{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T04:05:13Z","timestamp":1749960313332,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819682973","type":"print"},{"value":"9789819682980","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-8298-0_31","type":"book-chapter","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:21:38Z","timestamp":1749925298000},"page":"389-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VisCon-100K: Leveraging Contextual Web Data for\u00a0Fine-Tuning Vision Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2848-7095","authenticated-orcid":false,"given":"Gokul Karthik","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1156-9289","authenticated-orcid":false,"given":"Iheb","family":"Chaabane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4492-4152","authenticated-orcid":false,"given":"Kebin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,15]]},"reference":[{"key":"31_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., et al.: Flamingo: a visual language model for few-shot learning. NeurIPS 35, 23716\u201323736 (2022)","journal-title":"NeurIPS"},{"key":"31_CR2","unstructured":"Chen, G.H., Chen, S., Zhang, R., et\u00a0al.: Allava: Harnessing GPT4V-synthesized data for a lite vision-language model. arXiv preprint arXiv:2402.11684 (2024)"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Li, J., Dong, X., et\u00a0al.: ShareGPT4V: Improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793 (2023)","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"31_CR4","unstructured":"Huang, S., Dong, L., Wang, W., et\u00a0al.: Language is not all you need: aligning perception with language models. In: NeurIPS (2024)"},{"key":"31_CR5","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"31_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"31_CR7","unstructured":"Lauren\u00e7on, H., Saulnier, L., Tronchon, L., et\u00a0al.: Obelics: an open web-scale filtered dataset of interleaved image-text documents. In: NeurIPS, vol. 36 (2024)"},{"key":"31_CR8","unstructured":"Lauren\u00e7on, H., Tronchon, L., Cord, M., Sanh, V.: What matters when building vision-language models? arXiv preprint arXiv:2405.02246 (2024)"},{"key":"31_CR9","unstructured":"Li, B., Wang, R., Wang, G., et\u00a0al.: Seed-bench: Benchmarking multimodal LLMS with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)"},{"key":"31_CR10","unstructured":"Li, X., Li, J.: Angle-optimized text embeddings. arXiv preprint arXiv:2309.12871 (2023)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR, pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"31_CR12","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2024)"},{"key":"31_CR13","unstructured":"Liu, S., Fan, L., Johns, E., et\u00a0al.: Prismer: a vision-language model with multi-task experts. arXiv preprint arXiv:2303.02506 (2023)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cao, J., Liu, C., et\u00a0al.: Datasets for large language models: a comprehensive survey. arXiv preprint arXiv:2402.18041 (2024)","DOI":"10.21203\/rs.3.rs-3996137\/v1"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Duan, H., Zhang, Y., et\u00a0al.: Mmbench: Is your multi-modal model an all-around player? arXiv preprint arXiv:2307.06281 (2023)","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"31_CR16","unstructured":"Lu, P., Mishra, S., Xia, T., et\u00a0al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: NeurIPS, pp. 2507\u20132521 (2022)"},{"key":"31_CR17","unstructured":"Lu, P., Peng, B., Cheng, H., et\u00a0al.: Chameleon: plug-and-play compositional reasoning with large language models. In: NeurIPS (2024)"},{"key":"31_CR18","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Rasheed, H., Maaz, M., Shaji, S., et\u00a0al.: Glamm: Pixel grounding large multimodal model. In: CVPR, pp. 13009\u201313018 (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Bensaid, D., Brody, S., et\u00a0al.: Fusecap: Leveraging large language models to fuse visual data into enriched image captions. arXiv preprint arXiv:2305.17718 (2023)","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"31_CR21","unstructured":"Team, G., Mesnard, T., Hardin, C., et\u00a0al.: Gemma: Open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"31_CR22","unstructured":"Touvron, H., Martin, L., Stone, K., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"31_CR23","unstructured":"Wang, G., Cheng, S., Zhan, X., et\u00a0al.: Openchat: Advancing open-source language models with mixed-quality data. arXiv preprint arXiv:2309.11235 (2023)"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Yue, X., Ni, Y., Zhang, K., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: CVPR, pp. 9556\u20139567 (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"31_CR25","unstructured":"Zhang, Y., Gong, K., Zhang, K., et\u00a0al.: Meta-transformer: a unified framework for multimodal learning. arXiv preprint arXiv:2307.10802 (2023)"},{"key":"31_CR26","unstructured":"Zheng, L., Chiang, W.L., Sheng, Y., et\u00a0al.: Judging LLM-as-a-judge with MT-bench and chatbot arena. In: NeurIPS (2024)"},{"key":"31_CR27","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Data Science: Foundations and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8298-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:21:55Z","timestamp":1749925315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8298-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819682973","9789819682980"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8298-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}