{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T17:06:52Z","timestamp":1789405612219,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384034","type":"print"},{"value":"9783032384041","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38404-1_23","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T16:46:39Z","timestamp":1789404399000},"page":"279-291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision-Language-Action Model Optimization for\u00a0Real-Time Robotic Manipulation"],"prefix":"10.1007","author":[{"given":"Juyi","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amir","family":"Taherin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arash","family":"Akbari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arman","family":"Akbari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taskin","family":"Padir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jayanth","family":"Srinivasa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"23_CR1","unstructured":"Beyer, L., Steiner, A., Pinto, A.S.: PaliGemma: a versatile 3B VLM for transfer. arXiv preprint: arXiv:2407.07726 (2024)"},{"key":"23_CR2","unstructured":"Black, K., Brown, N., Driess, D., et\u00a0al.: $$ \\pi _0 $$: a vision-language-action flow model for general robot control. arXiv preprint: arXiv:2410.24164 (2024)"},{"key":"23_CR3","unstructured":"Brohan, A., Brown, N., Carbajal, J.: RT-1: robotics transformer for real-world control at scale. arXiv preprint: arXiv:2212.06817 (2022)"},{"key":"23_CR4","unstructured":"Brohan, A., Brown, N., Carbajal, J.: Rt-2: vision-language-action models transfer web knowledge to robotic control (2023)"},{"key":"23_CR5","unstructured":"Chen, X., Djolonga, J., Padlewski, P.: PaLI-X: on scaling up a multilingual vision and language model. arXiv preprint: arXiv:2305.18565 (2023)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chi, C., Xu, Z., Feng, S.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robot. Res. (2023)","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"23_CR7","unstructured":"Driess, D., Xia, F., Sajjadi, M.S.: PaLM-E: an embodied multimodal language model. arXiv preprint: arXiv:2303.03378 (2023)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Fang, H.S., Fang, H., Tang, Z., et\u00a0al.: RH20T: a comprehensive robotic dataset for learning diverse skills in one-shot. In: ICRA, pp. 653\u2013660. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611615"},{"issue":"2","key":"23_CR9","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., Shen, Y., Wallis, P., et al.: LoRA: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"23_CR10","unstructured":"Karamcheti, S., Nair, S.: Prismatic VLMs: investigating the design space of visually-conditioned language models. In: ICML (2024)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Kim, M.J., Finn, C., Liang, P.: Fine-tuning vision-language-action models: optimizing speed and success. arXiv preprint: arXiv:2502.19645 (2025)","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"23_CR12","unstructured":"Kim, M.J., Pertsch, K., Karamcheti, S.: OpenVLA: an open-source vision-language-action model. arXiv preprint: arXiv:2406.09246 (2024)"},{"key":"23_CR13","unstructured":"Leela, S.K.: NVIDIA Jetson AGX Orin Series Technical Brief: a giant leap forward for robotics and edge AI applications (2022)"},{"key":"23_CR14","unstructured":"Li, Q.: CogACT: a foundational vision-language-action model for synergizing cognition and action in robotic manipulation (2024). arXiv:2411.19650"},{"key":"23_CR15","unstructured":"Li, X., Li, P., Liu, M., et\u00a0al.: Towards generalist robot policies: What matters in building vision-language-action models. arXiv preprint: arXiv:2412.14058 (2024)"},{"key":"23_CR16","unstructured":"Li, X., Liu, M., Zhang, H., et\u00a0al.: Vision-language foundation models as effective robot imitators. arXiv preprint: arXiv:2311.01378 (2023)"},{"key":"23_CR17","unstructured":"Li, X., Hsu, K., Gu, J.: Evaluating real-world robot manipulation policies in simulation. arXiv preprint: arXiv:2405.05941 (2024)"},{"key":"23_CR18","unstructured":"Li, Y., Deng, Y.: HAMSTER: hierarchical action models for open-world robot manipulation (2025). arXiv:2502.05485"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhu, Y., Gao, C.: LIBERO: benchmarking knowledge transfer for lifelong robot learning. NeurIPS (2023)","DOI":"10.52202\/075280-1939"},{"key":"23_CR20","unstructured":"Mi, Z., Chen, Y., Zhao, P.: Effective MoE-based LLM compression by exploiting heterogeneous inter-group experts routing frequency and information density. arXiv preprint: arXiv:2602.09316 (2026)"},{"key":"23_CR21","unstructured":"O\u2019Neill, A., et\u00a0al.: Open X-embodiment: robotic learning datasets and RT-X models: open X-embodiment collaboration 0. In: ICRA. IEEE (2024)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Pertsch, K., Stachowicz, K., Ichter, B.: FAST: efficient action tokenization for vision-language-action models. arXiv preprint: arXiv:2501.09747 (2025)","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Qu, D., Song, H., Chen, Q.: SpatialVLA: exploring spatial representations for visual-language-action model. arXiv preprint: arXiv:2501.15830 (2025)","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"23_CR24","unstructured":"Shen, X., Han, C., Zhou, Y.: DraftAttention: fast video diffusion via low-resolution attention guidance. arXiv preprint: arXiv:2505.14708 (2025)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Shen, X., Ma, W., Liu, J.: QuartDepth: post-training quantization for real-time depth estimation on the edge. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01069"},{"key":"23_CR26","unstructured":"Shen, X., Ma, W., Zhou, Y.: FastCar: cache attentive replay for fast auto-regressive video generation on the edge. In: ICLR (2026)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Shen, X., Song, Z., Zhou, Y., et\u00a0al.: LazyDiT: lazy learning for the acceleration of diffusion transformers. AAAI 39(19) (2025)","DOI":"10.1609\/aaai.v39i19.34248"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Shen, X., Song, Z., Zhou, Y., et\u00a0al.: Numerical pruning for efficient autoregressive models. AAAI 39(19) (2025)","DOI":"10.1609\/aaai.v39i19.34249"},{"key":"23_CR29","unstructured":"Shen, X., Wang, Y.: Efficient reasoning with hidden thinking. arXiv preprint: arXiv:2501.19201 (2025)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Shen, X., Zhao, P., Gong, Y.: Search for efficient large language models. In: Advances in Neural Information Processing Systems, vol. 37 (2024)","DOI":"10.52202\/079017-4421"},{"key":"23_CR31","unstructured":"Shen, X., Zheng, H., Gong, Y.: Sparse learning for state space models on mobile. In: ICLR (2025)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Shentu, Y., Wu, P., et\u00a0al.: From LLMs to actions: latent codes as bridges in hierarchical robot control. In: IROS. IEEE (2024)","DOI":"10.1109\/IROS58592.2024.10801683"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Taherin, A., et al.: Cross-platform scaling of vision-language-action models from edge to cloud GPUs. arXiv preprint: arXiv:2509.11480 (2025)","DOI":"10.1145\/3787109.3816400"},{"key":"23_CR34","unstructured":"Team, O.M., Ghosh, D., Walke, H.: Octo: an open-source generalist robot policy. arXiv preprint: arXiv:2405.12213 (2024)"},{"key":"23_CR35","unstructured":"Walke, H.R., Black, K., Zhao, T.Z.: BridgeData V2: a dataset for robot learning at scale. In: Conference on Robot Learning, pp. 1723\u20131736. PMLR (2023)"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Yang, C., Zhao, P., Li, Y.: Pruning parameterization with bi-level optimization for efficient semantic segmentation on the edge. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01478"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: ALTER: all-in-one layer pruning and temporal expert routing for efficient diffusion generation. In: Advances in Neural Information Processing Systems, vol. 38, pp. 128571\u2013128599 (2026)","DOI":"10.52202\/085713-4283"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Zhan, Z., Kong, Z., Gong, Y.: Exploring token pruning in vision state space models. In: NeurIPS (2024)","DOI":"10.52202\/079017-1613"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Zhan, Z., Wu, Y., Gong, Y.: Fast and memory-efficient video diffusion using streamlined inference. In: Fast and Memory-Efficient Video Diffusion Using Streamlined Inference, vol. 37 (2024)","DOI":"10.52202\/079017-0437"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Zhan, Z., Wu, Y., Kong, Z.: Rethinking token reduction for state space models. In: EMNLP. ACL (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.100"},{"key":"23_CR41","unstructured":"Zhao, P., Akbari, A., Shen, X.: Open-source multimodal Moxin models with Moxin-VLM and Moxin-VLA. arXiv preprint: arXiv:2512.22208 (2025)"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, P., Sun, F., Shen, X., et\u00a0al.: Pruning foundation models for high accuracy without retraining. In: Findings of EMNLP 2024, pp. 9681\u20139694. ACL (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.566"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. arXiv preprint: arXiv:2304.13705 (2023)","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"23_CR44","unstructured":"Zheng, R., Liang, Y.: TraceVLA: visual trace prompting enhances spatial-temporal awareness for generalist robotic policies (2024). arXiv:2412.10345"},{"key":"23_CR45","unstructured":"Zhu, M., Zhu, Y., Li, J., et\u00a0al.: ObjectVLA: end-to-end open-world object manipulation without demonstration. arXiv preprint: arXiv:2502.19250 (2025)"},{"key":"23_CR46","unstructured":"Zitkovich, B., Yu, T.: RT-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning. PMLR (2023)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38404-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T16:46:53Z","timestamp":1789404413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38404-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"ISBN":["9783032384034","9783032384041"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38404-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]},"assertion":[{"value":"15 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Padua","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}