{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T07:02:04Z","timestamp":1789542124997,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032384096","type":"print"},{"value":"9783032384102","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"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\/978-3-032-38410-2_11","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:02:20Z","timestamp":1789538540000},"page":"132-144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AdaDiff-VLA: Hybrid Reasoning via Mode Policy Learning for Vision-Language-Action Models"],"prefix":"10.1007","author":[{"given":"Haipeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Shu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"11_CR1","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"11_CR2","unstructured":"Chen, S., et al.: VADv2: end-to-end vectorized autonomous driving via probabilistic planning. arXiv preprint arXiv:2402.13243 (2024)"},{"key":"11_CR3","unstructured":"Chen, X., et\u00a0al.: Do not think that much for 2+ 3=? On the overthinking of o1-like LLMs. arXiv preprint arXiv:2412.21187 (2024)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Y., Zhang, Z.: DrivingGPT: unifying driving world modeling and planning with multi-modal autoregressive transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26890\u201326900 (2025)","DOI":"10.1109\/ICCV51701.2025.02496"},{"issue":"10\u201311","key":"11_CR5","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. Robot. Res. 44(10\u201311), 1684\u20131704 (2025)","journal-title":"Int. J. Robot. Res."},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Dauner, D., et al.: NAVSIM: data-driven non-reactive autonomous vehicle simulation and benchmarking. In: Advances in Neural Information Processing Systems, vol. 37, pp. 28706\u201328719 (2024)","DOI":"10.52202\/079017-0902"},{"key":"11_CR7","unstructured":"Feng, R., et al.: ARTEMIS: autoregressive end-to-end trajectory planning with mixture of experts for autonomous driving. arXiv preprint arXiv:2504.19580 (2025)"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: Orion: a holistic end-to-end autonomous driving framework by vision-language instructed action generation. arXiv preprint arXiv:2503.19755 (2025)","DOI":"10.1109\/ICCV51701.2025.02302"},{"key":"11_CR9","unstructured":"Goyal, S., Ji, Z., Rawat, A.S., Menon, A.K., Kumar, S., Nagarajan, V.: Think before you speak: training language models with pause tokens. arXiv preprint arXiv:2310.02226 (2023)"},{"key":"11_CR10","unstructured":"Guo, D., et al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"11_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Planning-oriented autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17853\u201317862 (2023)","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"11_CR13","unstructured":"Jiang, B., Chen, S., Zhang, Q., Liu, W., Wang, X.: AlphaDrive: unleashing the power of VLMs in autonomous driving via reinforcement learning and reasoning. arXiv preprint arXiv:2503.07608 (2025)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Liu, Y., He, J., Fan, L., Zhang, Z.: End-to-end driving with online trajectory evaluation via BEV world model. arXiv preprint arXiv:2504.01941 (2025)","DOI":"10.1109\/ICCV51701.2025.02519"},{"key":"11_CR15","unstructured":"Li, Y., et al.: ReCogDrive: a reinforced cognitive framework for end-to-end autonomous driving. arXiv preprint arXiv:2506.08052 (2025)"},{"key":"11_CR16","unstructured":"Li, Z., et al.: Hydra-MDP: end-to-end multimodal planning with multi-target hydra-distillation. arXiv preprint arXiv:2406.06978 (2024)"},{"key":"11_CR17","unstructured":"Liu, P., et al.: OmniReason: a temporal-guided vision-language-action framework for autonomous driving. arXiv preprint arXiv:2509.00789 (2025)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Luo, H., et al.: O1-pruner: length-harmonizing fine-tuning for o1-like reasoning pruning. arXiv preprint arXiv:2501.12570 (2025)","DOI":"10.18653\/v1\/2026.findings-acl.697"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Marwala, T.: Thinking fast and slow. In: The Balancing Problem in the Governance of Artificial Intelligence, pp. 35\u201349. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-97-9251-1_3","DOI":"10.1007\/978-981-97-9251-1_3"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Renz, K., Chen, L., Arani, E., Sinavski, O.: Simlingo: vision-only closed-loop autonomous driving with language-action alignment. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 11993\u201312003 (2025)","DOI":"10.1109\/CVPR52734.2025.01120"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"Sima, C., et al.: DriveLM: driving with graph visual question answering. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) European Conference on Computer Vision, pp. 256\u2013274. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72943-0_15","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"11_CR22","unstructured":"Tian, X., et al.: DriveVLM: the convergence of autonomous driving and large vision-language models. arXiv preprint arXiv:2402.12289 (2024)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)","DOI":"10.52202\/068431-1800"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Weng, X., Ivanovic, B., Wang, Y., Wang, Y., Pavone, M.: PARA-Drive: parallelized architecture for real-time autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15449\u201315458 (2024)","DOI":"10.1109\/CVPR52733.2024.01463"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: DriveGPT4: interpretable end-to-end autonomous driving via large language model. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/LRA.2024.3440097"},{"issue":"4","key":"11_CR26","doi-asserted-by":"publisher","first-page":"281","DOI":"10.3390\/drones9040281","volume":"9","author":"Z Yu","year":"2025","unstructured":"Yu, Z., Li, J., Wei, Y., Lyu, Y., Tan, X.: Combining camera\u2013LiDAR fusion and motion planning using bird\u2019s-eye view representation for end-to-end autonomous driving. Drones 9(4), 281 (2025)","journal-title":"Drones"},{"key":"11_CR27","unstructured":"Yuan, C., et al.: DRAMA: an efficient end-to-end motion planner for autonomous driving with mamba. arXiv preprint arXiv:2408.03601 (2024)"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, X., Han, X., Yang, F., Ma, Y., Knoll, A.C.: OpenDriveVLA: towards end-to-end autonomous driving with large vision language action model. arXiv preprint arXiv:2503.23463 (2025)","DOI":"10.1609\/aaai.v40i16.38386"},{"key":"11_CR29","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"}],"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\/978-3-032-38410-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T06:02:35Z","timestamp":1789538555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38410-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"ISBN":["9783032384096","9783032384102"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38410-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]},"assertion":[{"value":"17 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"}}]}}