{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:12:44Z","timestamp":1763007164614,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":15,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819530540"},{"type":"electronic","value":"9789819530557"}],"license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"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\/978-981-95-3055-7_1","type":"book-chapter","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:07:34Z","timestamp":1763006854000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ACL: Adaptive Chunking of\u00a0Large Language Models for\u00a0Efficient Inference on\u00a0Automotive Edge Devices"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0941-3316","authenticated-orcid":false,"given":"Yufei","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-2432","authenticated-orcid":false,"given":"Tianxiang","family":"Xu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2593-3621","authenticated-orcid":false,"given":"Chengwei","family":"Ye","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3051-5642","authenticated-orcid":false,"given":"Huanzhen","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8392-4148","authenticated-orcid":false,"given":"Kangsheng","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"unstructured":"Agrawal, A., et al.: Taming $$\\{$$Throughput-Latency$$\\}$$ tradeoff in $$\\{$$LLM$$\\}$$ inference with $$\\{$$Sarathi-Serve$$\\}$$. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 117\u2013134 (2024)","key":"1_CR1"},{"doi-asserted-by":"crossref","unstructured":"Alizadeh, K., et al.: LLM in a flash: efficient large language model inference with limited memory. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 12562\u201312584 (2024)","key":"1_CR2","DOI":"10.18653\/v1\/2024.acl-long.678"},{"unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)","key":"1_CR3"},{"unstructured":"Hu, C., et\u00a0al.: Inference without interference: disaggregate LLM inference for mixed downstream workloads. arXiv preprint arXiv:2401.11181 (2024)","key":"1_CR4"},{"doi-asserted-by":"crossref","unstructured":"Kong, R., et al.: SwapMoE: Serving off-the-shelf MoE-based large language models with tunable memory budget. arXiv preprint arXiv:2308.15030 (2023)","key":"1_CR5","DOI":"10.18653\/v1\/2024.acl-long.363"},{"doi-asserted-by":"crossref","unstructured":"Lin, Y., Ye, C., Zhang, H., et\u00a0al.: CCL: collaborative curriculum learning for sparse-reward multi-agent reinforcement learning via co-evolutionary task evolution (2025). arXiv preprint arXiv:2505.07854","key":"1_CR6","DOI":"10.21203\/rs.3.rs-6605272\/v1"},{"doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, K.: Comprehensive review: advancing cognitive computing through theory of mind integration and deep learning in artificial intelligence. In: Proceedings of the 8th International Conference on Computer Science and Application Engineering, pp. 31\u201335 (2024)","key":"1_CR7","DOI":"10.1145\/3704814.3704822"},{"unstructured":"Liu, Z., et\u00a0al.: Deja vu: Contextual sparsity for efficient LLMs at inference time. In: International Conference on Machine Learning, pp. 22137\u201322176. PMLR (2023)","key":"1_CR8"},{"unstructured":"Qi, X., et\u00a0al.: Medconv: convolutions beat transformers on long-tailed bone density prediction (2025), arXiv preprint arXiv:2502.00631","key":"1_CR9"},{"doi-asserted-by":"crossref","unstructured":"Song, Y., Mi, Z., Xie, H., Chen, H.: Powerinfer: fast large language model serving with a consumer-grade GPU. In: Proceedings of the ACM SIGOPS 30th Symposium on Operating Systems Principles, pp. 590\u2013606 (2024)","key":"1_CR10","DOI":"10.1145\/3694715.3695964"},{"doi-asserted-by":"crossref","unstructured":"Sun, S., Liang, C.X., Ye, C., et\u00a0al.: Non-contact vital signs detection in dynamic environments. In: 2025 4th International Symposium on Computer Applications and Information Technology (ISCAIT), pp. 1618\u20131621. IEEE (2025)","key":"1_CR11","DOI":"10.1109\/ISCAIT64916.2025.11010532"},{"doi-asserted-by":"crossref","unstructured":"Ye, C., Zhang, H., Lin, Y., et\u00a0al.: Gamnet: a hybrid network with Gabor fusion and NMamba for efficient 3D Glioma segmentation (2025). arXiv preprint arXiv:2505.05520","key":"1_CR12","DOI":"10.21203\/rs.3.rs-6603414\/v1"},{"unstructured":"Yi, R., et al.: EdgeMoE: Fast on-device inference of MoE-based large language models. arXiv preprint arXiv:2308.14352 (2023)","key":"1_CR13"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Integer or floating point? new outlooks for low-bit quantization on large language models. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2024)","key":"1_CR14","DOI":"10.1109\/ICME57554.2024.10688089"},{"unstructured":"Zhong, Y., et al.: $$\\{$$DistServe$$\\}$$: disaggregating prefill and decoding for goodput-optimized large language model serving. In: 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), pp. 193\u2013210 (2024)","key":"1_CR15"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3055-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T04:07:38Z","timestamp":1763006858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3055-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"ISBN":["9789819530540","9789819530557"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3055-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"14 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KSEM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Knowledge Science, Engineering and Management","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macao","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ksem2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ksem2025.scimeeting.cn\/en\/web\/index\/27434","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}