{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:05:08Z","timestamp":1776679508054,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":14,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570775","type":"print"},{"value":"9789819570782","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\/978-981-95-7078-2_44","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:21:35Z","timestamp":1776676895000},"page":"648-655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Morpheus: Accelerating Large Language Models with\u00a0Feature-Augmented Autoregressive Drafting"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1135-7251","authenticated-orcid":false,"given":"Haoran","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3635-2342","authenticated-orcid":false,"given":"Peng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6020-0525","authenticated-orcid":false,"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"44_CR1","unstructured":"Kim, S., et al.: Squeezellm: dense-and-sparse quantization. arXiv preprint arXiv:2306.07629 (2023)"},{"key":"44_CR2","unstructured":"Leviathan, Y., Kalman, M., Matias, Y.: Fast inference from transformers via speculative decoding. In: International Conference on Machine Learning, pp. 19274\u201319286. PMLR (2023)"},{"key":"44_CR3","unstructured":"Chen, C., Borgeaud, S., Irving, G., Lespiau, J.B., Sifre, L., Jumper, J.: Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)"},{"key":"44_CR4","first-page":"39236","volume":"36","author":"S Kim","year":"2023","unstructured":"Kim, S., et al.: Speculative decoding with big little decoder. Adv. Neural. Inf. Process. Syst. 36, 39236\u201339256 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"44_CR5","first-page":"86226","volume":"37","author":"Z Chen","year":"2024","unstructured":"Chen, Z., Yang, X., Lin, J., Sun, C., Chang, K., Huang, J.: Cascade speculative drafting for even faster LLM inference. Adv. Neural. Inf. Process. Syst. 37, 86226\u201386242 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"44_CR6","unstructured":"Du, C., et\u00a0al.: Glide with a cape: a low-hassle method to accelerate speculative decoding. In: Proceedings of the 41st International Conference on Machine Learning, pp. 11704\u201311720 (2024)"},{"key":"44_CR7","unstructured":"Hooper, C., et al.: Speed: speculative pipelined execution for efficient decoding. arXiv preprint arXiv:2310.12072 (2023)"},{"key":"44_CR8","unstructured":"Yang, S., Lee, G., Cho, J., Papailiopoulos, D., Lee, K.: Predictive pipelined decoding: a compute-latency trade-off for exact LLM decoding. arXiv preprint arXiv:2307.05908 (2023)"},{"key":"44_CR9","unstructured":"Stern, M., Shazeer, N., Uszkoreit, J.: Blockwise parallel decoding for deep autoregressive models. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"44_CR10","unstructured":"Cai, T., et al.: Medusa: Simple LLM inference acceleration framework with multiple decoding heads. In: International Conference on Machine Learning, pp. 5209\u20135235. PMLR (2024)"},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp.\u00a01715. Association for Computational Linguistics (2016)","DOI":"10.18653\/v1\/P16-1162"},{"key":"44_CR12","doi-asserted-by":"crossref","unstructured":"Chen, H., et\u00a0al.: Db-LLM: accurate dual-binarization for efficient LLMs. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 8719\u20138730 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.516"},{"key":"44_CR13","first-page":"74764","volume":"36","author":"Y Wang","year":"2023","unstructured":"Wang, Y., et al.: How far can camels go? exploring the state of instruction tuning on open resources. Adv. Neural. Inf. Process. Syst. 36, 74764\u201374786 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"44_CR14","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7078-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:21:48Z","timestamp":1776676908000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_44","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":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}