{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:42Z","timestamp":1777865322072,"version":"3.51.4"},"reference-count":90,"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\/iccv51701.2025.01909","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20529-20540","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Multi-Modal Diffusion Mamba"],"prefix":"10.1109","author":[{"given":"Chunhao","family":"Lu","sequence":"first","affiliation":[{"name":"China University of Petroleum-Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Lu","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meichen","family":"Dong","sequence":"additional","affiliation":[{"name":"China University of Petroleum-Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jake","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Milwaukee"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","first-page":"72","article-title":"Sumformer: Universal approximation for efficient transformers","volume-title":"Topological, Algebraic and Geometric Learning Workshops 2023","author":"Alberti","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2384"},{"key":"ref5","author":"Bavishi","year":"2023","journal-title":"Introducing our multimodal models"},{"key":"ref6","first-page":"23972430","article-title":"Pythia: A suite for analyzing large language models across training and scaling","volume-title":"International Conference on Machine Learning","author":"Biderman"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref8","year":"2023","journal-title":"GPTV System Card. Openai"},{"key":"ref9","article-title":"Boolq: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Think you have solved question answering? try arc, the ai 2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.183"},{"key":"ref17","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2025.3599020"},{"key":"ref19","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref21","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref22","article-title":"Dimba: Transformermamba diffusion models","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Flurka: Fast fused low-rank & kernel attention","author":"Gupta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref29","article-title":"Hyperattention: Long-context attention in near-linear time","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02352"},{"key":"ref31","article-title":"Mars: Mixture of auto-regressive models for fine-grained text-to-image synthesis","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Measuring mathematical problem solving with the math dataset","author":"Hendrycks","year":"2021","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"47","key":"ref36","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref39","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref41","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref42","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Generating images with multimodal language models","volume":"36","author":"Koh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref46","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00265"},{"key":"ref48","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Robomamba: Multimodal state space model for efficient robot reasoning and manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Discrete diffusion modeling by estimating the ratios of the data distribution","volume-title":"Forty-first International Conference on Machine Learning","author":"Lou"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00725"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2613"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref58","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"vattention: Dynamic memory management for serving 11 ms without pagedattention","author":"Prabhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Vl-mamba: Exploring state space models for multimodal learning","author":"Qiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"A survey of mamba","author":"Qu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref66","article-title":"Fast transformer decoding: One write-head is all you need","author":"Shazeer","year":"2019","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2161"},{"key":"ref69","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Generative pretraining in multimodality","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Chameleon Team. Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","author":"Teng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Efficient large language models: A survey","author":"Wan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00176"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3624601"},{"key":"ref78","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3597461"},{"key":"ref83","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref85","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref86","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref88","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref89","article-title":"Monoformer: One transformer for both diffusion and autoregression","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref90","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","author":"Zhou","year":"2024","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\/11445784.pdf?arnumber=11445784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:52Z","timestamp":1777529752000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445784\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01909","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}