{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:52:44Z","timestamp":1781848364958,"version":"3.54.5"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"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":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11561990","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"284-288","source":"Crossref","is-referenced-by-count":0,"title":["Revisiting MLLM Token Technology through the Lens of Classical Visual Coding"],"prefix":"10.1109","author":[{"given":"Jinming","family":"Liu","sequence":"first","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyan","family":"Lin","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuntao","family":"Wei","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kele","family":"Shao","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keda","family":"Tao","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Huang","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Yang","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibo","family":"Chen","sequence":"additional","affiliation":[{"name":"USTC"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"Eastern Institute of Technology,Ningbo,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref3","article-title":"Variational image compression with a scale hyperprior","author":"Ball\u00e9","year":"2018","journal-title":"preprint arXiv:1802.01436"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref6","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"preprint arXiv:2502.13923"},{"key":"ref7","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2025"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02122"},{"key":"ref10","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01939"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref14","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024"},{"key":"ref15","article-title":"Specification information technology-computer graphics and image processing-portable network graphics (png): Functional specification","volume":"15948","author":"Graphics","year":"2003","journal-title":"ISO\/IEC"},{"key":"ref16","article-title":"High efficiency video coding (hevc) text specification draft 10 (for fdis & last call)","volume-title":"Joint Collaborative Team on Video Coding (JCT-VC) of ITU-T SG 16 WP 3 and ISO\/IEC JTC 1\/SC 29\/WG 11, 12th Meeting","author":"Bross"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00563"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02129"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3515874"},{"key":"ref20","first-page":"11 913","article-title":"High-fidelity generative image compression","volume":"33","author":"Mentzer","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Call for evidence for video coding for machines","volume":"2","author":"Zhang","year":"2022","journal-title":"ISO\/IEC JTC 1\/SC 29\/WG"},{"key":"ref22","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume":"31","author":"Minnen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01170"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849862"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PCS56426.2022.10018036"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3386639"},{"key":"ref28","first-page":"329","article-title":"Rate-distortion-cognition controllable versatile neural image compression","volume-title":"European Conference on Computer Vision","author":"Liu"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103816"},{"key":"ref30","article-title":"White paper on jpeg ai scope and framework","volume":"1","author":"Ascenso","year":"2021","journal-title":"ISO\/IEC JTC"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref33","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref34","article-title":"When tokens talk too much: A survey of multimodal long-context token compression across images, videos, and audios","author":"Shao","year":"2025","journal-title":"preprint arXiv:2507.20198"},{"key":"ref35","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"preprint arXiv:2409.12191"},{"key":"ref36","article-title":"Mobilevlm: A fast, strong and open vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"preprint arXiv:2312.16886"},{"key":"ref37","article-title":"Auroracap: Efficient, performant video detailed captioning and a new benchmark","author":"Chai","year":"2025"},{"key":"ref38","article-title":"Pyramiddrop: Accelerating your large vision-language models via pyramid visual redundancy reduction","author":"Xing","year":"2025"},{"key":"ref39","article-title":"Holitom: Holistic token merging for fast video large language models","author":"Shao","year":"2025","journal-title":"preprint arXiv:2505.21334"},{"key":"ref40","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01169"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0882"},{"key":"ref44","article-title":"Tokencarve: Information-preserving visual token compression in multimodal large language models","author":"Tan","year":"2025","journal-title":"preprint arXiv:2503.10501"},{"key":"ref45","article-title":"Single-pass adaptive image tokenization for minimum program search","author":"Duggal","year":"2025","journal-title":"preprint arXiv:2507.07995"},{"key":"ref46","article-title":"X-omni: Reinforcement learning makes discrete autoregressive image generative models great again","author":"Geng","year":"2025"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP63160.2024.10849922"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00107"},{"key":"ref49","first-page":"1","article-title":"Lossless data compression by large models","author":"Li","year":"2025","journal-title":"Nature Machine Intelligence"},{"key":"ref50","article-title":"Bridging compressed image latents and multimodal large language models","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kao"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2500084"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11561990.pdf?arnumber=11561990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:26:14Z","timestamp":1781846774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11561990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11561990","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}