{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T08:34:23Z","timestamp":1778661263762,"version":"3.51.4"},"reference-count":72,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02230","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24056-24067","source":"Crossref","is-referenced-by-count":1,"title":["LIRA: Inferring Segmentation in Large Multi-Modal Models with Local Interleaved Region Assistance"],"prefix":"10.1109","author":[{"given":"Zhang","family":"Li","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Yang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Kingsoft Office"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyin","family":"Ma","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yin","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linger","family":"Deng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yabo","family":"Sun","sequence":"additional","affiliation":[{"name":"Kingsoft Office"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"issue":"2","key":"ref2","first-page":"3","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv:2308.12966"},{"key":"ref3","article-title":"Internlm2 technical report","author":"Cai","year":"2024"},{"key":"ref4","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","volume-title":"arXiv preprint arXiv:2306.15195","author":"Chen","year":"2023"},{"key":"ref5","article-title":"Sharegpt4v: Improving large multi-modal models with better captions","volume-title":"arXiv preprint arXiv:2311.12793","author":"Chen","year":"2023"},{"key":"ref6","article-title":"Pali-3 vision language models: Smaller, faster, stronger","volume-title":"arXiv preprint arXiv:2310.09199","author":"Chen","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4231-5","article-title":"How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites","volume-title":"arXiv preprint arXiv:2404.16821","author":"Chen","year":"2024"},{"key":"ref9","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","volume-title":"arXiv preprint arXiv:2306.13394","author":"Fu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01354"},{"key":"ref13","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","author":"Hu","year":"2022"},{"key":"ref14","article-title":"Minicpm: Unveiling the potential of small language models with scalable training strategies","volume-title":"arXiv preprint arXiv:2404.06395","author":"Hu","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref20","article-title":"Text4seg: Reimagining image segmentation as text generation","volume-title":"arXiv preprint arXiv:2410.09855","author":"Lan","year":"2024"},{"key":"ref21","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02640","article-title":"Omg-seg: Is one model good enough for all segmentation?","volume-title":"arXiv preprint arXiv:2401.10229","author":"Li","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref24","article-title":"Mini-gemini: Mining the potential of multi-modality vision language models","volume-title":"arXiv preprint arXiv:2403.18814","author":"Li","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref28","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","article-title":"Llava-plus: Learning to use tools for creating multimodal agents","volume-title":"arXiv preprint arXiv:2311.05437","author":"Liu","year":"2023"},{"key":"ref31","article-title":"Textmonkey: An ocr-free large multimodal model for understanding document","volume-title":"arXiv preprint arXiv:2403.04473","author":"Liu","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref33","article-title":"Interngpt: Solving vision-centric tasks by interacting with chatgpt beyond language","volume-title":"arXiv preprint arXiv:2305.05662","author":"Liu","year":"2023"},{"key":"ref34","article-title":"Chain-of-spot: Interactive reasoning improves large vision-language models","volume-title":"arXiv preprint arXiv:2403.12966","author":"Liu","year":"2024"},{"key":"ref35","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"The 36th Conference on Neural Information Processing Systems (NeurIPS)","author":"Lu","year":"2022"},{"key":"ref36","article-title":"Feast your eyes: Mixture-ofresolution adaptation for multimodal large language models","volume-title":"arXiv preprint arXiv:2403.03003","author":"Luo","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2022.findings-acl.177","article-title":"Chartqa: A benchmark for question answering about charts with visual and logical reasoning","volume-title":"arXiv preprint arXiv:2203.10244","author":"Masry","year":"2022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref40","article-title":"Kosmos-2: Grounding multimodal large language models to the world","volume-title":"arXiv preprint arXiv:2306.14824","author":"Peng","year":"2023"},{"key":"ref41","article-title":"Cogcom: Train large vision-language models diving into details through chain of manipulations","volume-title":"arXiv preprint arXiv:2402.04236","author":"Qi","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02302"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref47","article-title":"Tinylvlm-ehub: Towards comprehensive and efficient evaluation for large vision-language models","author":"Shao","year":"2024.7"},{"key":"ref48","article-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Tong","year":"2024"},{"key":"ref49","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","volume-title":"arXiv preprint arXiv:2409.12191","author":"Wang","year":"2024"},{"key":"ref50","article-title":"Cogvlm: Visual expert for pretrained language models","volume-title":"arXiv preprint arXiv:2311.03079","author":"Wang","year":"2023"},{"key":"ref51","article-title":"Visionllm: Large language model is also an openended decoder for vision-centric tasks","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref52","article-title":"Hierarchical open-vocabulary universal image segmentation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","article-title":"Segllm: Multi-round reasoning segmentation","volume-title":"arXiv preprint arXiv:2410.18923","author":"Wang","year":"2024"},{"key":"ref54","article-title":"Lasagna: Language-based segmentation assistant for complex queries","volume-title":"arXiv preprint arXiv:2404.08506","author":"Wei","year":"2024"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref56","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of visionlanguage tasks","volume-title":"arXiv preprint arXiv:2406.08394","author":"Wu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01243"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref59","article-title":"Llava-uhd: an 1 mm perceiving any aspect ratio and high-resolution images","volume-title":"arXiv preprint arXiv:2403.11703","author":"Xu","year":"2024"},{"key":"ref60","article-title":"An improved baseline for reasoning segmentation with large language model","volume-title":"arXiv preprint arXiv:2312.17240","author":"Yang","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref62","article-title":"mplug-owl3: Towards long image-sequence understanding in multi-modal large language models","volume-title":"arXiv preprint arXiv:2408.04840","author":"Ye","year":"2024"},{"key":"ref63","article-title":"mplug-owl: Modularization empowers large language models with multimodality","volume-title":"arXiv preprint arXiv:2304.14178","author":"Ye","year":"2023"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.253500"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref67","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","volume-title":"arXiv preprint arXiv:2407.03320","author":"Zhang","year":"2024"},{"key":"ref68","article-title":"Gpt4roi: Instruction tuning large language model on region-of-interest","volume-title":"arXiv preprint arXiv:2307.03601","author":"Zhang","year":"2023"},{"key":"ref69","article-title":"Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Zhang","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref71","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv:2304.10592"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3688863.3689575"}],"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\/11445833.pdf?arnumber=11445833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:17Z","timestamp":1777612337000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445833\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02230","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}