{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T14:38:24Z","timestamp":1779201504014,"version":"3.51.4"},"reference-count":23,"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\/icme59968.2025.11209367","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":2,"title":["AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models"],"prefix":"10.1109","author":[{"given":"Zunhai","family":"Su","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Shen","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linge","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyu","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huangqi","family":"Yu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02166-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref3","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref4","article-title":"Zipvl: Efficient large vision-language models with dynamic token sparsification and kv cache compression","author":"He","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.235"},{"key":"ref6","article-title":"Kivi: A tuning-free asymmetric 2bit quantization for kv cache","author":"Liu","year":"2024"},{"key":"ref7","article-title":"Skvq: Sliding-window key and value cache quantization for large language models","author":"Duanmu","year":"2024"},{"key":"ref8","article-title":"Kvquant: Towards 10 million context length llm inference with kv cache quantization","author":"Hooper","year":"2024"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref10","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.460"},{"key":"ref12","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023"},{"key":"ref13","article-title":"Massive activations in large language models","author":"Sun","year":"2024"},{"key":"ref14","article-title":"Milebench: Benchmarking mllms in long context","author":"Song","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref16","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref17","article-title":"No token left behind: Reliable kv cache compression via importance-aware mixed precision quantization","author":"Yong","year":"2024"},{"key":"ref18","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Quarot: Outlier-free 4-bit inference in rotated llms","author":"Ashkboos","year":"2024"},{"key":"ref20","article-title":"Spinquant\u2013llm quantization with learned rotations","author":"Liu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1976.1674569"},{"key":"ref23","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Xiao"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"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\/11209367.pdf?arnumber=11209367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:58:21Z","timestamp":1761890301000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209367","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}