{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:47:49Z","timestamp":1791913669732,"version":"4.3.4"},"reference-count":96,"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\/iccv51701.2025.01544","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-12","source":"Crossref","is-referenced-by-count":14,"title":["FlowTok: Flowing Seamlessly Across Text and Image Tokens"],"prefix":"10.1109","author":[{"given":"Ju","family":"He","sequence":"first","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihang","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihao","family":"Liu","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Seed"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"LAION2B-en-aesthetic"},{"key":"ref2","volume-title":"LAION-art"},{"key":"ref3","volume-title":"LAION-pop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","author":"Albergo","year":"2022","journal-title":"Building normalizing flows with stochastic interpolants"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref7","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","author":"Bai","year":"2025","journal-title":"ICLR"},{"key":"ref8","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee","year":"2005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"issue":"3","key":"ref10","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref11","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023","journal-title":"ICML"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref14","article-title":"PixArt- $\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02190"},{"key":"ref17","author":"Chen","year":"2015","journal-title":"Microsoft coco captions: Data collection and evaluation server"},{"key":"ref18","article-title":"Unifying vision-and-language tasks via text generation","author":"Cho","year":"2021","journal-title":"ICML"},{"key":"ref19","author":"Dai","year":"2023","journal-title":"Emu: Enhancing image generation models using photogenic needles in a haystack"},{"key":"ref20","author":"Deng","year":"2025","journal-title":"Coconut-pancap: Joint panoptic segmentation and grounded captions for fine-grained understanding and generation"},{"key":"ref21","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref22","author":"Driess","year":"2023","journal-title":"Palm-e: An embodied multimodal language model"},{"key":"ref23","author":"Egan","year":"2024","journal-title":"XWAVE, and SilentAntagonist. Dalle3 1 Million+ High Quality Captions"},{"key":"ref24","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref25","author":"Fan","year":"2024","journal-title":"Fluid: Scaling autoregressive text-to-image generative models with continuous tokens"},{"key":"ref26","author":"Fischer","year":"2023","journal-title":"Boosting latent diffusion with flow matching"},{"key":"ref27","article-title":"Datacomp: In search of the next generation of multimodal datasets","author":"Yitzhak Gadre","year":"2023","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref29","author":"Gao","year":"2019","journal-title":"Masked non-autoregressive image captioning"},{"key":"ref30","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","author":"Grill","year":"2020","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/107"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref34","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref35","article-title":"Perceiver: General perception with iterative attention","author":"Jaegle","year":"2021","journal-title":"ICML"},{"key":"ref36","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01714"},{"key":"ref39","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref40","year":"2024","journal-title":"Black Forest Labs. Flux"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref42","article-title":"Minimizing trajectory curvature of ode-based generative models","author":"Lee","year":"2023","journal-title":"ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-23161-2_300919"},{"key":"ref44","article-title":"Blip: Bootstrapping language-image pre-training for unified visionlanguage understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref45","author":"Harold Li","year":"2019","journal-title":"Visualbert: A simple and performant baseline for vision and language"},{"key":"ref46","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref48","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR"},{"key":"ref49","author":"Liu","year":"2023","journal-title":"I2 sb: Image-to-image schr\u00f6dinger bridge"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00263"},{"key":"ref51","article-title":"Alleviating distortion in image generation via multi-resolution diffusion models","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref52","author":"Liu","year":"2025","journal-title":"Revision: High-quality, low-cost video generation with explicit 3d physics modeling for complex motion and interaction"},{"key":"ref53","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref54","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019","journal-title":"NeurIPS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref57","author":"Nichol","year":"2021","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref58","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref59","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref61","author":"Podell","year":"2023","journal-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis"},{"key":"ref62","author":"Polyak","year":"2024","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref63","author":"Pooladian","year":"2023","journal-title":"Multisample flow matching: Straightening flows with minibatch couplings"},{"key":"ref64","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"issue":"2","key":"ref65","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref66","author":"Ren","year":"2024","journal-title":"Flowar: Scale-wise autoregressive image generation meets flow matching"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"ref68","author":"Ren","year":"2025","journal-title":"Grouping first, attending smartly: Trainingfree acceleration for diffusion transformers"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref70","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref71","author":"Shazeer","year":"2020","journal-title":"Glu variants improve transformer"},{"key":"ref72","article-title":"Diffusion schr\u00f6dinger bridge matching","author":"Shi","year":"2023","journal-title":"NeurIPS"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01535"},{"key":"ref74","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref75","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref76","year":"2023","journal-title":"stabilityai"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref78","article-title":"Journeydb: A benchmark for generative image understanding","author":"Sun","year":"2023","journal-title":"NeurIPS"},{"key":"ref79","author":"Sun","year":"2024","journal-title":"Autoregressive model beats diffusion: Llama for scalable image generation"},{"key":"ref80","author":"Tong","year":"2023","journal-title":"Improving and generalizing flow-based generative models with minibatch optimal transport"},{"key":"ref81","author":"Tong","year":"2023","journal-title":"Simulation-free schr \u201codinger bridges via score and flow matching"},{"key":"ref82","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref84","author":"Wang","year":"2021","journal-title":"Simvlm: Simple visual language model pretraining with weak supervision"},{"key":"ref85","author":"Weber","year":"2024","journal-title":"Maskbit: Embedding-free image generation via bit tokens"},{"key":"ref86","author":"Xie","year":"2024","journal-title":"Show-o: One single transformer to unify multimodal understanding and generation"},{"key":"ref87","author":"Yang","year":"2024","journal-title":"1.58-bit flux"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref90","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"TMLR"},{"key":"ref91","author":"Yu","year":"2024","journal-title":"Randomized autoregressive visual generation"},{"key":"ref92","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref93","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2025","journal-title":"ICLR"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_1"},{"key":"ref95","author":"Zhou","year":"2023","journal-title":"Denoising diffusion bridge models"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"}],"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\/11444312.pdf?arnumber=11444312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:23:12Z","timestamp":1777530192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01544","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}