Robot. Autom. Mag. 13(4), 82\u201390 (2006)","DOI":"10.1109\/MRA.2006.250573"},{"key":"25_CR2","first-page":"15084","volume":"34","author":"L Chen","year":"2021","unstructured":"Chen, L., et al.: Decision transformer: reinforcement learning via sequence modeling. Adv. Neural. Inf. Process. Syst. 34, 15084\u201315097 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Chi, C., et al.: diffusion policy: visuomotor policy learning via action diffusion, June 2023. arXiv:2303.04137 [cs]","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"25_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"25_CR5","unstructured":"Du, Y., et al.: Learning universal policies via text-guided video generation, February 2023. arXiv:2302.00111 [cs]"},{"key":"25_CR6","first-page":"21711","volume":"35","author":"D Garg","year":"2022","unstructured":"Garg, D., Vaidyanath, S., Kim, K., Song, J., Ermon, S.: LISA: learning interpretable skill abstractions from language. Adv. Neural. Inf. Process. Syst. 35, 21711\u201321724 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR7","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR10","unstructured":"Jiang, Y., et al.: VIMA: general robot manipulation with multimodal prompts, May 2023. arXiv:2210.03094 [cs]"},{"key":"25_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"25_CR13","unstructured":"Majumdar, A., et al.: Where are we in the search for an artificial visual cortex for embodied intelligence? (2023)"},{"key":"25_CR14","unstructured":"Mandlekar, A., et al.: What matters in learning from offline human demonstrations for robot manipulation. arXiv preprint arXiv:2108.03298"},{"key":"25_CR15","unstructured":"Nair, S., Rajeswaran, A., Kumar, V., Finn, C., Gupta, A.: R3M: a universal visual representation for robot manipulation, November 2022. arXiv:2203.12601 [cs]"},{"key":"25_CR16","unstructured":"Brohan, A., et al.: RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control"},{"key":"25_CR17","unstructured":"Padalkar, A., et al.: Open X-Embodiment: Robotic Learning Datasets and RT-X Models"},{"key":"25_CR18","unstructured":"Reed, S., et al.: A Generalist Agent, November 2022. arXiv:2205.06175 [cs]"},{"key":"25_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"25_CR21","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"25_CR22","unstructured":"Siegel, N.Y., et al.: Keep doing what worked: behavioral modelling priors for offline reinforcement learning. arXiv preprint arXiv:2002.08396 (2020)"},{"key":"25_CR23","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"25_CR24","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"25_CR25","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"25_CR26","unstructured":"Yang, J., Liu, B., Fu, J., Pan, B., Wu, G., Wang, L.: Spatiotemporal predictive pre-training for robotic motor control. arXiv preprint arXiv:2403.05303 (2024)"},{"key":"25_CR27","unstructured":"Yang, J., et al.: Pave the way to grasp anything: transferring foundation models for universal pick-place robots. arXiv preprint arXiv:2306.05716 (2023)"},{"key":"25_CR28","unstructured":"Yu, T., et al.: Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning. In: Conference on Robot Learning (CoRL) (2019)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Zeng, Y., et al.: What matters in training a GPT4-style language model with multimodal inputs? arXiv preprint arXiv:2307.02469 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.440"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware, April 2023. arXiv:2304.13705 [cs]","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"25_CR31","unstructured":"Zhao, W.X., et\u00a0al.: A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2064-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T20:04:52Z","timestamp":1735329892000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2064-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"ISBN":["9789819620630","9789819620647"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2064-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"28 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}