{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:57Z","timestamp":1789207617960,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-37335-9_20","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:09Z","timestamp":1789204389000},"page":"363-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Personalization as\u00a0Inverse Planning: Learning Latent Design Intents for\u00a0Agentic Slide Generation via\u00a0Structural Denoising"],"prefix":"10.1007","author":[{"given":"Tianci","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emre","family":"K\u0131c\u0131man","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranveer","family":"Chandra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"20_CR1","unstructured":"Anthropic: Claude sonnet 4: Hybrid reasoning model with superior intelligence for high-volume use cases, and 200k context window. https:\/\/www.anthropic.com\/claude\/sonnet (2025)"},{"key":"20_CR2","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report (2025)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Cao, J., et al.: Multi2: multi-agent test-time scalable framework for multi-document processing. In: Proceedings of The 5th New Frontiers in Summarization Workshop, pp. 135\u2013156 (2025)","DOI":"10.18653\/v1\/2025.newsum-main.10"},{"key":"20_CR4","unstructured":"Chen, L., Chen, J., Goldstein, T., Huang, H., Zhou, T.: Instructzero: Efficient instruction optimization for black-box large language models. arXiv preprint arXiv:2306.03082 (2023)"},{"key":"20_CR5","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities (2025). arXiv:2507.06261 arXiv preprint"},{"key":"20_CR6","unstructured":"Dong, Y., et al.: A survey on code generation with llm-based agents (2025). arXiv preprint arXiv:2508.00083"},{"key":"20_CR7","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Fu, T.J., Wang, W.Y., McDuff, D., Song, Y.: Doc2ppt: automatic presentation slides generation from scientific documents. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 634\u2013642 (2022)","DOI":"10.1609\/aaai.v36i1.19943"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Ge, J., et al.: Autopresent: designing structured visuals from scratch. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2902\u20132911 (2025)","DOI":"10.1109\/CVPR52734.2025.00276"},{"key":"20_CR10","unstructured":"Hahn, M., et al.: Proactive agents for multi-turn text-to-image generation under uncertainty (2024). arXiv:2412.06771 arXiv preprint"},{"key":"20_CR11","doi-asserted-by":"publisher","first-page":"86309","DOI":"10.52202\/079017-2740","volume":"37","author":"W Hu","year":"2024","unstructured":"Hu, W.: Localized zeroth-order prompt optimization. Adv. Neural. Inf. Process. Syst. 37, 86309\u201386345 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR12","unstructured":"Hu, Y., Wan, X.: Ppsgen: learning to generate presentation slides for academic papers. In: IJCAI, pp, 2099\u20132105 (2013)"},{"key":"20_CR13","unstructured":"Jaiswal, S., et al.: Iterative refinement improves compositional image generation (2026). arXiv:2601.15286 arXiv preprint"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Jang, D., et al.: Deckbench: benchmarking multi-agent frameworks for academic slide generation and editing (2026). arXiv:2602.13318 arXiv preprint","DOI":"10.1145\/3770855.3817525"},{"key":"20_CR15","unstructured":"Jung, K., Cho, H., Yun, J., Yang, S., Jang, J., Choo, J.: Talk to your slides: language-driven agents for efficient slide editing. arXiv preprint arXiv:2505.11604 (2025)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Lan, G.: First-order and stochastic optimization methods for machine learning, vol. 1. Springer (2020)","DOI":"10.1007\/978-3-030-39568-1_1"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Start: self-taught reasoner with tools. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 13523\u201313564 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.683"},{"key":"20_CR18","unstructured":"Li, W., Wang, X., Li, W., Jin, B.: A survey of automatic prompt engineering: An optimization perspective. arXiv preprint arXiv:2502.11560 (2025)"},{"key":"20_CR19","unstructured":"Liang, X., Zhang, X., Xu, Y., Sun, S., You, C.: Slidegen: collaborative multimodal agents for scientific slide generation (2025). arXiv preprint arXiv:2512.04529"},{"key":"20_CR20","unstructured":"Liu, C., et al.: Presenting a paper is an art: Self-improvement aesthetic agents for academic presentations (2025). arXiv:2510.05571 arXiv preprint"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, J., Chen, C., Lu, H.: Subject-diffusion: open domain personalized text-to-image generation without test-time fine-tuning. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657469"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Ma, S., Guo, Y., Su, J., Huang, Q., Zhou, Z., Wang, Y.: Talk2image: a multi-agent system for multi-turn image generation and editing (2025). arXiv preprint arXiv:2508.06916","DOI":"10.1609\/aaai.v40i38.40519"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Maheshwari, H., Bandyopadhyay, S., Garimella, A., Natarajan, A.: Presentations are not always linear! gnn meets llm for document-to-presentation transformation with attribution, (2024). arXiv:2405.13095 arXiv preprint","DOI":"10.18653\/v1\/2024.findings-emnlp.936"},{"key":"20_CR24","doi-asserted-by":"publisher","first-page":"53038","DOI":"10.52202\/075280-2308","volume":"36","author":"S Malladi","year":"2023","unstructured":"Malladi, S., Gao, T., Nichani, E., Damian, A., Lee, J.D., Chen, D., Arora, S.: Fine-tuning language models with just forward passes. Adv. Neural. Inf. Process. Syst. 36, 53038\u201353075 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Mondal, I., Shwetha, S., Natarajan, A., Garimella, A., Bandyopadhyay, S., Boyd-Graber, J.: Presentations by the humans and for the humans: Harnessing llms for generating persona-aware slides from documents. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2664\u20132684 (2024)","DOI":"10.18653\/v1\/2024.eacl-long.163"},{"key":"20_CR26","unstructured":"OpenAI: Introducing chatgpt (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"20_CR27","unstructured":"OpenAI: Gpt-image-1 (2025). https:\/\/platform.openai.com\/docs\/models\/gpt-image-1"},{"key":"20_CR28","unstructured":"OpenAI: Introducing gpt-5 (2025). https:\/\/openai.com\/index\/introducing-gpt-5\/"},{"key":"20_CR29","doi-asserted-by":"crossref","unstructured":"Pang, W., Lin, K.Q., Jian, X., He, X., Torr, P.: Paper2poster: towards multimodal poster automation from scientific papers (2025). arXiv:2505.21497 arXiv preprint","DOI":"10.52202\/085713-0530"},{"key":"20_CR30","unstructured":"Park, S., Jeong, J., Kim, Y., Lee, J., Lee, N.: Zip: an efficient zeroth-order prompt tuning for black-box vision-language models. arXiv preprint arXiv:2504.06838 (2025)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Qi, Y., et al.: Learning to instruct: Fine-tuning a task-aware instruction optimizer for black-box llms. In: Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 7707\u20137733 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.407"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Qu, Y., et al.: Igd: instructional graphic design with multimodal layer generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18218\u201318228 (2025)","DOI":"10.1109\/ICCV51701.2025.01693"},{"issue":"4","key":"20_CR33","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1177\/1066896906292274","volume":"14","author":"MG Rojo","year":"2006","unstructured":"Rojo, M.G., Garc\u00eda, G.B., Mateos, C.P., Garc\u00eda, J.G., Vicente, M.C.: Critical comparison of 31 commercially available digital slide systems in pathology. Int. J. Surg. Pathol. 14(4), 285\u2013305 (2006)","journal-title":"Int. J. Surg. Pathol."},{"key":"20_CR34","unstructured":"Ruder, S.: An overview of gradient descent optimization algorithms (2016). arXiv preprint arXiv:1609.04747"},{"key":"20_CR35","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: Pushing the limits of mathematical reasoning in open language models (2024). arXiv preprint arXiv:2402.03300"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Sun, E., Hou, Y., Wang, D., Zhang, Y., Wang, N.X.: D2s: document-to-slide generation via query-based text summarization. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1405\u20131418 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.111"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Tang, W., et\u00a0al.: Slidecoder: layout-aware rag-enhanced hierarchical slide generation from design. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 9026\u20139050 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.458"},{"issue":"6","key":"20_CR38","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1002\/ase.1620","volume":"9","author":"RB Trelease","year":"2016","unstructured":"Trelease, R.B.: From chalkboard, slides, and to e-learning: How computing technologies have transformed anatomical sciences education. Anat. Sci. Educ. 9(6), 583\u2013602 (2016)","journal-title":"Anat. Sci. Educ."},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Venkatesh, K., Dunlop, C., Yanardag, P.: Crea: a collaborative multi-agent framework for creative image editing and generation (2025). arXiv preprintarXiv:2504.05306","DOI":"10.52202\/085713-5705"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Xie, E., Waterfield, D., Kennedy, M., Zhang, A.: Slidebot: a multi-agent framework for generating informative, reliable, multi-modal presentations (2025). arXiv preprint arXiv:2511.09804","DOI":"10.1609\/aaai.v40i48.42124"},{"key":"20_CR41","unstructured":"Xu, R., et al.: Alternating reinforcement learning for rubric-based reward modeling in non-verifiable llm post-training (2026). arXiv:2602.01511 arXiv preprint"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: Pregenie: an agentic framework for high-quality visual presentation generation. arXiv preprint arXiv:2505.21660 (2025)","DOI":"10.18653\/v1\/2025.findings-emnlp.165"},{"key":"20_CR43","unstructured":"Xu, Y., Ma, X., Qiu, J., Zhao, H.: Textual-to-visual iterative self-verification for slide generation (2025). arXiv:2502.15412 arXiv preprint"},{"key":"20_CR44","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: Ip-adapter: text compatible image prompt adapter for text-to-image diffusion models (2023). arXiv preprintarXiv:2308.06721"},{"key":"20_CR45","unstructured":"Yu, Q., et\u00a0al.: Dapo: An open-source llm reinforcement learning system at scale. arXiv preprint arXiv:2503.14476 (2025)"},{"key":"20_CR46","unstructured":"Zelikman, E., Harik, G., Shao, Y., Jayasiri, V., Haber, N., Goodman, N.D.: Quiet-star: Language models can teach themselves to think before speaking (2024). arXiv preprintarXiv:2403.09629"},{"key":"20_CR47","doi-asserted-by":"publisher","first-page":"15476","DOI":"10.52202\/068431-1126","volume":"35","author":"E Zelikman","year":"2022","unstructured":"Zelikman, E., Wu, Y., Mu, J., Goodman, N.: Star: bootstrapping reasoning with reasoning. Adv. Neural. Inf. Process. Syst. 35, 15476\u201315488 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR48","doi-asserted-by":"crossref","unstructured":"Zeng, W., Ouyang, M., Cui, L., Ng, H.T.: Slidetailor: personalized presentation slide generation for scientific papers (2025). arXiv preprint arXiv:2512.20292","DOI":"10.1609\/aaai.v40i41.40758"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Zhan, H., Chen, C., Ding, T., Li, Z., Sun, R.: Unlocking black-box prompt tuning efficiency via zeroth-order optimization. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 14825\u201314838 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.871"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, K., Li, J., Li, G., Shi, X., Jin, Z.: Codeagent: enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 13643\u201313658 (2024)","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"20_CR51","doi-asserted-by":"crossref","unstructured":"Zheng, H., et al.: Pptagent: generating and evaluating presentations beyond text-to-slides. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 14413\u201314429 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.728"},{"key":"20_CR52","unstructured":"Zhu, D., et al.: Paperbanana: automating academic illustration for ai scientists (2026). arXiv:2601.23265 arXiv preprint"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:13:20Z","timestamp":1789204400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}