{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:32:07Z","timestamp":1778081527103,"version":"3.51.4"},"reference-count":46,"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\/wacv61042.2026.00122","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1191-1200","source":"Crossref","is-referenced-by-count":2,"title":["mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval"],"prefix":"10.1109","author":[{"given":"Kyeong Seon","family":"Kim","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baek","family":"Seong-Eun","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lee","family":"Jung-Mok","sequence":"additional","affiliation":[{"name":"POSTECH"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae-Hyun","family":"Oh","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00217"},{"key":"ref3","article-title":"Llm2vec: Large language models are secretly powerful text encoders","author":"BehnamGhader","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA63115.2024.00023"},{"key":"ref5","article-title":"Leveraging large language models for scalable vector graphics-driven image understanding","author":"Cai","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00525"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00973"},{"key":"ref8","first-page":"16351","article-title":"Deepsvg: A hierarchical generative network for vector graphics animation","volume":"33","author":"Carlier","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758287"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61042.2026.00478"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.311"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref13","volume-title":"Scalable vector graphics (SVG) 1.0 specification","author":"Ferraiolo","year":"2000"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref15","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11210204"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00190"},{"key":"ref18","author":"Jiang","year":"2023","journal-title":"Mistral 7b"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.603"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"ref21","article-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks","author":"Jiang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.740"},{"key":"ref23","article-title":"Nv-embed: Improved techniques for training llms as generalist embedding models","author":"Lee","year":"2024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.546"},{"key":"ref25","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00802"},{"key":"ref28","first-page":"6","article-title":"Sfrembedding-mistral: enhance text retrieval with transfer learning","volume":"3","author":"Meng","year":"2024","journal-title":"Salesforce AI Research Blog"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref30","article-title":"Generative representational instruction tuning","volume-title":"ICLR 2024 Workshop: How Far Are We From AGI","author":"Muennighoff"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref32","first-page":"57","article-title":"Can large language models understand symbolic graphics programs?","author":"Qiu","year":"2024"},{"key":"ref33","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01508"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01835"},{"key":"ref37","article-title":"Strokenuwa: Tokenizing strokes for vector graphic synthesis","author":"Tang","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.122"},{"key":"ref39","article-title":"Visually descriptive language model for vector graphics reasoning","author":"Wang","year":"2024"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52734.2025.02206","article-title":"Chat2svg: Vector graphics generation with large language models and image diffusion models","volume-title":"CVPR","author":"Wu"},{"key":"ref41","article-title":"Svgfusion: Scalable text-to-svg generation via vector space diffusion","author":"Xing","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00435"},{"key":"ref43","article-title":"Omnisvg: A unified scalable vector graphics generation model","author":"Yang","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5669-8_5"},{"key":"ref46","article-title":"Vg-bench: Evaluating large language models on vector graphics understanding and generation","author":"Zou","year":"2024","journal-title":"CoRR"}],"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\/11492556.pdf?arnumber=11492556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:57:39Z","timestamp":1778047059000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00122","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}