{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:40Z","timestamp":1761894700883,"version":"build-2065373602"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010905","name":"Major Research Plan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010905","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004763","name":"Natural Science Foundation of Inner Mongolia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210148","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["FedAdamZO: a Zeroth-order Adaptive Momentum Method for Memory-efficient Fine-tuning of Federated Large Language Models"],"prefix":"10.1109","author":[{"given":"Bo","family":"Ma","sequence":"first","affiliation":[{"name":"School of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongmei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Inner Mongolia University,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_4"},{"article-title":"Gemini: a family of highly capable multimodal models","year":"2023","author":"Team","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"ref4","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref5","article-title":"Will we run out of data? an analysis of the limits of scaling datasets in machine learning","volume":"1","author":"Villalobos","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671897"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671573"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"article-title":"Fwdllm: Efficient fedllm using forward gradient","year":"2024","author":"Xu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447454"},{"article-title":"Slora: Federated parameter efficient fine-tuning of language models","year":"2023","author":"Babakniya","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.632"},{"article-title":"Adalora: Adaptive budget allocation for parameter-efficient fine-tuning","year":"2023","author":"Zhang","key":"ref13"},{"article-title":"Second-order fine-tuning without pain for llms: A hessian informed zeroth-order optimizer","year":"2024","author":"Zhao","key":"ref14"},{"article-title":"Sparse mezo: Less parameters for better performance in zeroth-order llm fine-tuning","year":"2024","author":"Liu","key":"ref15"},{"article-title":"Deepzero: Scaling up zeroth-order optimization for deep model training","year":"2023","author":"Chen","key":"ref16"},{"article-title":"Just one byte (per gradient): A note on low-bandwidth decentralized language model finetuning using shared randomness","year":"2023","author":"Zelikman","key":"ref17"},{"article-title":"Fedzen: Towards superlinear zeroth-order federated learning via incremental hessian estimation","year":"2023","author":"Maritan","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3214122"},{"key":"ref20","first-page":"53038","article-title":"Fine-tuning language models with just forward passes","volume":"36","author":"Malladi","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671865"},{"key":"ref22","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial intelligence and statistics.","author":"McMahan","year":"2017"},{"article-title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","year":"2023","author":"Qin","key":"ref23"},{"key":"ref24","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Flashattention-3: Fast and accurate attention with asynchrony and low-precision","year":"2024","author":"Shah","key":"ref25"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210148.pdf?arnumber=11210148","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:45Z","timestamp":1761888825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210148\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210148","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}