{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:41:42Z","timestamp":1762368102243,"version":"build-2065373602"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204330","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Trust the Model: Compact VLMS as In-Context Judges for Image-Text Data Quality"],"prefix":"10.1109","author":[{"given":"Daulet","family":"Toibazar","sequence":"first","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kesen","family":"Wang","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sherif","family":"Mohamed","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulaziz","family":"Al-Badawi","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulrahman","family":"Alfulayt","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pedro J.","family":"Moreno","sequence":"additional","affiliation":[{"name":"Humain,Riyadh,KSA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024","author":"Team","key":"ref1"},{"volume-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref2"},{"article-title":"OpenAI","volume-title":"Gpt-4 technical report","year":"2023","key":"ref3"},{"volume-title":"Qwen2.5-vl technical report","year":"2025","author":"Bai","key":"ref4"},{"key":"ref5","first-page":"2835","article-title":"LLaVA-onevision: Easy visual task transfer","author":"Li","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"volume-title":"Deepseek-vl: Towards real-world visionlanguage understanding","year":"2024","author":"Lu","key":"ref6"},{"volume-title":"Alignvlm: Bridging vision and language latent spaces for multimodal understanding","year":"2025","author":"Masry","key":"ref7"},{"volume-title":"Global semantic-guided sub-image feature weight allocation in high-resolution large vision-language models","year":"2025","author":"Liang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"volume-title":"What if we recaption billions of web images with llama-3?","year":"2024","author":"Li","key":"ref11"},{"key":"ref12","first-page":"71683","article-title":"Obelics: An open web-scale filtered dataset of interleaved image-text documents","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Lauren\u00e7on","year":"2023"},{"volume-title":"Let\u2019s go shopping (lgs) - web-scale image-text dataset for visual concept understanding","year":"2024","author":"Bai","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.889"},{"key":"ref15","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Ouyang","year":"2022"},{"key":"ref16","first-page":"34 892\u201334 916","article-title":"Visual instruction tuning","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Liu","year":"2023"},{"key":"ref17","article-title":"Lima: Less is more for alignment","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Zhou","year":"2023"},{"volume-title":"Data valuation using neural networks for efficient instruction fine-tuning","year":"2025","author":"Agarwal","key":"ref18"},{"volume-title":"Your vision-language model itself is a strong filter: Towards high-quality instruction tuning with data selection","year":"2024","author":"Chen","key":"ref19"},{"volume-title":"A survey on hallucination in large visionlanguage models","year":"2024","author":"Liu","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.387"},{"journal-title":"Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4","year":"2023","author":"Wei","key":"ref22"},{"key":"ref23","article-title":"Alpagasus: Training a better alpaca with fewer data","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref24","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhu","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event","volume":"139","author":"Radford"},{"volume-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref27"},{"key":"ref28","first-page":"2024","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI"},{"volume-title":"A frustratingly simple approach for end-to-end image captioning","year":"2022","author":"Luo","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2025.059192"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204330.pdf?arnumber=11204330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:19Z","timestamp":1762367839000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204330","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}