{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:44:32Z","timestamp":1778694272487,"version":"3.51.4"},"reference-count":55,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02122","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22857-22867","source":"Crossref","is-referenced-by-count":6,"title":["LLaVA-Prumerge: Adaptive Token Reduction for Efficient Large Multimodal Models"],"prefix":"10.1109","author":[{"given":"Yuzhang","family":"Shang","sequence":"first","affiliation":[{"name":"UCF"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mu","family":"Cai","sequence":"additional","affiliation":[{"name":"UW-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingxin","family":"Xu","sequence":"additional","affiliation":[{"name":"Illinois Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"UW-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"UIC PruMerge"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations","author":"Bolya","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3381028"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref7","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Mobilevlm v2: Faster and stronger baseline for vision language model","author":"Chu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref12","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"ref14","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3152247"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"ref18","article-title":"3d-llm: Injecting the 3d world into large language models","author":"Hong","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Edward","year":"2022"},{"key":"ref20","article-title":"Phi-2: The surprising power of small language models","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref21","article-title":"Mistral 7b","author":"Albert","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Re-former: The efficient transformer","volume-title":"International Conference on Learning Representations","author":"Kitaev","year":"2020"},{"key":"ref23","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on Machine Learning","author":"Li","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref25","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref27","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref29","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/136"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"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","year":"2023","journal-title":"OpenAI. Gpt-4 technical report"},{"key":"ref35","volume-title":"OpenAI. Gpt-4v(ision) system card","year":"2023"},{"key":"ref36","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","article-title":"Pb-llm: Partially binarized large language models","author":"Shang","year":"2024","journal-title":"ICLR"},{"key":"ref39","article-title":"Crossget: Cross-guided ensemble of tokens for accelerating vision-language transformers","author":"Shi","year":"2024","journal-title":"ICML"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref42","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","volume-title":"Vicuna. Vicuna: An open-source chatbot impressing gpt-4 with 90 chatgpt quality","year":"2023"},{"key":"ref46","author":"Wang","year":"2020","journal-title":"Linformer: Self-attention with linear complexity"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref48","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Tinygpt-v: Efficient multimodal large language model via small backbones","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Asvd: Activation-aware singular value decomposition for compressing large language models","author":"Yuan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Llm inference unveiled: Survey and roofline model insights","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref53","article-title":"Video-llama: An instruction-tuned audio-visual language model for video un-derstanding","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref55","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445607.pdf?arnumber=11445607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:10Z","timestamp":1777531150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02122","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}