{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:10:27Z","timestamp":1761894627419,"version":"build-2065373602"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209796","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":["Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression"],"prefix":"10.1109","author":[{"given":"Te","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Michigan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuheng","family":"Li","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Central South University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lujun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Mistral 7b","year":"2023","author":"Jiang","key":"ref1"},{"article-title":"Llama 2: Open foundation and fine-tuned chat models","year":"2023","author":"Touvron","key":"ref2"},{"article-title":"Visual instruction tuning","year":"2023","author":"Liu","key":"ref3"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref4"},{"key":"ref5","article-title":"Detkds: Knowledge distillation search for object detectors","author":"Li","year":"2024","journal-title":"ICML"},{"key":"ref6","article-title":"Kd-zero: Evolving knowledge distiller for any teacher-student pairs","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01145"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01597"},{"key":"ref9","article-title":"Norm: Knowledge distillation via n-to-one representation matching","author":"Xiaolong","year":"2023","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_3"},{"key":"ref13","article-title":"Discovering sparsity allocation for layer-wise pruning of large language models","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref14","article-title":"Als: Adaptive layer sparsity for large language models via activation correlation assessment","author":"Li","year":"2024","journal-title":"NeuIPS"},{"key":"ref15","article-title":"Pruner-zero: Evolving symbolic pruning metric from scratch for large language models","author":"Dong","year":"2024","journal-title":"ICML"},{"year":"2023","key":"ref16","article-title":"Gpt-4 technical report"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","year":"2023","author":"Frantar","key":"ref19"},{"article-title":"A simple and effective pruning approach for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun","key":"ref20"},{"key":"ref21","article-title":"Llm-pruner: On the structural pruning of large language models","volume":"abs\/2305.11627","author":"Ma","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01566"},{"key":"ref23","article-title":"Stbllm: Breaking the 1-bit barrier with structured binary llms","author":"Dong","year":"2025","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"article-title":"Tree-structured parzen estimator: Understanding its algorithm components and their roles for better empirical performance","year":"2023","author":"Watanabe","key":"ref25"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref26"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref27"},{"article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","year":"2023","author":"Chen","key":"ref28"},{"year":"2023","key":"ref29","article-title":"Introducing idefics: An open reproduction of state-of-the-art visual language model"},{"article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","year":"2023","author":"Bai","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref33","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"article-title":"Pointer sentinel mixture models","year":"2016","author":"Merity","key":"ref36"}],"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\/11209796.pdf?arnumber=11209796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:11Z","timestamp":1761888731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209796\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209796","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}