{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T04:28:05Z","timestamp":1764563285497,"version":"3.46.0"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819549566"},{"type":"electronic","value":"9789819549573"}],"license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4957-3_13","type":"book-chapter","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T04:24:13Z","timestamp":1764563053000},"page":"155-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Language and\u00a0Vision: Fine-Tuning Latent Diffusion Models for\u00a0Robust Text-to-Image Generation"],"prefix":"10.1007","author":[{"given":"Daniel","family":"Vadranapu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhiram Yadav","family":"Myla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charan Ramtej","family":"Kodi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"13_CR1","unstructured":"Dash, S.R., Sahu, S., Majumdar, A., Panda, R.: T2F: text to face generation using deep neural networks. In: WACV (2020)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"13_CR3","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"13_CR4","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems (2014)"},{"key":"13_CR5","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"13_CR6","unstructured":"Ho, J., Jaini, P., Abbeel, P.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems (2020)"},{"key":"13_CR7","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Kodi, C.R., Bharath Vemula, S.S., Pulipeta, N.K., Krishnan, V.V., Rajkumar, V., Musalaya, B.G.: Toward efficient multi-attribute prediction: lessons from political bias detection. In: International Conference on Computing and Communication Networks, pp. 149\u2013164. Springer, Cham (2024)","DOI":"10.1007\/978-981-96-3250-3_13"},{"key":"13_CR9","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"13_CR10","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., et al.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"13_CR12","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36, pp. 34892\u201334916 (2023)"},{"key":"13_CR13","unstructured":"Martin, K.: Tackling bias in AI: ensuring fairness in machine learning models. Ethical AI J. (2021). https:\/\/www.ethicalaijournal.com\/tackling-bias-in-ai"},{"key":"13_CR14","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)"},{"key":"13_CR15","unstructured":"Ng, A.: Responsible AI: guidelines for ethical AI development. AI Ethics Rev. (2020). https:\/\/www.aireview.com\/responsible-ai-guidelines"},{"key":"13_CR16","unstructured":"Patel, N.: The ethical considerations of generative adversarial networks. J. AI Ethics (2023). https:\/\/www.journalofaie.com\/ethical-considerations-of-gans"},{"key":"13_CR17","unstructured":"Ramesh, A., et al.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"13_CR18","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML (2016)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. arXiv preprint arXiv:2112.10752 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"13_CR21","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487 (2022)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: Attngan: fine-grained text to image generation with attentional generative adversarial networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, M., et al.: DM-GAN: dynamic memory generative adversarial networks for text-to-image synthesis. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00595"}],"container-title":["Lecture Notes in Computer Science","Multi-disciplinary Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4957-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T04:24:23Z","timestamp":1764563063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4957-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"ISBN":["9789819549566","9789819549573"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4957-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"2 December 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIWAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multi-disciplinary Trends in Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ho Chi Minh City","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"3 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miwai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miwai25.miwai.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}