{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:59:10Z","timestamp":1789163950290,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373618","type":"print"},{"value":"9783032373625","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37362-5_9","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:08:06Z","timestamp":1789034886000},"page":"163-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SAFE-Pruner: Semantic Attention\u2013Guided Future-Aware Token Pruning for\u00a0Efficient Vision-Language-Action Manipulation"],"prefix":"10.1007","author":[{"given":"Shilin","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chubin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuji","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingqi","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Alvar, S.R., Singh, G., Akbari, M., Zhang, Y.: Divprune: diversity-based visual token pruning for large multimodal models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9392\u20139401 (2025)","DOI":"10.1109\/CVPR52734.2025.00877"},{"key":"9_CR2","unstructured":"Bai, S.: Qwen2.5-VL Technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"9_CR3","unstructured":"Beyer, L., et al.: Paligemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"9_CR4","unstructured":"Bjorck, J., et\u00a0al.: Gr00t n1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"9_CR5","unstructured":"Black, K., et\u00a0al.: $$\\pi _0 $$: a vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"9_CR6","unstructured":"Brohan, A., et al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"9_CR7","unstructured":"Brohan, A., et al.: Rt-1: robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2023)"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: An image is worth 1\/2 tokens after layer 2: plug-and-play inference acceleration for large vision-language models. In: European Conference on Computer Vision, pp. 19\u201335. Springer (2024)","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"9_CR9","unstructured":"Chen, X., Djolo et al.: Pali-x: on scaling up a multilingual vision and language model. arXiv preprint arXiv:2305.18565 (2023)"},{"issue":"10\u201311","key":"9_CR10","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1177\/02783649241273668","volume":"44","author":"C Chi","year":"2025","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Int. J. Robo. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Robo. Res."},{"key":"9_CR11","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.52202\/068431-1189","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. Adv. Neural. Inf. Process. Syst. 35, 16344\u201316359 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR12","unstructured":"Dasari, S., et al.: Robonet: large-scale multi-robot learning. arXiv preprint arXiv:1910.11215 (2020)"},{"key":"9_CR13","unstructured":"Dong, S., et al.: Vita-VLA: efficiently teaching vision-language models to act via action expert distillation. arXiv preprint arXiv:2510.09607 (2025)"},{"key":"9_CR14","unstructured":"Driess, D., et al.: Palm-e: an embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Ebert, F., et al.: Bridge data: boosting generalization of robotic skills with cross-domain datasets. arXiv preprint arXiv:2109.13396 (2021)","DOI":"10.15607\/RSS.2022.XVIII.063"},{"key":"9_CR16","unstructured":"Gao, G., et al.: Towards human-level intelligence via human-like whole-body manipulation. arXiv preprint arXiv:2507.17141 (2025)"},{"key":"9_CR17","unstructured":"Kalashnikov, D., et al.: Mt-opt: continuous multi-task robotic reinforcement learning at scale. arXiv preprint arXiv:2104.08212 (2021)"},{"key":"9_CR18","unstructured":"Karamcheti, S., Nair, S., Balakrishna, A., Liang, P., Kollar, T., Sadigh, D.: Prismatic VLMS: investigating the design space of visually-conditioned language models. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"9_CR19","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":"9_CR20","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with pagedattention. arXiv preprint arXiv:2309.06180 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"9_CR22","unstructured":"Li, Q., et\u00a0al.: Cogact: a foundational vision-language-action model for synergizing cognition and action in robotic manipulation. arXiv preprint arXiv:2411.19650 (2024)"},{"key":"9_CR23","unstructured":"Li, X., Het al.: Evaluating real-world robot manipulation policies in simulation. arXiv preprint arXiv:2405.05941 (2024)"},{"key":"9_CR24","doi-asserted-by":"publisher","first-page":"44776","DOI":"10.52202\/075280-1939","volume":"36","author":"B Liu","year":"2023","unstructured":"Liu, B., et al.: Libero: benchmarking knowledge transfer for lifelong robot learning. Adv. Neural. Inf. Process. Syst. 36, 44776\u201344791 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR25","unstructured":"Liu, Z., et al.: Vla-pruner: temporal-aware dual-level visual token pruning for efficient vision-language-action inference. arXiv preprint arXiv:2511.16449 (2025)"},{"key":"9_CR26","unstructured":"Luo, Y., et al.: Ascend hifloat8 format for deep learning. arXiv preprint arXiv:2409.16626 (2024)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Lv, Z., Fan, Z., Tian, Q., Zhang, W., Zhuang, Y.: Enhancing post-training quantization via future activation awareness. arXiv preprint arXiv:2602.02538 (2026)","DOI":"10.1109\/ICASSP55912.2026.11465076"},{"issue":"3","key":"9_CR28","doi-asserted-by":"publisher","first-page":"7327","DOI":"10.1109\/LRA.2022.3180108","volume":"7","author":"O Mees","year":"2022","unstructured":"Mees, O., Hermann, L., Rosete-Beas, E., Burgard, W.: Calvin: a benchmark for language-conditioned policy learning for long-horizon robot manipulation tasks. IEEE Robo. Autom. Lett. 7(3), 7327\u20137334 (2022)","journal-title":"IEEE Robo. Autom. Lett."},{"key":"9_CR29","unstructured":"Micikevicius, P., et al.: Mixed precision training. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"9_CR30","unstructured":"O\u2019Neill, A., et\u00a0al.: Open x-embodiment: robotic learning datasets and rt-x models: open x-embodiment collaboration 0. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 6892\u20136903. IEEE (2024)"},{"key":"9_CR31","unstructured":"Pei, X., Chen, Y., Xu, S., Wang, Y., Shi, Y., Xu, C.: Action-aware dynamic pruning for efficient vision-language-action manipulation. arXiv preprint arXiv:2509.22093 (2025)"},{"key":"9_CR32","unstructured":"Physical Intelligence, Black, K., et al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054 (2025)"},{"key":"9_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR34","unstructured":"Reed, S., et al.: A generalist agent. arXiv preprint arXiv:2205.06175 (2022)"},{"key":"9_CR35","doi-asserted-by":"publisher","first-page":"114553","DOI":"10.52202\/079017-3638","volume":"37","author":"C Wang","year":"2024","unstructured":"Wang, C., Wang, Z., Xu, X., Tang, Y., Zhou, J., Lu, J.: Q-vlm: post-training quantization for large vision-language models. Adv. Neural. Inf. Process. Syst. 37, 114553\u2013114573 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR36","unstructured":"Wang, H., Xu, J., Pan, J., Zhou, Y., Dai, G.: Specprune-VLA: accelerating visionlanguage-action models via action-aware self-speculative pruning. arXiv preprint arXiv:2509.05614 (2025)"},{"key":"9_CR37","doi-asserted-by":"crossref","unstructured":"Xu, S., Wang, Y., Xia, C., Zhu, D., Huang, T., Xu, C.: Vla-cache: efficient vision-language-action manipulation via adaptive token caching. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-5484"},{"key":"9_CR38","unstructured":"Xu, Y., et al.: Qvla: not all channels are equal in vision-language-action model\u2019s quantization. arXiv preprint arXiv:2602.03782 (2026)"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Efficientvla: Training-free acceleration and compression for vision-language-action models. arXiv preprint arXiv:2506.10100 (2025)","DOI":"10.52202\/085713-1365"},{"key":"9_CR40","doi-asserted-by":"publisher","first-page":"56619","DOI":"10.52202\/079017-1803","volume":"37","author":"Y Yue","year":"2024","unstructured":"Yue, Y., et al.: Deer-VLA: dynamic inference of multimodal large language models for efficient robot execution. Adv. Neural. Inf. Process. Syst. 37, 56619\u201356643 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR41","unstructured":"Zhang, C., et al.: Clap: contrastive latent action pretraining for learning vision-language-action models from human videos. arXiv preprint arXiv:2601.04061 (2026)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: Beyond attention or similarity: maximizing conditional diversity for token pruning in mllms. arXiv preprint arXiv:2506.10967 (2025)","DOI":"10.52202\/085713-0855"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, R., et al.: Mole-VLA: dynamic layer-skipping vision language action model via mixture-of-layers for efficient robot manipulation. arXiv preprint arXiv:2503.20384 (2025)","DOI":"10.1609\/aaai.v40i22.38945"},{"key":"9_CR44","unstructured":"Zhang, Y., et al.: Sparsevlm: visual token sparsification for efficient vision-language model inference. arXiv preprint arXiv:2410.04417 (2024)"},{"key":"9_CR45","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":"9_CR46","unstructured":"Zhu, Y., et al.: Varestorer: one-step var distillation for real-world image super-resolution. arXiv preprint arXiv:2604.21450 (2026)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37362-5_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:08:22Z","timestamp":1789034902000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37362-5_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373618","9783032373625"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37362-5_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}