{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:40:20Z","timestamp":1789666820176,"version":"4.0.1"},"reference-count":67,"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":["62276108"],"award-info":[{"award-number":["62276108"]}],"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\/iccv51701.2025.01941","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20878-20888","source":"Crossref","is-referenced-by-count":3,"title":["MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling"],"prefix":"10.1109","author":[{"given":"Yingyue","family":"Li","sequence":"first","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bencheng","family":"Liao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of EIC, Huazhong University of Science & Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","author":"Agarwal","year":"2024","journal-title":"On-policy distillation of language models: Learning from self-generated mistakes"},{"key":"ref3","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"2","key":"ref4","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"},{"key":"ref5","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0999"},{"key":"ref7","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref10","article-title":"Pali: A jointlyscaled multilingual language-image model","author":"Chen","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"issue":"3","key":"ref14","first-page":"6","volume":"2","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality"},{"key":"ref15","article-title":"Mobilevlm: A fast, reproducible and strong vision language assistant for mobile devices","author":"Chu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref17","article-title":"Flashattention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Transformers are ssms: Generalized models and efficient algorithms through structured state space duality","author":"Dao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref20","article-title":"Griffin: Mixing gated linear recurrences with local attention for efficient language models","author":"De","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00146"},{"key":"ref22","article-title":"Mme: a comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"corr abs\/2306.13394"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00067-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref25","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref27","author":"Gu","year":"2023","journal-title":"Knowledge distillation of large language models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1670"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02352"},{"key":"ref30","first-page":"arXiv-2408","article-title":"Mini-monkey: Alleviate the sawtooth effect by multi-scale adaptive cropping","author":"Huang","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref31","article-title":"Mlmamba: Efficient multi-modal large language model utilizing mamba-2","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"issue":"3","key":"ref33","first-page":"3","article-title":"Phi-2: The surprising power of small language models","volume":"1","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref34","article-title":"Large language model distillation doesn\u2019t need a teacher","author":"Harsh Jha","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Obelics: An open web-scale filtered dataset of interleaved image-text documents","volume":"36","author":"Lauren\u00e7on","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref39","article-title":"Moe-llava: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref43","article-title":"Mega: moving average equipped gated attention","author":"Ma","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref46","article-title":"Simplified state space layers for sequence modeling","author":"Smith","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"An empirical study of mamba-based language models","author":"Waleffe","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"The mamba in the llama: Distilling and accelerating hybrid models","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"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 arXiv"},{"issue":"57765788","key":"ref52","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref53","author":"Wang","year":"2022","journal-title":"Multimodal adaptive distillation for leveraging unimodal encoders for visionlanguage tasks"},{"key":"ref54","article-title":"Rnns are not transformers (yet): The key bottleneck on in-context retrieval","author":"Wen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.605"},{"key":"ref56","article-title":"Llavadi: What matters for multimodal large language models distillation","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Do efficient transformers really save computation?","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Gated linear attention transformers with hardware-efficient training","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref59","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref61","article-title":"Mmmu: A massive multidiscipline multimodal understanding and reasoning benchmark for expert agi","author":"Yue","year":"2023","journal-title":"arxiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref63","article-title":"Mmbench: Is your multi-modal model an all-around player","author":"Zhang Bo Li-Songyang Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref64","article-title":"Cobra: Extending mamba to multi-modal large language model for efficient inference","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","article-title":"Tinyllava: A framework of small-scale large multimodal models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref67","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\/11444910.pdf?arnumber=11444910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:30Z","timestamp":1777529850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01941","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}