{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:19Z","timestamp":1777890079479,"version":"3.51.4"},"reference-count":83,"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\/iccv51701.2025.02237","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24135-24146","source":"Crossref","is-referenced-by-count":0,"title":["MUSE-VL: Modeling Unified VLM through Semantic Discrete Encoding"],"prefix":"10.1109","author":[{"given":"Rongchang","family":"Xie","sequence":"first","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Du","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"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 frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref4","volume-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref5","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","volume-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref9","volume-title":"Pixart-\\alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref12","article-title":"A single transformer for scalable vision-language modeling","author":"Chen","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref13","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"Unveiling encoder-free vision-language models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Diao"},{"key":"ref17","article-title":"DreamLLM: Synergistic multimodal comprehension and creation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Dong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref20","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref24","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilib-rium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Illume+: Illuminating unified mllm with dual visual tokenization and diffusion refinement","author":"Huang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref27","article-title":"Mixtral of experts","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref28","first-page":"22185","article-title":"Video-lavit: Unified videolanguage pre-training with decoupled visual-motional tokenization","volume-title":"International Conference on Machine Learning","author":"Jin"},{"key":"ref29","article-title":"Unified language-vision pretraining in 11 m with dynamic discrete visual tokenization","volume-title":"International Conference on Learning Representations","author":"Jin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref32","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02771"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref40","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref41","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref42","article-title":"World model on million-length video and language with ringattention","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"ref45","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"},{"key":"ref46","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02324"},{"key":"ref48","article-title":"Unimod: Efficient unified multimodal transformers with mixture-of-depths","author":"Mao","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers","author":"Peng","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Podell"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00243"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref57","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Emu: Generative pretraining in multimodality","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref60","article-title":"Chameleon Team","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref61","volume-title":"Qwen2.5: A party of foundation models","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref63","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref65","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref66","article-title":"Illume: Illuminating your llms to see, draw, and self-enhance","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref67","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"},{"key":"ref68","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref70","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref72","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref76","article-title":"Yi: Open foundation models by 01. ai","author":"Young","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref77","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref78","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref83","article-title":"Transfusion: Predict the next token and diffuse images with one multimodal model","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhou"}],"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\/11443655.pdf?arnumber=11443655","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:49Z","timestamp":1777613329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443655\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02237","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}