{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:51:54Z","timestamp":1776315114828,"version":"3.50.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031919787","type":"print"},{"value":"9783031919794","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-91979-4_7","type":"book-chapter","created":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:07:30Z","timestamp":1748718450000},"page":"67-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["LLaMA-NAS: Efficient Neural Architecture Search for\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Anthony","family":"Sarah","sequence":"first","affiliation":[]},{"given":"Sharath","family":"Nittur Sridhar","sequence":"additional","affiliation":[]},{"given":"Maciej","family":"Szankin","sequence":"additional","affiliation":[]},{"given":"Sairam","family":"Sundaresan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"7_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"7_CR2","unstructured":"Ashkboos, S., Croci, M.L., do\u00a0Nascimento, M.G., Hoefler, T., Hensman, J.: Slicegpt: compress large language models by deleting rows and columns (2024)"},{"key":"7_CR3","unstructured":"Cai, H., Gan, C., Wang, T., Zhang, Z., Han, S.: Once-for-all: Train one network and specialize it for efficient deployment (2020)"},{"key":"7_CR4","unstructured":"Clark, P., et al.: Think you have solved question answering? try arc, the ai2 reasoning challenge (2018)"},{"key":"7_CR5","unstructured":"Cummings, D., Sarah, A., Sridhar, S.N., Szankin, M., Munoz, J.P., Sundaresan, S.: A hardware-aware framework for accelerating neural architecture search across modalities (2022)"},{"issue":"2","key":"7_CR6","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/4235.996017","volume":"6","author":"K Deb","year":"2002","unstructured":"Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Trans. Evol. Comput. 6(2), 182\u2013197 (2002). https:\/\/doi.org\/10.1109\/4235.996017","journal-title":"IEEE Trans. Evol. Comput."},{"key":"7_CR7","unstructured":"Dettmers, T.: bitsandbytes [computer software]. https:\/\/github.com\/TimDettmers\/bitsandbytes (2024)"},{"key":"7_CR8","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: Gptq: accurate post-training quantization for generative pre-trained transformers (2023)"},{"key":"7_CR9","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding (2021)"},{"key":"7_CR10","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)"},{"key":"7_CR11","unstructured":"Le\u00a0Scao, T., et\u00a0al.: Bloom: a 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2023)"},{"key":"7_CR12","unstructured":"Lin, B., et al.: Video-llava: learning united visual representation by alignment before projection (2023). https:\/\/arxiv.org\/abs\/2311.10122"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Awq: activation-aware weight quantization for llm compression and acceleration (2024)","DOI":"10.1145\/3714983.3714987"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: Truthfulqa: measuring how models mimic human falsehoods (2022)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"7_CR15","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023). https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"7_CR16","unstructured":"Ma, X., Fang, G., Wang, X.: Llm-pruner: on the structural pruning of large language models (2023)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatgpt: towards detailed video understanding via large vision and language models (2024). https:\/\/arxiv.org\/abs\/2306.05424","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Sakaguchi, K., Bras, R.L., Bhagavatula, C., Choi, Y.: Winogrande: an adversarial winograd schema challenge at scale (2019)","DOI":"10.1609\/aaai.v34i05.6399"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Sridhar, S.N., Kundu, S., Sundaresan, S., Szankin, M., Sarah, A.: Instatune: instantaneous neural architecture search during fine-tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1523\u20131527 (2023)","DOI":"10.1109\/ICCVW60793.2023.00166"},{"key":"7_CR20","unstructured":"Taori, R., et al.: Stanford alpaca: an instruction-following llama model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca (2023)"},{"key":"7_CR21","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models (2023)"},{"key":"7_CR22","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023)"},{"key":"7_CR23","doi-asserted-by":"publisher","unstructured":"Wang, H., et al.: Hat: hardware-aware transformers for efficient natural language processing. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.686, http:\/\/dx.doi.org\/10.18653\/v1\/2020.acl-main.686","DOI":"10.18653\/v1\/2020.acl-main.686"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91979-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T19:07:35Z","timestamp":1748718455000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91979-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031919787","9783031919794"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91979-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","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":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}