[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84119-en":3,"doc-seo-84119-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84119,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation","PACR-Video proposes a parameter-efficient framework for multi-shot long video extrapolation that maintains recurring entities, scene structure, visual style, and causal event progression without full generator fine-tuning. A frozen text-to-video diffusion transformer is paired with low-rank temporal adapters conditioned on learned shot-role prompt tokens. Recursive prompt bank routing selects narrative-relevant context via adapter gates. A Shot-Local/Story-Global objective combines next-shot reconstruction, cross-shot identity contrast, and prompt sparsity regularization, yielding stronger coherence and preference across six benchmarks.","arXiv :2607 .0648 1v 1 [ cs .CV] 7 Jul 2026  \nPrompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video  \nExtrapolation  \nAnna Córdoba Adam Puente Tercero Nerea Angulo Hijo Mar Linares Tercero  \nJulia Barrientos Ainhoa Miranda Jesús Olivera  \nInstituto de Investigación en Visión Artificial  \ncontact@iiva .tibeu  \nAbstract  \nWe present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-tovideo diffusion transformer frozen and augments it with low-rank temporal adapters conditioned by learned shot-role prompt tokens. To maintain long-horizon coherence, it builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates according to predicted narrative dependencies. A Shot-Local/Story-Global tuning objective combines next-shot reconstruction, cross-shot identity contrast, and prompt sparsity regularization, while an adapter composition schedule balances early-shot visual consistency with later-shot event progression and viewpoint change. Across six multi-shot and long-video benchmarks, PACR-Video outperforms text-to-video, tuning-based, memory-augmented, streaming, and recursive-context baselines on distributional quality, semantic alignment, identity consistency, temporal smoothness, motion stability, transition coherence, and human preference. These results show that compact prompt routing and lightweight temporal adaptation provide sufficient controllable capacity for stable long video extrapolation.  \n1 Introduction  \nLong-form video generation requires more than extending clip duration. A coherent multi-shot sequence must preserve recurring characters, spatial layout, visual style, object affordances, and causal event progression while allowing each shot to introduce new motion, viewpoint, and narrative information. This balance is especially difficult in text-conditioned generation: conditioning signals are often local to the next clip, whereas the errors that matter most accumulate across shots. Asa result, long video systems frequently drift in identity, duplicate or forget objects, flatten event structure, or overfit to early visual context.  \nRecent work has made progress through explicit story memories, shot planning, and recursive context allocation Zhang et al. [2025b], Luo et al. [2026], Zheng et al. [2025], Liu et al. [2026b] . ReCA is particularly relevant: it frames multi-shot extrapolation as a recursive allocation problem, deciding which previous context should condition each future shot Liu et al. [2026b] . However, many existing approaches either fine-tune large portions of the generator or rely on external memory modules whose capacity and retrieval behavior can become brittle over long horizons. This raises a natural question: can a frozen video diffusion backbone be steered with enough precision using only lightweight, parameter-efficient modules?  \n37th Conference on Neural Information Processing Systems (NeurIPS 2023) .  \nFigure 1: PACR-Video overview. The method extrapolates a long multi-shot video by recursively summarizing prior shots into compact prompts, selecting narrative-relevant context, and steering a stable frozen generator through lightweight adapters instead of full-model fine-tuning or large external memory.  \nWe propose PACR-Video, a Prompt-Adapter Context Routing framework for parameter-efficient multi-shot long video extrapolation. PACR-Video inserts low-rank temporal adapters into a frozen text-to-video diffusion transformer and conditions them with learned shot-role prompt tokens. Instead of storing dense video memories, the model maintains a recursive prompt bank containing compact entity, location, action, and style prompts extracted from previous shots. At generation time, these prompts are routed","cbCain3OBmMdELMl","https://ap.wps.com/l/cbCain3OBmMdELMl","pdf",2818069,1,10,"English","en",105,"# Introduction\n# Related Work","[{\"question\":\"What problem does PACR-Video address in long-form multi-shot video generation?\",\"answer\":\"It targets identity drift, object duplication/forgetting, flattened event structure, and accumulated errors across shots when generating long sequences from text.\"},{\"question\":\"How does PACR-Video achieve parameter-efficient control without full generator fine-tuning?\",\"answer\":\"It keeps a text-to-video diffusion transformer frozen and adds low-rank temporal adapters conditioned by learned shot-role prompt tokens.\"},{\"question\":\"What mechanism helps PACR-Video maintain long-horizon coherence across shots?\",\"answer\":\"It builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates based on predicted narrative dependencies.\"}]",1784193027,25,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"prompt-adapter-context-routing-for-parameter-efficient-multi-shot-long-video-extrapolation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/prompt-adapter-context-routing-for-parameter-efficient-multi-shot-long-video-extrapolation/84119/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does PACR-Video address in long-form multi-shot video generation?","Question",{"text":75,"@type":76},"It targets identity drift, object duplication/forgetting, flattened event structure, and accumulated errors across shots when generating long sequences from text.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PACR-Video achieve parameter-efficient control without full generator fine-tuning?",{"text":80,"@type":76},"It keeps a text-to-video diffusion transformer frozen and adds low-rank temporal adapters conditioned by learned shot-role prompt tokens.",{"name":82,"@type":73,"acceptedAnswer":83},"What mechanism helps PACR-Video maintain long-horizon coherence across shots?",{"text":84,"@type":76},"It builds a recursive prompt bank that stores compact entity, location, action, and style prompts from previous shots, then routes them through adapter gates based on predicted narrative dependencies.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]