{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:57:30Z","timestamp":1780329450709,"version":"3.54.1"},"reference-count":98,"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\/iccv51701.2025.01653","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17793-17806","source":"Crossref","is-referenced-by-count":1,"title":["Tikzero: Zero-Shot Text-Guided Graphics Program Synthesis"],"prefix":"10.1109","author":[{"given":"Jonas","family":"Belouadi","sequence":"first","affiliation":[{"name":"University of Mannheim,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eddy","family":"Ilg","sequence":"additional","affiliation":[{"name":"University of Technology Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Margret","family":"Keuper","sequence":"additional","affiliation":[{"name":"University of Mannheim,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hideki","family":"Tanaka","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masao","family":"Utiyama","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raj","family":"Dabre","sequence":"additional","affiliation":[{"name":"National Institute of Information and Communications Technology,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen","family":"Eger","sequence":"additional","affiliation":[{"name":"University of Technology Nuremberg,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Ponzetto","sequence":"additional","affiliation":[{"name":"University of Mannheim,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Tantau","year":"2023","journal-title":"The TikZ and PGF Packages"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2701"},{"key":"ref3","article-title":"AutomaTikZ: Text-guided synthesis of scientific vector graphics with TikZ","volume-title":"The Twelfth International Conference on Learning Representations","author":"Belouadi","year":"2024"},{"key":"ref4","article-title":"ScImage: How good are multimodal large language models at scientific text-to-image generation?","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref5","article-title":"DiagrammerGPT: Generating open-domain, open-platform diagrams via LLM planning","volume-title":"First Conference on Language Modeling","author":"Zala","year":"2024"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref7","article-title":"Zero-shot learning with semantic output codes","author":"Palatucci","year":"2009","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"OpenAI","year":"2023","journal-title":"GPT-4 technical report"},{"key":"ref9","article-title":"Neuro-symbolic program synthesis","volume-title":"International Conference on Learning Representations","author":"Parisotto","year":"2017"},{"key":"ref10","first-page":"990","article-title":"RobustFill: Neural program learning under noisy I\/O","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Devlin","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454080"},{"key":"ref12","first-page":"1666","article-title":"Synthesizing programs for images using reinforced adversarial learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Ganin","year":"2018"},{"key":"ref13","first-page":"6062","article-title":"Learning to infer graphics programs from hand-drawn images","volume-title":"Thirty-second Conference on Neural Information Processing Systems","author":"Ellis","year":"2018"},{"key":"ref14","article-title":"Write, execute, assess:Program synthesis with a REPL","volume-title":"Advances in Neural Information Processing Systems","author":"Ellis","year":"2019"},{"key":"ref15","article-title":"Re-thinking inverse graphics with large language models","author":"Kulits","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1422"},{"key":"ref17","article-title":"Diffusion on syntax trees for program synthesis","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Kapur","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00578"},{"key":"ref19","article-title":"Learning to infer and execute 3D shape programs","volume-title":"International Conference on Learning Representations","author":"Tian","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10270-023-01105-5"},{"key":"ref21","article-title":"What matters when building vision-language models?","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Lauren\u00e7on","year":"2024"},{"key":"ref22","author":"Lauren\u00e7on","year":"2024","journal-title":"Building and better understanding vision-language models: insights and future directions"},{"key":"ref23","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal LLMs","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Tong","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01508"},{"key":"ref25","article-title":"MM1.5: Methods, analysis & insights from multimodal LLM fine-tuning","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-8912-5_6"},{"key":"ref28","author":"Bubeck","year":"2023","journal-title":"Sparks of artificial general intelligence: Early experiments with GPT-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01366"},{"key":"ref30","author":"Zhang","year":"2023","journal-title":"Controllable text-to-image generation with GPT-4"},{"issue":"2","key":"ref31","article-title":"How Is ChatGPT\u2019s Behavior Changing Over Time?","volume-title":"Harvard Data Science Review","volume":"6","author":"Chen","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01434"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3618364"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0376"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.63317\/3xj9fvb29rby"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457261"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/22949.22950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/191666.191719"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3654992"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Ramesh","year":"2021"},{"key":"ref43","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with CLIP latents"},{"key":"ref44","first-page":"19822","article-title":"CogView: Mastering text-to-image generation via transformers","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021","author":"Ding","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref46","article-title":"FigGen: Text to scientific figure generation","author":"Rodriguez","year":"2023","journal-title":"The First Tiny Papers Track at ICLR 2023, Tiny Papers @ ICLR 2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00368"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref50","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Sohl-Dickstein"},{"key":"ref51","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591520"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref57","author":"Grattafiori","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref59","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"ref61","author":"Sanh","year":"2020","journal-title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter"},{"key":"ref62","author":"Touvron","year":"2023","journal-title":"LLaMA: Open and efficient foundation language models"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref65","author":"Beyer","year":"2024","journal-title":"PaliGemma: A versatile 3B VLM for transfer"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref67","article-title":"DreamSim: Learning new dimensions of human visual similarity using synthetic data","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Fu","year":"2023"},{"key":"ref68","article-title":"When does perceptual alignment benefit vision representations?","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Sundaram","year":"2024"},{"key":"ref69","article-title":"Demystifying MMD GANs","volume-title":"International Conference on Learning Representations","author":"Bi\u0144kowski","year":"2018"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3510454.3528648"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5359"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref75","author":"Hui","year":"2024","journal-title":"Qwen2.5-Coder technical report"},{"key":"ref76","article-title":"Who evaluates the evaluations? objectively scoring text-to-image prompt coherence metrics with t2IScorescore (TS2)","volume-title":"The Thirtyeighth Annual Conference on Neural Information Processing Systems","author":"Saxon","year":"2024"},{"key":"ref77","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781107337855","volume-title":"BestWorst Scaling: Theory, Methods and Applications","author":"Louviere","year":"2015"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1095"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2074"},{"key":"ref80","article-title":"MaxDiff analysis: Simple counting, individual-level logit, and HB","author":"Orme","year":"2009","journal-title":"Sawtooth Software Research Paper Series"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/0267-3649(94)90017-5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"ref83","article-title":"Improving multimodal datasets with image captioning","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Nguyen","year":"2023"},{"key":"ref84","article-title":"BLIP3KALE: Knowledge augmented large-scale dense captions","volume-title":"Synthetic Data for Computer Vision Workshop @ CVPR 2025","author":"Awadalla","year":"2025"},{"key":"ref85","author":"Li","year":"2024","journal-title":"What if we recaption billions of web images with LLaMA-3?"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref88","article-title":"LanguageBind: Extending video-language pretraining to n modality by language-based semantic alignment","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"},{"key":"ref89","article-title":"OpenAI","year":"2024","journal-title":"Learning to reason with LLMs"},{"key":"ref90","author":"DeepSeek-AI","year":"2025","journal-title":"DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning"},{"key":"ref91","article-title":"UltraEdit: Instruction-based fine-grained image editing at scale","volume-title":"The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhao","year":"2024"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1027\/1614-2241.2.2.57"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.27"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1053"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.151"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.252"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1998.710701"},{"key":"ref98","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"Kusner","year":"2015"}],"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\/11446126.pdf?arnumber=11446126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:38Z","timestamp":1777613618000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01653","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}