{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:23Z","timestamp":1777865483959,"version":"3.51.4"},"reference-count":52,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161600"],"award-info":[{"award-number":["2022ZD0161600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225112,62271312,62301310,623B2073"],"award-info":[{"award-number":["62225112,62271312,62301310,623B2073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00397","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4167-4177","source":"Crossref","is-referenced-by-count":1,"title":["Information Density Principle for MLLM Benchmarks"],"prefix":"10.1109","author":[{"given":"Chunyi","family":"Li","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaozhe","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziheng","family":"Jia","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Semdedup: Dataefficient learning at web-scale through semantic deduplication","volume-title":"ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models","author":"Abbas","year":"2023"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref4","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref5","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird","year":"2009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","article-title":"Chatbot arena: An open platform for evaluating 11 ms by human preference","volume-title":"Forty-first International Conference on Machine Learning","author":"Chiang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.664"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-demo.6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref16","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00636"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2025.3558652"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3515874"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref27","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref29","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":"ref30","volume-title":"Zerobench: An impossible visual benchmark for contemporary large multimodal models","author":"Roberts","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref33","first-page":"325","article-title":"Coding Theorems for a Discrete Source With a Fidelity CriterionInstitute of Radio Engineers","volume-title":"International Convention Record","volume":"7","author":"Shannon","year":"1959"},{"key":"ref34","article-title":"Parrot: Multilingual visual instruction tuning","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367879"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02866"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34835"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref39","volume-title":"Enigmaeval: A benchmark of long multimodal reasoning challenges","author":"Wang","year":"2025"},{"key":"ref40","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Divide, conquer and combine: A training-free framework for high-resolution image perception in multimodal large language models","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Q-bench: A benchmark for general-purpose foundation models on low-level vision","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu","year":"2024"},{"key":"ref43","volume-title":"grok-1.5v","year":"2024"},{"key":"ref44","article-title":"mplug-ow13: Towards long image-sequence understanding in multi-modal large language models","author":"Ye","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","volume-title":"Forty-first International Conference on Machine Learning","author":"Yu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref47","article-title":"Task me anything","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhang","year":"2024"},{"key":"ref48","volume-title":"Lmmseval: Reality check on the evaluation of large multimodal models","author":"Zhang","year":"2024"},{"key":"ref49","article-title":"Mme-realworld: Could your multimodal llm challenge high-resolution real-world scenarios that are difficult for humans?","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"A-bench: Are lmms masters at evaluating ai-generated images?","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.612"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.474"}],"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\/11446093.pdf?arnumber=11446093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:40:16Z","timestamp":1777531216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00397","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}