{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:06Z","timestamp":1777865286100,"version":"3.51.4"},"reference-count":64,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471064"],"award-info":[{"award-number":["62471064"]}],"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\/iccv51701.2025.00088","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"859-869","source":"Crossref","is-referenced-by-count":0,"title":["From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning"],"prefix":"10.1109","author":[{"given":"Hang","family":"Du","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoshun","family":"Nan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wendi","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenyan","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shan","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuqi","family":"Pan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qi","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sicong","family":"Leng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Moses Alabi","volume-title":"Visual learning: The power of visual aids and multimedia","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2023.120483"},{"key":"ref3","article-title":"MathQA: Towards interpretable math word problem solving with operation-based formalisms","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Amini","year":"2019"},{"key":"ref4","first-page":"279","article-title":"Neuro-symbolic visual reasoning: Disentangling \u201cVisual\u201d from \u201cReasoning\u201d","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Amizadeh","year":"2020"},{"key":"ref5","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","volume-title":"AAAI Press","author":"Besta","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3560042"},{"key":"ref9","article-title":"Survey on Large Language Model-Enhanced Re-inforcement Learning: Concept, Taxonomy, and Methods","author":"Cao","year":"2024","journal-title":"arXiv e-prints, art. arXiv:2404.00282"},{"key":"ref10","article-title":"Interleaved scene graph for interleaved text-and-image generation assessment","volume":"abs\/2411.17188","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref11","article-title":"Comm: A coherent interleaved image-text dataset for multimodal understanding and generation","volume":"abs\/2406.10462","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1272"},{"key":"ref14","first-page":"220","article-title":"Towards neurosymbolic video understanding","author":"Choi","year":"2025","journal-title":"Computer Vision - ECCV 2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29748"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01778"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_9"},{"key":"ref19","author":"Gadre","journal-title":"Datacomp: In search of the next generation of multimodal datasets"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"ref21","author":"Huang","journal-title":"Language is not all you need: Aligning perception with language models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102270"},{"key":"ref23","author":"Jiang","year":"2024","journal-title":"Mantis: Interleaved multi-image instruction tuning"},{"key":"ref24","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref25","author":"Jiang","year":"2024","journal-title":"Many-shot in-context learning in multimodal foundation models"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00868"},{"key":"ref27","author":"Lauren\u00e7on","year":"2023","journal-title":"Obelisc: An open webscale filtered dataset of interleaved image-text documents"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref29","article-title":"Naturalbench: Evaluating vision-language models on natural adversarial samples","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","author":"Li","year":"2024","journal-title":"Lmms-eval: Accelerating the development of large multimoal models"},{"key":"ref31","article-title":"LLaVA- OneVision: Easy Visual Task Transfer","author":"Li","year":"2024","journal-title":"arXiv e-prints, art. arXiv:2408.03326"},{"key":"ref32","article-title":"Llava-next-interleave: Tackling multi-image, video, and 3d in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"LLaVA- NeXTInterleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","author":"Li","year":"2024","journal-title":"arXiv e-prints, art. arXiv:2407.07895"},{"key":"ref34","article-title":"Fine-tuning multimodal LLMs to follow zero-shot demonstrative instructions","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref36","author":"Meng","year":"2024","journal-title":"Mmiu: Multimodal multiimage understanding for evaluating large vision-language models"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.141"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00279"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.937"},{"key":"ref40","first-page":"22","article-title":"The integration of text and image in media and its impact on reader interest","volume":"48","author":"Peterson","year":"2014","journal-title":"Visible Language"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.46827\/ejals.v7i2.550"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.esp.2025.01.002"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116159"},{"key":"ref44","author":"Shukor","year":"2024","journal-title":"Beyond task performance: Evaluating and reducing the flaws of large multimodal models with incontext learning"},{"key":"ref45","article-title":"Milebench: Benchmarking mllms in long context","author":"Song","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00028-Y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1247"},{"key":"ref49","article-title":"Mm-interleaved: Interleaved image-text generative modeling via multi-modal feature synchronizer","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Muirbench: A comprehensive benchmark for robust multi-image understanding","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proceedings of the 36 th International Conference on Neural Information Processing Systems, Red Hook, NY, USA","author":"Wei","year":"2022"},{"key":"ref53","article-title":"Mmra: A benchmark for evaluating multi-granularity and multi-image relational association capabilities in large visual language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models","author":"Xia","year":"2024","journal-title":"arXiv eprints, art. arXiv:2410.10139"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1984.6313337"},{"key":"ref56","article-title":"Mirbench: Benchmarking llm\u2019s long-context intelligence via many-shot in-context inductive reasoning","author":"Yan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3607"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref59","author":"Ye","year":"2024","journal-title":"mplugowl3: Towards long image-sequence understanding in multimodal large language models"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2020.101397"},{"key":"ref62","article-title":"Improve Vision Language Model Chain-ofthought Reasoning","author":"Zhang","year":"2024","journal-title":"arXiv e-prints, art. arXiv:2410.16198"},{"key":"ref63","article-title":"Multimodal chain-ofthought reasoning in language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","author":"Zhu","year":"2023","journal-title":"Multimodal c4: An open"}],"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\/11443487.pdf?arnumber=11443487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:10:32Z","timestamp":1777529432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443487\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00088","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}