{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:32Z","timestamp":1777865492382,"version":"3.51.4"},"reference-count":68,"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\/iccv51701.2025.02044","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22004-22024","source":"Crossref","is-referenced-by-count":0,"title":["LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs"],"prefix":"10.1109","author":[{"given":"Haoran","family":"Lou","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunxiao","family":"Fan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexin","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinliang","family":"Wang","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01311"},{"key":"ref4","first-page":"3558","article-title":"Conceptual 12 m: Pushing web-scale image-text pretraining to recognize long-tail visual concepts","author":"Changpinyo","year":"2021","journal-title":"CVPR"},{"key":"ref5","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref7","article-title":"A single transformer for scalable vision-language modeling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref11","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref13","article-title":"Unveiling encoder-free vision-language models","author":"Diao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2025.125965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref19","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref22","article-title":"Mantis: Interleaved multi-image instruction tuning","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref24","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Otterhd: A high-resolution multimodality model","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref27","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref32","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref35","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref38","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","author":"Lu","year":"2022","journal-title":"NeurIPS"},{"key":"ref39","article-title":"Feast your eyes: Mixture-of-resolution adaptation for multimodal large language models","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv.2403.03003"},{"key":"ref40","article-title":"Unirgb-ir: A unified framework for rgb-infrared semantic tasks via adapter tuning","author":"Maoxun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref42","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref43","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"NeurIPS"},{"key":"ref44","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref45","author":"Rohan","year":"2023","journal-title":"Introducing our multimodal models"},{"key":"ref46","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Eagle: Exploring the design space for multimodal 11 ms with mixture of encoders","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3227503"},{"key":"ref51","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref56","article-title":"Llava-uhd: an 1 mm perceiving any aspect ratio and high-resolution images","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"xgen-mm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Dense connector for mllms","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20218"},{"key":"ref60","article-title":"Deco: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref62","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102246"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_1"},{"key":"ref65","article-title":"Mmicl: Empowering vision-language model with multi-modal in-context learning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Removal and selection: Improving rgbinfrared object detection via coarse-to-fine fusion","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","journal-title":"arXiv preprint"}],"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\/11445216.pdf?arnumber=11445216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:41:38Z","timestamp":1777531298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02044","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}