{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:13:53Z","timestamp":1761894833873,"version":"build-2065373602"},"reference-count":26,"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209915","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":["SQ-Delta: Ultra-High Delta Compression for LLMs via Joint Sparsification-Quantization"],"prefix":"10.1109","author":[{"given":"Yanfeng","family":"Jiang","sequence":"first","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zelan","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Inc,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohua","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Inc,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shen","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Inc,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Inc,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref3","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Lora: Low-rank adaptation of large language models","year":"2021","author":"Hu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.168"},{"article-title":"S-lora: Serving thousands of concurrent lora adapters","year":"2023","author":"Sheng","key":"ref6"},{"article-title":"Punica: Multi-tenant lora serving","year":"2023","author":"Chen","key":"ref7"},{"article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","year":"2023","author":"Yu","key":"ref8"},{"article-title":"Bitdelta: Your fine-tune may only be worth one bit","year":"2024","author":"Liu","key":"ref9"},{"article-title":"Deltazip: Multi-tenant language model serving via delta compression","year":"2023","author":"Yao","key":"ref10"},{"article-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","year":"2023","author":"Luo","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1009"},{"article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","year":"2024","author":"Han","key":"ref13"},{"article-title":"Qlora: Efficient finetuning of quantized llms","year":"2023","author":"Dettmers","key":"ref14"},{"issue":"1","key":"ref15","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The journal of machine learning research"},{"article-title":"Delta-come: Training-free delta-compression with mixed-precision for large language models","year":"2024","author":"Ping","key":"ref16"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref17"},{"article-title":"Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity","year":"2023","author":"Yin","key":"ref18"},{"key":"ref19","article-title":"Cusparse library","volume-title":"GPU Technology conference","volume":"12","author":"Naumov"},{"key":"ref20","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"article-title":"Wizardlm: Empowering large language models to follow complex instructions","year":"2023","author":"Xu","key":"ref21"},{"article-title":"Code llama: Open foundation models for code","year":"2023","author":"Roziere","key":"ref22"},{"article-title":"Training verifiers to solve math word problems","year":"2021","author":"Cobbe","key":"ref23"},{"article-title":"Evaluating large language models trained on code","year":"2021","author":"Chen","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"}],"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\/11209915.pdf?arnumber=11209915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:37:02Z","timestamp":1761889022000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209915","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}