{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:38Z","timestamp":1783737818219,"version":"3.55.0"},"reference-count":73,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172018,62102008"],"award-info":[{"award-number":["62172018,62102008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01591","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17129-17139","source":"Crossref","is-referenced-by-count":1,"title":["Preacher: Paper-to-Video Agentic System"],"prefix":"10.1109","author":[{"given":"Jingwei","family":"Liu","sequence":"first","affiliation":[{"name":"School of Intelligence Science and Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Yang","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Luo","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba group,Hangzhou,China,310023"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba group,Hangzhou,China,310023"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Technology, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengdi","family":"Wang","sequence":"additional","affiliation":[{"name":"Princeton University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm12020309"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00843"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-023-04675-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08526-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref7","author":"Cui","year":"2024","journal-title":"Hallo2: Long-duration and high-resolution audio-driven portrait image animation"},{"key":"ref8","article-title":"Collaborating with language models for embodied reasoning","volume-title":"NeurIPS 2022 Foundation Models for Decision Making Workshop","author":"Dasgupta"},{"key":"ref9","article-title":"DeepSeek-AI","year":"2025","journal-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning"},{"key":"ref10","article-title":"Longrope: extending llm context window beyond 2 million tokens","author":"Ding","year":"2025","journal-title":"JMLR.org"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3672459"},{"key":"ref12","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","volume-title":"CoRR","author":"Du","year":"2024"},{"key":"ref13","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fcomm.2021.596248"},{"key":"ref15","author":"Gal","year":"2024","journal-title":"Comfygen: Promptadaptive workflows for text-to-image generation"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00543"},{"key":"ref17","article-title":"Large language model based multiagents: A survey of progress and challenges","volume-title":"33rd International Joint Conference on Artificial Intelligence (IJCAI 2024). IJCAI; Cornell","author":"Guo"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2021.36.e66"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00245"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref21","article-title":"Metagpt: Meta programming for a multi-agent collaborative framework","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hong"},{"key":"ref22","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Conference on Robot Learning","author":"Huang"},{"key":"ref23","author":"Jaech","year":"2024","journal-title":"Openai o1 system card"},{"key":"ref24","author":"Jin","year":"2024","journal-title":"A comprehensive survey on process-oriented automatic text summarization with exploration of 11 m -based methods"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.70"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref28","article-title":"A human-inspired reading agent with gist memory of very long contexts","volume-title":"Proceedings of the 41st International Conference on Machine Learning. JMLR.org","author":"Lee"},{"key":"ref29","author":"Letiche","journal-title":"Literature reviews with 11m-based tools"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.859"},{"key":"ref32","article-title":"Long-context llms struggle with long in-context learning","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref33","volume-title":"Luma"},{"key":"ref34","volume-title":"Midjourney"},{"key":"ref35","volume-title":"OpenAI. Sora: Creating video from text","year":"2024"},{"key":"ref36","volume-title":"OpenAIO3-mini"},{"key":"ref37","volume-title":"PIKA"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref40","author":"Ramesh","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref43","author":"Scherbakov","year":"2024","journal-title":"The emergence of large language models (llm) as a tool in literature reviews: an 11 m automated systematic review"},{"key":"ref44","article-title":"Laion400 m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI, number FZJ-2022\u201300923. J\u00fclich Supercomputing Center","author":"Schuhmann"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"ref47","volume-title":"tavus"},{"key":"ref48","author":"Team","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9443-0_35"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0928"},{"key":"ref51","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref52","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3673949"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160420505"},{"key":"ref55","article-title":"Rectified diffusion: Straightness is not your need in rectified flow","volume-title":"International Conference on Learning Representations","author":"Wang"},{"key":"ref56","author":"Wang","year":"2024","journal-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0334"},{"key":"ref58","article-title":"Autosurvey: Large language models can automatically write surveys","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref59","first-page":"128374","article-title":"Genartist: Multimodal 11 m as an agent for unified image generation and editing","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00735"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00549"},{"key":"ref63","author":"Xie","year":"2024","journal-title":"Dreamfactory: Pioneering multi-scene long video generation with a multi-agent framework"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1636"},{"key":"ref66","article-title":"Mastering text-to-image diffusion: Recaptioning, planning, and generating with multi-modal 11 ms","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang"},{"key":"ref67","author":"Yang","year":"2025","journal-title":"Mmada: Multimodal large diffusion language models"},{"key":"ref68","author":"Yuan","year":"2024","journal-title":"Mora: Enabling generalist video generation via a multi-agent framework"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref70","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.728"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.3c01087"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.63317\/48d359hjdvog"},{"key":"ref74","article-title":"An intelligent agentic system for complex image restoration problems","author":"Zhu","year":"2024","journal-title":"CoRR"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-019-03108-w"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445056.pdf?arnumber=11445056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:13:33Z","timestamp":1777529613000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01591","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}