{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:17:44Z","timestamp":1776680264736,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":17,"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_48","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:32:15Z","timestamp":1776677535000},"page":"682-690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Runtime Information for\u00a0LLM Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4493-6984","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9952-005X","authenticated-orcid":false,"given":"Yuhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4646-7960","authenticated-orcid":false,"given":"Wenyuan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"48_CR1","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM. int8 (): 8-bit matrix multiplication for transformers at scale. corr abs\/2208.07339 (2022) (2022)"},{"key":"48_CR2","doi-asserted-by":"crossref","unstructured":"Duarte, A.V., Marques, J., Gra\u00e7a, M., Freire, M., Li, L., Oliveira, A.L.: LumberChunker: long-form narrative document segmentation (2024). https:\/\/arxiv.org\/abs\/2406.17526","DOI":"10.18653\/v1\/2024.findings-emnlp.377"},{"key":"48_CR3","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: GPTQ: accurate post-training quantization for generative pre-trained transformers. arXiv preprint: arXiv:2210.17323 (2022)"},{"key":"48_CR4","unstructured":"Huang, W., et al.: BiLLM: pushing the limit of post-training quantization for LLMs. arXiv preprint: arXiv:2402.04291 (2024)"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Lee, C., Jin, J., Kim, T., Kim, H., Park, E.: OWQ: outlier-aware weight quantization for efficient fine-tuning and inference of large language models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 13355\u201313364 (2024)","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"48_CR6","unstructured":"Li, H., et al.: A survey on large language model acceleration based on KV cache management. arXiv preprint: arXiv:2412.19442 (2024)"},{"key":"48_CR7","first-page":"87","volume":"6","author":"J Lin","year":"2024","unstructured":"Lin, J., et al.: AWQ: activation-aware weight quantization for on-device LLM compression and acceleration. Proc. Mach. Learn. Syst. 6, 87\u2013100 (2024)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"48_CR8","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint: arXiv:1609.07843 (2016)"},{"key":"48_CR9","unstructured":"Shao, W., et al.: OmniQuant: omnidirectionally calibrated quantization for large language models. arXiv preprint: arXiv:2308.13137 (2023)"},{"key":"48_CR10","unstructured":"Shi, W., et al.: REPLUG: retrieval-augmented black-box language models. arXiv preprint: arXiv:2301.12652 (2023)"},{"key":"48_CR11","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint: arXiv:2307.09288 (2023)"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Wu, W., et al.: LLM-enhanced multimodal fusion for cross-domain sequential recommendation. arXiv preprint: arXiv:2506.17966 (2025)","DOI":"10.1016\/j.eswa.2026.132228"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Wu, W., Qiu, X., Song, S., Chen, Z., Huang, X., Ma, F., Xiao, J.: Image augmentation agent for weakly supervised semantic segmentation. Neurocomputing, 131314 (2025)","DOI":"10.1016\/j.neucom.2025.131314"},{"key":"48_CR14","unstructured":"Xiao, G., Lin, J., Seznec, M., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. arXiv preprint: arXiv:2211.10438 (2022)"},{"key":"48_CR15","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning, pp. 38087\u201338099. PMLR (2023)"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Yao, Z., Yazdani Aminabadi, R., Zhang, M., Wu, X., Li, C., He, Y.: ZeroQuant: efficient and affordable post-training quantization for large-scale transformers. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27168\u201327183 (2022)","DOI":"10.52202\/068431-1970"},{"key":"48_CR17","unstructured":"Zhou, Z., et\u00a0al.: A survey on efficient inference for large language models. arXiv preprint: arXiv:2404.14294 (2024)"}],"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_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:32:29Z","timestamp":1776677549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_48","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"}}]}}