{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:08:55Z","timestamp":1789031335740,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374318","type":"print"},{"value":"9783032374325","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\/978-3-032-37432-5_32","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:30:54Z","timestamp":1789029054000},"page":"563-581","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transport Discrepancy as\u00a0a\u00a0Reliability Signal for\u00a0Vision-Language-Action Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5351-3449","authenticated-orcid":false,"given":"Wanpeng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2492-4219","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4612-5450","authenticated-orcid":false,"given":"Hao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqi","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yicheng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5171-198X","authenticated-orcid":false,"given":"Chaoyi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1679-6116","authenticated-orcid":false,"given":"Sipeng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6486-6020","authenticated-orcid":false,"given":"Qin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3967-2704","authenticated-orcid":false,"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"32_CR1","doi-asserted-by":"publisher","first-page":"23716","DOI":"10.52202\/068431-1723","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR2","unstructured":"Albergo, M.S., Boffi, N.M., Vanden-Eijnden, E.: Stochastic interpolants: A unifying framework for flows and diffusions. arXiv preprint arXiv:2303.08797 (2023)"},{"key":"32_CR3","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"32_CR4","unstructured":"Bjorck, J., et\u00a0al.: Gr00t n1: An open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"32_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":"32_CR6","doi-asserted-by":"crossref","unstructured":"Bonneel, N., Rabin, J., Peyr\u00e9, G., Pfister, H.: Sliced and radon wasserstein barycenters of measures. J. Math. Imaging Vision 51, 22\u201345 (2015)","DOI":"10.1007\/s10851-014-0506-3"},{"key":"32_CR7","unstructured":"Brohan, A., et al.: Rt-2: Vision-language-action models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818 (2023)"},{"key":"32_CR8","unstructured":"Brohan, A., et al.: Rt-1: Robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2023)"},{"key":"32_CR9","unstructured":"Cheang, C.L., et al.: Gr-2: A generative video-language-action model with web-scale knowledge for robot manipulation. arXiv preprint arXiv:2410.06158 (2024)"},{"key":"32_CR10","unstructured":"Cheang, C., et\u00a0al.: Gr-3 technical report. arXiv preprint arXiv:2507.15493 (2025)"},{"key":"32_CR11","unstructured":"Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Chi, C., et al.: Diffusion policy: Visuomotor policy learning via action diffusion. arXiv preprint arXiv:2303.04137 (2023)","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"32_CR13","unstructured":"Cuturi, M.: Sinkhorn distances: Lightspeed computation of optimal transport. Adv. Neural. Inf. Process. Syst. 26 (2013)"},{"key":"32_CR14","unstructured":"Driess, D., et al.: Palm-e: An embodied multimodal language model. In: International Conference on Machine Learning, pp. 8469\u20138488. PMLR (2023)"},{"key":"32_CR15","doi-asserted-by":"publisher","first-page":"31957","DOI":"10.52202\/068431-2316","volume":"35","author":"F Feng","year":"2022","unstructured":"Feng, F., Huang, B., Zhang, K., Magliacane, S.: Factored adaptation for non-stationary reinforcement learning. Adv. Neural. Inf. Process. Syst. 35, 31957\u201331971 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Videoorion: Tokenizing object dynamics in videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20401\u201320412 (2025)","DOI":"10.1109\/ICCV51701.2025.01897"},{"key":"32_CR17","unstructured":"Feng, Y., et al.: Spatial-aware vla pretraining through visual-physical alignment from human videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2026)"},{"issue":"11","key":"32_CR18","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665\u2013673 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"32_CR19","unstructured":"Grathwohl, W., Chen, R.T., Bettencourt, J., Sutskever, I., Duvenaud, D.: Ffjord: Free-form continuous dynamics for scalable reversible generative models. arXiv preprint arXiv:1810.01367 (2018)"},{"key":"32_CR20","unstructured":"Huang, H., et al.: Otter: A vision-language-action model with text-aware visual feature extraction. arXiv preprint arXiv:2503.03734 (2025)"},{"key":"32_CR21","unstructured":"Intelligence, P., et\u00a0al.: $$\\pi _{0.5}$$: a vision-language-action model with open-world generalization. arXiv preprint arXiv:2504.16054 (2025)"},{"key":"32_CR22","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":"32_CR23","unstructured":"Kim, M.J., et al.: Openvla: An open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"32_CR24","unstructured":"Kolouri, S., Nadjahi, K., Simsekli, U., Badeau, R., Rohde, G.: Generalized sliced wasserstein distances. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"32_CR25","unstructured":"Krueger, D., et al.: Out-of-distribution generalization via risk extrapolation (rex). In: International Conference on Machine Learning, pp. 5815\u20135826. PMLR (2021)"},{"key":"32_CR26","unstructured":"Lin, F., Nai, R., Hu, Y., You, J., Zhao, J., Gao, Y.: Onetwovla: A unified vision-language-action model with adaptive reasoning. arXiv preprint arXiv:2505.11917 (2025)"},{"key":"32_CR27","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2023)"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Liu, B., et al.: Libero: Benchmarking knowledge transfer for lifelong robot learning. arXiv preprint arXiv:2306.03310 (2023)","DOI":"10.52202\/075280-1939"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"32_CR30","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"32_CR31","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:2209.03003 (2022)"},{"key":"32_CR32","unstructured":"Lu, Y., Li, C., Liu, H., Yang, J., Gao, J., Shen, Y.: An empirical study of scaling instruct-tuned large multimodal models. arXiv preprint arXiv:2309.09958 (2023)"},{"key":"32_CR33","unstructured":"Luo, H., et al.: Being-H0: Vision-language-action pretraining from large-scale human videos. In: International Conference on Machine Learning. In: PMLR (2026)"},{"key":"32_CR34","unstructured":"Luo, H., Wang, Y., Zhang, W., Yuan, H., Feng, Y., Xu, H., Zheng, S., Lu, Z.: Joint-aligned latent action: Towards scalable vla pretraining in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2026)"},{"key":"32_CR35","unstructured":"Luo, H., et\u00a0al.: Being-H0.5: Scaling human-centric robot learning for cross-embodiment generalization. arXiv preprint arXiv:2601.12993 (2026)"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: OpenMMEgo: Enhancing egocentric understanding for LMMs with open weights and data. In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-0868"},{"key":"32_CR37","unstructured":"Luo, H., et al.: Being-H0.7: A latent world-action model from egocentric videos. arXiv preprint arXiv:2605.00078 (2026)"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Nasiriany, S., et al.: Robocasa: Large-scale simulation of everyday tasks for generalist robots. arXiv preprint arXiv:2406.02523 (2024)","DOI":"10.15607\/RSS.2024.XX.050"},{"issue":"57","key":"32_CR39","first-page":"1","volume":"22","author":"G Papamakarios","year":"2021","unstructured":"Papamakarios, G., Nalisnick, E., Rezende, D.J., Mohamed, S., Lakshminarayanan, B.: Normalizing flows for probabilistic modeling and inference. J. Mach. Learn. Res. 22(57), 1\u201364 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"5\u20136","key":"32_CR40","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","volume":"11","author":"G Peyr\u00e9","year":"2019","unstructured":"Peyr\u00e9, G., Cuturi, M.: Computational optimal transport. Found. Trends Mach. Learn. 11(5\u20136), 355\u2013607 (2019)","journal-title":"Found. Trends Mach. Learn."},{"key":"32_CR41","unstructured":"Pooladian, A.A., Ben-Hamu, H., Domingo-Enrich, C., Amos, B., Lipman, Y., Chen, R.T.: Multisample flow matching: Straightening flows with minibatch couplings. arXiv preprint arXiv:2304.14772 (2023)"},{"key":"32_CR42","doi-asserted-by":"crossref","unstructured":"Qu, D., et al.: Spatialvla: Exploring spatial representations for visual-language-action model. arXiv preprint arXiv:2501.15830 (2025)","DOI":"10.15607\/RSS.2025.XXI.011"},{"key":"32_CR43","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"32_CR44","unstructured":"Sun, J., et al.: Vla-jepa: Enhancing vision-language-action model with latent world model. arXiv preprint arXiv:2602.10098 (2026)"},{"key":"32_CR45","unstructured":"Team, O.M., et al.: Octo: An open-source generalist robot policy. arXiv preprint arXiv:2405.12213 (2024)"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., Abbeel, P.: Domain randomization for transferring deep neural networks from simulation to the real world. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 23\u201330. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202133"},{"key":"32_CR47","unstructured":"Tong, A., et al.: Improving and generalizing flow-based generative models with minibatch optimal transport. arXiv preprint arXiv:2302.00482 (2024)"},{"key":"32_CR48","unstructured":"Tong, A., Huang, J., Wolf, G., Van Dijk, D., Krishnaswamy, S.: Conditional flow matching: Simulation-free training of continuous normalizing flows. arXiv preprint arXiv:2302.00482 (2023)"},{"key":"32_CR49","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"32_CR50","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"32_CR51","series-title":"Springer Proceedings in Advanced Robotics","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1007\/978-3-030-43089-4_44","volume-title":"Algorithmic Foundations of Robotics XII","author":"E Tzeng","year":"2020","unstructured":"Tzeng, E., Devin, C., Hoffman, J., Finn, C., Abbeel, P., Levine, S., Saenko, K., Darrell, T.: Adapting Deep Visuomotor Representations with Weak Pairwise Constraints. In: Algorithmic Foundations of Robotics XII. SPAR, vol. 13, pp. 688\u2013703. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-43089-4_44"},{"key":"32_CR52","doi-asserted-by":"crossref","unstructured":"Villani, C.: Optimal transport: old and new, vol. 338, Springer (2009)","DOI":"10.1007\/978-3-540-71050-9"},{"key":"32_CR53","unstructured":"Wang, P., et\u00a0al.: Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"32_CR54","unstructured":"Wang, Y., et\u00a0al.: Rethinking visual-language-action model scaling: Alignment, mixture, and regularization. arXiv preprint arXiv:2602.09722 (2026)"},{"key":"32_CR55","unstructured":"Xing, Y., Luo, X., Xie, J., Gao, L., Shen, H., Song, J.: Shortcut learning in generalist robot policies: The role of dataset diversity and fragmentation. arXiv preprint arXiv:2508.06426 (2025)"},{"key":"32_CR56","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"32_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: Unified multimodal understanding via byte-pair visual encoding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12976\u201312986 (2025)","DOI":"10.1109\/ICCV51701.2025.01206"},{"key":"32_CR58","unstructured":"Zhang, W., Li, Y., Yang, B., Lu, Z.: Tackling non-stationarity in reinforcement learning via causal-origin representation. In: Proceedings of the 41st International Conference on Machine Learning, vol. 235, pp. 59264\u201359288. PMLR (2024)"},{"key":"32_CR59","unstructured":"Zhang, W., et al.: Conservative offline robot policy learning via posterior-transition reweighting. arXiv preprint arXiv:2603.16542 (2026)"},{"key":"32_CR60","unstructured":"Zhang, W., et alZ.: From pixels to tokens: Byte-pair encoding on quantized visual modalities. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"32_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, W., et\u00a0al.: Dreamvla: A vision-language-action model dreamed with comprehensive world knowledge. arXiv preprint (2025)","DOI":"10.52202\/085713-0818"},{"key":"32_CR62","unstructured":"Zhang, W., Zhang, B., Qi, Z., Zeng, W., Jin, X., Zhang, L.: Disentangled robot learning via separate forward and inverse dynamics pretraining. arXiv preprint arXiv:2604.16391 (2026)"},{"key":"32_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, Q., et al.: Cot-vla: Visual chain-of-thought reasoning for vision-language-action models. arXiv preprint arXiv:2503.22020 (2025)","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"32_CR64","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (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\/978-3-032-37432-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:31:22Z","timestamp":1789029082000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37432-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374318","9783032374325"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37432-5_32","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"}}]}}