{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:32Z","timestamp":1778051552788,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00054","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"472-482","source":"Crossref","is-referenced-by-count":0,"title":["Interleaved Vision-and-Language Generation via Generative Voken"],"prefix":"10.1109","author":[{"given":"Kaizhi","family":"Zheng","sequence":"first","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuehai","family":"He","sequence":"additional","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin Eric","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California,Santa Cruz"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Jointly training large autoregressive multi-modal models","author":"Aiello","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref4","author":"Bai","year":"2025","journal-title":"Qwen2.5-vl technical report"},{"key":"ref5","first-page":"65","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"},{"key":"ref6","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref7","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35142-6_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref11","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":"ref12","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.405"},{"key":"ref16","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1529"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref20","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"International Conference on Machine Learning","author":"Houlsby"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref23","article-title":"and Max Welling. Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref24","article-title":"Generating images with multimodal language models","author":"Koh","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.3"},{"key":"ref27","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref29","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref32","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref35","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International Conference on Machine Learning","author":"Ramesh"},{"key":"ref36","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"International conference on machine learning","author":"Reed"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref41","first-page":"29","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref43","article-title":"Multimodal dialogue response generation","author":"Sun","year":"2021"},{"key":"ref44","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023"},{"key":"ref45","article-title":"Emu: Generative pretraining in multimodality","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.162"},{"key":"ref47","year":"2024","journal-title":"Chameleon: Mixed-modal early-fusion foundation models"},{"key":"ref48","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref49","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume":"34","author":"Tsimpoukelli","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","author":"Wang","year":"2024","journal-title":"Emu3: Next-token prediction is all you need"},{"key":"ref53","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref54","article-title":"Visual chatgpt: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023"},{"key":"ref55","author":"Wu","year":"2023","journal-title":"Next-gpt: Any-to-any multimodal llm"},{"key":"ref56","article-title":"Show-o: One single transformer to unify multi-modal understanding and generation","author":"Xie","year":"2025","journal-title":"ICLR"},{"issue":"3","key":"ref57","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022"},{"key":"ref58","article-title":"Scaling autoregressive multi-modal models: Pretraining and instruction tuning","author":"Yu","year":"2023"},{"key":"ref59","author":"Zhang","year":"2021","journal-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling"},{"key":"ref60","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492060.pdf?arnumber=11492060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:30Z","timestamp":1778048250000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00054","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}