{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:04Z","timestamp":1788894424260,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","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\/978-3-032-37044-0_13","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:34Z","timestamp":1788891574000},"page":"226-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["$$\\mathcal {M}^2$$Tok: Multi-head Multi-codebook Discrete Action Tokenization for\u00a0Vision-Language-Action Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4377-9934","authenticated-orcid":false,"given":"Chunpu","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6815-9866","authenticated-orcid":false,"given":"Zhixuan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3370-9258","authenticated-orcid":false,"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0218-3412","authenticated-orcid":false,"given":"Chi-Min","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8254-8138","authenticated-orcid":false,"given":"Jiashuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6191-1522","authenticated-orcid":false,"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3779-3378","authenticated-orcid":false,"given":"Mengkang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0321-021X","authenticated-orcid":false,"given":"Yao","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"13_CR1","unstructured":"Achiam, J., et al.: Gpt-4 technical report. arXiv:2303.08774 arXiv preprint (2023)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Belkhale, S., et al.: Rt-h: action hierarchies using language. ArXiv abs\/2403.01823 (2024)","DOI":"10.15607\/RSS.2024.XX.049"},{"key":"13_CR3","unstructured":"Brohan, A., et al.: Rt-1: robotics transformer for real-world control at scale. arXiv:2212.06817 arXiv preprint (2022)"},{"key":"13_CR4","doi-asserted-by":"crossref","unstructured":"Bu, Q., et al.: Univla: learning to act anywhere with task-centric latent actions. ArXiv abs\/2505.06111 (2025)","DOI":"10.15607\/RSS.2025.XXI.014"},{"key":"13_CR5","unstructured":"Cheang, C.L., et al.: Gr-2: a generative video-language-action model with web-scale knowledge for robot manipulation. ArXiv abs\/2410.06158 (2024)"},{"key":"13_CR6","unstructured":"Chen, T., et al.: Robotwin 2.0: a scalable data generator and benchmark with strong domain randomization for robust bimanual robotic manipulation. ArXiv abs\/2506.18088 (2025)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chi, C., et al.: Diffusion policy: visuomotor policy learning via action diffusion. Robot. Sci. Syst. (2023)","DOI":"10.15607\/RSS.2023.XIX.026"},{"issue":"2","key":"13_CR8","first-page":"23","volume":"12","author":"P Gage","year":"1994","unstructured":"Gage, P.: A new algorithm for data compression. C Users J. 12(2), 23\u201338 (1994)","journal-title":"C Users J."},{"key":"13_CR9","unstructured":"Grattafiori, A., et al.: The llama 3 herd of models. arXiv:2407.21783 arXiv preprint (2024)"},{"key":"13_CR10","unstructured":"Hu, Y., et al.: Video prediction policy: a generalist robot policy with predictive visual representations. ArXiv abs\/2412.14803 (2024)"},{"key":"13_CR11","unstructured":"Intelligence, P., et al.: $$\\pi $$0.5: a vision-language-action model with open-world generalization. ArXiv abs\/2504.16054 (2025)"},{"key":"13_CR12","unstructured":"Ji, S., et al.: Wavtokenizer: an efficient acoustic discrete codec tokenizer for audio language modeling. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Kim, M.J., Finn, C., Liang, P.: Fine-tuning vision-language-action models: optimizing speed and success (2025)","DOI":"10.15607\/RSS.2025.XXI.017"},{"key":"13_CR14","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. ArXiv abs\/2406.09246 (2024)"},{"key":"13_CR15","unstructured":"Lee, S., Wang, Y., Etukuru, H., Kim, H.J., Shafiullah, N.M.M., Pinto, L.: Behavior generation with latent actions. In: ICML (2024)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Gao, Y., Sadigh, D., Song, S.: Unified video action model. ArXiv abs\/2503.00200 (2025)","DOI":"10.15607\/RSS.2025.XXI.074"},{"key":"13_CR17","unstructured":"Liang, Z., et al.: Discrete diffusion VLA: bringing discrete diffusion to action decoding in vision-language-action policies. arXiv preprint arXiv:2508.20072 (2025)"},{"key":"13_CR18","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv:2412.19437 arXiv preprint (2024)"},{"key":"13_CR19","unstructured":"Liu, J., et al.: Hybridvla: collaborative diffusion and autoregression in a unified vision-language-action model. ArXiv abs\/2503.10631 (2025)"},{"key":"13_CR20","unstructured":"Liu, S., et al.: RDT-1b: a diffusion foundation model for bimanual manipulation. ArXiv abs\/2410.07864 (2024)"},{"key":"13_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"key":"13_CR22","unstructured":"Ma, C., et al.: Unitok: a unified tokenizer for visual generation and understanding. In: Belgrave, D., et al., (eds.) Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 \/ Mexico City, Mexico, November 30 - December 5, 2025 (2025). http:\/\/papers.nips.cc\/paper_files\/paper\/2025\/hash\/bbe04d329d531e8814f1199098bd8fb6-Abstract-Conference.html"},{"key":"13_CR23","unstructured":"Mohit, S., Lucas, M., Dieter, F.: Perceiver-actor: a multi-task transformer for robotic manipulation. ArXiv abs\/2209.05451 (2022)"},{"key":"13_CR24","unstructured":"Nvidia, Bjorck, J., et al.: Gr00t n1: an open foundation model for generalist humanoid robots. ArXiv abs\/2503.14734 (2025)"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Pertsch, K., et al.: Fast: efficient action tokenization for vision-language-action models. arXiv:2501.09747 arXiv preprint (2025)","DOI":"10.15607\/RSS.2025.XXI.012"},{"key":"13_CR26","unstructured":"Shridhar, M., Manuelli, L., Fox, D.: Cliport: what and where pathways for robotic manipulation. ArXiv abs\/2109.12098 (2021)"},{"key":"13_CR27","unstructured":"Sun, P., et al.: Autoregressive model beats diffusion: Llama for scalable image generation. arXiv:2406.06525 arXiv preprint (2024)"},{"key":"13_CR28","unstructured":"Team, O.M., et al.: Octo: an open-source generalist robot policy. ArXiv abs\/2405.12213 (2024)"},{"key":"13_CR29","doi-asserted-by":"publisher","first-page":"84839","DOI":"10.52202\/079017-2694","volume":"37","author":"K Tian","year":"2024","unstructured":"Tian, K., Jiang, Y., Yuan, Z., Peng, B., Wang, L.: Visual autoregressive modeling: scalable image generation via next-scale prediction. Adv. Neural. Inf. Process. Syst. 37, 84839\u201384865 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR30","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"13_CR31","unstructured":"Walke, H.R., et al.: Bridgedata v2: a dataset for robot learning at scale. In: Conference on Robot Learning, pp. 1723\u20131736. PMLR (2023)"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Wang, L., Chen, X., Zhao, J., He, K.: Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers. ArXiv abs\/2409.20537 (2024)","DOI":"10.52202\/079017-3952"},{"key":"13_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhu, H., Liu, M., Yang, J., Fang, H.S., He, T.: VQ-VLA: improving vision-language-action models via scaling vector-quantized action tokenizers. ArXiv abs\/2507.01016 (2025). https:\/\/api.semanticscholar.org\/CorpusID:280145409","DOI":"10.1109\/ICCV51701.2025.01032"},{"key":"13_CR34","unstructured":"Wu, H., et al.: Unleashing large-scale video generative pre-training for visual robot manipulation. ArXiv abs\/2312.13139 (2023)"},{"key":"13_CR35","unstructured":"Yang, Q.A., et al.: Qwen2.5 technical report. ArXiv abs\/2412.15115 (2024)"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11941\u201311952 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"13_CR37","unstructured":"Zhang, X., Zhang, D., Li, S., Zhou, Y., Qiu, X.: Speechtokenizer: unified speech tokenizer for speech language models. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"13_CR38","doi-asserted-by":"crossref","unstructured":"Zhao, T.Z., Kumar, V., Levine, S., Finn, C.: Learning fine-grained bimanual manipulation with low-cost hardware. arXiv:2304.13705 arXiv preprint (2023)","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"13_CR39","unstructured":"Zitkovich, B., et\u00a0al.: Rt-2: vision-language-action models transfer web knowledge to robotic control. In: Conference on Robot Learning, pp. 2165\u20132183. PMLR (2023)"}],"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\/978-3-032-37044-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:19:41Z","timestamp":1788891581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_13","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":"9 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"}}]}}