{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:04:53Z","timestamp":1770933893319,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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","award":["62222209"],"award-info":[{"award-number":["62222209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","award":["BNR2023TD03006"],"award-info":[{"award-number":["BNR2023TD03006"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3567138","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:05:48Z","timestamp":1746536748000},"page":"1392-1405","source":"Crossref","is-referenced-by-count":2,"title":["DiViCo: Disentangled Visual Token Compression for Efficient Large Vision-Language Model"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0351-2939","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zirui","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0943-2286","authenticated-orcid":false,"given":"Hong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref3","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref4","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref5","article-title":"DeepSeek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv:2401.02954"},{"key":"ref6","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref8","article-title":"Mini-Gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024","journal-title":"arXiv:2403.18814"},{"key":"ref9","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref10","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref11","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262514620.001.0001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref15","article-title":"Token merging: Your ViT but faster","author":"Bolya","year":"2022","journal-title":"arXiv:2210.09461"},{"key":"ref16","article-title":"SparseVLM: Visual token sparsification for efficient vision-language model inference","author":"Zhang","year":"2024","journal-title":"arXiv:2410.04417"},{"key":"ref17","article-title":"LLaVA-PruMerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv:2403.15388"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref19","article-title":"DeCo: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024","journal-title":"arXiv:2405.20985"},{"key":"ref20","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref21","article-title":"VoCo-LLaMA: Towards vision compression with large language models","author":"Ye","year":"2024","journal-title":"arXiv:2406.12275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref23","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref25","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref27","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref29","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Kingma"},{"key":"ref30","first-page":"14837","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref31","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"Yan","year":"2021","journal-title":"arXiv:2104.10157"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053558"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3153112"},{"key":"ref35","first-page":"5711","article-title":"Learning disentangled representations for recommendation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref36","first-page":"36174","article-title":"Curriculum co-disentangled representation learning across multiple environments for social recommendation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-018-0826-4"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322904"},{"key":"ref42","first-page":"1","article-title":"Beta-VAE: Learning basic visual concepts with a constrained variational framework","volume-title":"Proc. ICLR","author":"Higgins"},{"key":"ref43","article-title":"Diagnosing and enhancing VAE models","author":"Dai","year":"2019","journal-title":"arXiv:1903.05789"},{"key":"ref44","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv:2202.07800"},{"key":"ref45","article-title":"SPViT: Enabling faster vision transformers via soft token pruning","author":"Kong","year":"2021","journal-title":"arXiv:2112.13890"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.721"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref49","volume-title":"Elements of Information Theory","author":"Thomas","year":"2006"},{"key":"ref50","article-title":"Notes on Kullback\u2013Leibler divergence and likelihood","author":"Shlens","year":"2014","journal-title":"arXiv:1404.2000"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref55","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref61","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"issue":"11","key":"ref62","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9338-y"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/10988618.pdf?arnumber=10988618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:36Z","timestamp":1770930156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10988618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":63,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3567138","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}